Walton County, Georgia, didn’t ask to become a test case for the artificial intelligence (AI) infrastructure boom. Meta, the company behind Facebook, Instagram, and WhatsApp, decided for them.

In 2018, the company broke ground in Social Circle, a small town an hour east of Atlanta with about 5,000 residents, to build one of its largest U.S. data centers. It opened in 2020.

Local officials called it a win. Shane Short, president and CEO of the Development Authority of Walton County, said the plant generates about $10 million annually in property tax revenue and has led to road improvements and expanded broadband.

Electric vehicle maker Rivian followed Meta’s lead and began construction on a plant near Social Circle in September 2025, adding to the area’s rapid industrial growth.

But for residents, the shift from a largely rural, agricultural economy to an energy-intensive industrial one has put new pressure on power and water systems.

“They’re seeing higher water and power bills, worse air quality, and very few jobs in return for this, while large corporations get tax benefits,” said Ahmed Saeed, an assistant professor in Georgia Tech’s School of Computer Science, describing why residents in some communities push back on new data center development.

Saeed and Josiah Hester, associate professor, Catherine M. and James E. Allchin Early Career Professor in the College of Computing, and director of the Center for Advancing Responsible Computing, have spent the past year studying the energy, water, and financial demands associated with these facilities, and how those costs are distributed.

Betting on Demand

AI data centers run on specialized chips that use large amounts of electricity. That power generates heat, which requires energy- and water-intensive cooling.

The state is adding capacity based on expected demand, not current use.

Last year, the Georgia Public Service Commission approved an estimated $16 billion expansion for Georgia Power to support that growth. It is expected to produce about 10 gigawatts of electricity at a given time. That’s enough energy to power about 7.5 million homes for a year.

If that demand materializes, the electricity is used. If it doesn’t, the cost still has to be paid.

Grid Stability

“Those workloads can put a very large demand on the grid all at once, and then remove it just as quickly,” Saeed said. “That sudden change is difficult for the system to handle.”

That volatility is a separate issue. Even if data center operators pay for the infrastructure they use, large swings in demand can still strain grid operations, especially during peak periods or extreme weather.

What Comes Next

Back in Walton County, the Meta facility is already attracting additional data centers.

Each new site adds power and water infrastructure designed to operate for decades. The servers inside need to be upgraded every few years. Saeed and Hester said if Georgia wants to remain an AI and cloud hub, the state needs to set the terms, and companies need to meet them.

That starts with disclosure — how much power data centers draw from the grid, how that demand spikes, and how much water they use. It includes clear expectations for how those facilities respond when the grid is under stress, and protections for the communities where they’re built.

Saeed and Hester say that “build it and hope” is not a strategy.

In December, The Conversation hosted a webinar on AI’s revolutionary role in drug discovery and development.

Science and technology editor Eric Smalley interviewed Jeffrey Skolnick, eminent scholar in computational systems biology at Georgia Institute of Technology, and Benjamin P. Brown, assistant professor of pharmacology at Vanderbilt University.

Skolnick has developed AI-based approaches to predict protein structure and function that may help with drug discovery and finding off-label uses of existing drugs. Brown’s lab works on creating new computer models that make drug discovery faster and more reliable. Below is a condensed and edited version of the interview.

Let’s start with the big picture. How is AI changing biomedical research and drug discovery, and what is the potential we are talking about?

Skolnick: The upside, potentially, is very large. One of the frustrating things about drug discovery is that, in spite of the fact that the people doing it are extraordinarily intelligent and have done an extraordinarily good job, the success rate is very low. About 1 in 5 drugs will have negative health effects that outweigh its benefits. Of the ones that pass, roughly half don’t work.

In drug development, there are several key issues: Can you predict which target is driving a particular disease? Once this target is identified, how can you guarantee the drug is going to work and isn’t simultaneously going to kill you?

These are outstanding problems in drug discovery in which AI can play an important, though not 100% guaranteed, role. Unlike us, AI can look at basically all available knowledge. On a good day it makes strong and true connections called “insights,” and on a bad day it does what is called “hallucinating” and sees things that are weak and probably false.

At the end of the day, many diseases do not have a cure. Most diseases are maintained, such as high cholesterol or autoimmune conditions. A treatment for cancer might buy you five years, and now you’re in Stage 4 and you’ve exhausted all the standard care drugs. AI can play a role to suggest alternatives where there are none.

Let’s give some basic definitions here. When we use the word drug, we’re talking about a wide range of therapies. Can you explain the range – we’ve got small molecule drugs, biologics, gene therapies, cell therapies.

Brown: We have fairly large molecules in our bodies called proteins. They are like machines that carry out specific functions and interact with one another. Oftentimes, when we’re trying to treat disease, we’re trying to alter functions of specific proteins. Many drugs, like aspirin and Tylenol, are small molecules that can fit into a protein and change its function. Fundamentally, drugs don’t have to just interact with proteins, but this is a major way in which our current repertoire of medications work.

There are also proteins that act like drugs, such as antibodies. When you receive a vaccine for a virus, your body is basically given instructions on how to develop antibodies. These antibodies will target some part of that virus. Your body is creating these big molecules, much bigger than aspirin, to go and interact with foreign proteins in a different way. Gene therapy is a larger step beyond that.

So these modalities – molecule, protein, antibody or gene – are very different types of molecules. They have different scales and rules, so the way you approach designing and discovering them various widely.

Can you briefly explain artificial neural networks, and what the “deep” in deep learning means?

Skolnick: AlphaFold, developed by DeepMind, involved understanding how neural networks worked. They built a network with a lot of inputs, which are stimuli, and outputs with different weights, similar to how your brain actually works. These simple connections, or neurons, have reinforcement learning.

They also created sophisticated neural networks, such as transformers, which do specific things like a special-purpose tool that can learn, and they added a mechanism called “attention,” which amplifies critical details. Super neural networks with transformers is what we call deep learning. These now have literally billions, if not trillions, of parameters.

Essentially, these machines can learn higher order correlations between events, meaning the patterns of conditional interactions that depend on the properties of multiple things simultaneously. In these higher order correlations, AI has the potential to see previously unknown things that are embedded in petabytes (a unit of data equivalent to half of the contents of all U.S. academic research libraries of biological data.

AlphaFold, which predicts three-dimensional, bioactive forms of a protein, has millions of sequences and a couple of hundred thousand structures. It can tell you, based on a particular pattern, what small molecule to design that sticks to a protein to induce some kind of structural shift.

How is this technology being used in biomedical research to understand molecular dynamics or, essentially, the biological processes involved in health and disease?

Brown: In 2013, there was a Nobel Prize for molecular dynamics simulations, computational tools that help you understand the motions of molecules as they move according to physics. There’s a huge body of scientific research built around those ideas.

AI and deep learning are large right now, but it’s worth mentioning that for the last decade and a half, people have been using much smaller machine learning algorithms to help design drugs. A lot of the ideas, such as [using machine learning for virtual screening], are not new and have been in practice for a while.

With AlphaFold’s technologies to help people design proteins and predict their structure, we’ve changed how we think about a lot of these problems. We have this new repertoire of approaches to build ideas around and to start thinking about drug discovery.

From 20 years ago to now, what has today’s AI technology done in terms of scale of change in this process?

Skolnick: A lot of diseases, like cancers, are caused by a collection of malfunctioning proteins. AI now allows us to start to think conceptually about how these diseases are organized and related to each other.

Diseases tend to co-occur. For example, if you have hyperthyroidism, you’re very likely to develop Alzheimer’s. Kind of weird, right? We can look at pieces, but AI can look at all the information, integrate the collective behavior and then identify common drivers. This allows you to construct disease interrelationships which offer the possibility of broad spectrum treatments that could treat whole collections of diseases rather than narrow-spectrum treatments.

Relatedly, AI also can help us understand disease trajectories. Diseases that tend to co-occur often present themselves consecutively. You have disease 1, it gives you disease 2, then gives you disease 3. This suggests that if you go back to the root with disease 1, you may be able to stop a whole bunch of stuff. You can’t analyze millions of trajectories and millions of data without a tool, so you couldn’t do this before.

This holds a lot of promise, but one also must be careful not to overpromise. It will help, it will accelerate, but it is not a substitute yet for real experiments, real clinical validation and trials.

This article is republished from The Conversation under a Creative Commons license. Read the original article.

It’s not glamorous. It’s not trendy. In fact, it’s downright grubby. But the work that a Georgia Tech researcher and his students are doing is improving campus sustainability, one pound of food waste at a time. 

Working with collaborators at University College London (UCL), Georgia Tech researchers used computer models to reveal how, during early development, forces generated by cells physically pull the neural tube closed — like a drawstring. This discovery offers new insight into a critical process that, when disrupted, can result in severe birth defects such as spina bifida.

“Understanding a complex developmental process like neural tube closure requires a highly interdisciplinary approach,” said Shiladitya Banerjee, an associate professor in the School of Physics. “By combining advanced biological imaging with theoretical physics, we were able to uncover the mechanical rules that drive cells to close the tube. My lab builds computational models to uncover the physical rules of living systems. The neural tube is an ideal focus because its formation requires incredible mechanical coordination.”

The researchers presented their findings in Current Biology. 

Closing the Gap

The UCL team studied mouse embryos, which develop similarly to humans, and Georgia Tech researchers used that data to construct their models. From the data, they identified the fundamental physics mechanism that enables neural tube closure in part of the brain. This mechanism, called a “purse string,” is made of actin, a pivotal protein that forms a cell’s skeletal structure. As the purse strings tighten, the tube closes.

“These actin molecules are very important because they give rigidity and shape to cells,” Banerjee said.

“During neural tube closure, actin filaments form a ring around the opening and engage molecular motors — proteins that generate forces inside cells,” he said. “As these motors pull on the actin, they generate tension that tightens the ring and draws the tube closed.”

Stretching to Fit

As the actin ring tightens, cells stretch and elongate, causing them to align and move together in a synchronized pattern, like a school of fish. This coordination allows the cells to move faster and more efficiently, increasing tension and driving a feedback loop that helps seal the neural tube.

The team built a computer model to show how this feedback loop leads to successful neural tube formation. Further research using the model could help explain why the neural tube fails to close.

“Physics-based modeling of cell and tissue mechanics allows us to connect the dots between developmental stages in a way that is both robust and quantitative, simulating experiments that are impossible in biological tissues,” said Gabriel Galea, the study co-author and UCL group leader. “In this case, it allowed us to explain how a cell’s mechanical experience impacts its current and future shapes during a critical step of brain development.”

Beyond neural tube development, the findings highlight the power of physics-based modeling to explain complex biological processes that can’t be observed directly. The researchers say this approach could be applied to other stages of human development where forces, motion, and timing are just as critical.

The computational research at Banerjee Lab is funded by the National Institute of General Medical Sciences

Fernanda Pérez-Verdugo, Eirini Maniou, Gabriel L. Galea, Shiladitya Banerjee, “Mechanosensitive feedback organizes cell shape and motion during hindbrain neuropore morphogenesis,” Current Biology, 2026.

DOI: 10.1016/j.cub.2026.02.068 

“A small vial of genetically engineered cells can contain multiple millions of dollars’ worth of intellectual property and require several years of work to develop,” said Corey Wilson, a professor in Georgia Tech’s School of Chemical and Biomolecular Engineering (ChBE). “Accordingly, the protection of high-value engineered cell lines has become critically important to the biotechnology industry.”

Wilson and his research team have published their findings in Science Advances demonstrating the effectiveness of their new biological security technology, known as GeneLock™, in protecting high-value engineered cell lines.

GeneLock is a cybersecurity-inspired technology that protects valuable genetic material directly at the DNA level. To demonstrate its strength, Wilson’s team conducted what they describe as a first-of-its-kind biohackathon, detailed in the new paper, to simulate unauthorized access. 

“GeneLock greatly improves our ability to protect high-value engineered cell lines by expanding security from the lab environment to the genetic level,” Wilson said.

Economic Impact

What are the stakes? Estimates place the global market for high-value genetic materials at more than $1.5 trillion, projected to reach $8 trillion by 2035. The use of these materials ranges from advanced medicines and proprietary research enzymes to specialty chemicals and sustainable materials.

Currently, the protection of high-value cell lines depends on physical safeguards such as restricted lab access and secure facilities, Wilson explained.

“The key weakness of physical security measures is once circumvented, there are typically no measures in place to protect valuable cells from theft, abuse, or unauthorized use,” Wilson said. 

“Once a sample leaves the building, the DNA it carries typically remains fully functional. This is like placing an unlocked cellphone in a desk drawer. Anyone who gains access to the drawer can view sensitive content on the phone­­­­­­­—or in this case will have full access to the valuable cell line.”

Genetic Passcode Protection

The GeneLock biological security technology developed by Wilson and his team places a passcode on engineered cells, akin to those used on ATM machines and protected cellphones.

Instead of leaving a valuable gene in readable form, the team scrambles the DNA sequence of interest. The scrambled genetic asset remains in a nonfunctional state unless the living cell where it resides receives the correct sequence of chemical inputs. Those inputs act as a molecular passcode.

“Only the right combination, delivered in the right order, rearranges the DNA into a working form,” Wilson said.

Biohackathon Security Test

To evaluate the technology, the researchers organized a blue team and a red team in what they describe as an ethical biohackathon. The blue team designed the encrypted DNA sequence, while the red team was challenged to discover the correct chemical passcode through experimentation in a gray box exercise, meaning the red team had partial knowledge of the system but did not have access to the internal designs. 

“This approach for testing security strength is commonly used in cybersecurity,” Wilson explained. 

The blue team engineered the system inside Escherichia coli, or E. coli, a bacterium widely used in biotechnology. The protected asset was a fluorescent protein gene selected as a measurable stand-in for commercially valuable targets. When the correct chemical sequence was applied, the fluorescence turned on. Without the correct passcode, the gene remained scrambled and the cells could not fluoresce green. 

“In practice, most DNA sequences produce valuable proteins or chemicals that are essentially invisible to the human eye, requiring specialized devices or experiments to observe,” Wilson said. “If the biohackathon were conducted with a standard commercially valuable target, the penetration testing would have taken more than 10 times longer to complete, years instead of months.”

The biohackathon results showed a dramatic reduction in risk. GeneLock reduced the probability of unlocking the genetic asset by random search to about 1 in 85,000 (a 0.001% chance), assuming the unauthorized user had access to the required chemical inputs.

Without access to those inputs, “the likelihood of success by chance becomes effectively negligible,” said Dowan Kim (Georgia Tech PhD 2024), co-lead author of the study.

Commercial Uses and What’s Next 

Although the researchers used a non-commercial fluorescent protein as a test case, the implications extend much further. Many biotechnology companies rely on proprietary engineered strains. New England Biolabs, for example, produces more than 265 non-disclosed enzymes in E. coli, each representing a high-value cell line. 

Protein-based drugs are also manufactured in living cells, and proprietary metabolic pathways are used to produce specialty chemicals, bioplastics, and high-value ingredients. 

“In each case, the genetic blueprint inside the cell represents intellectual property that can be protected by our technology,” said Ishita Kumar, a PhD candidate in ChBE and co-lead author of the study.

While the team’s current focus is on protecting intellectual property in the form of high-value cells, future iterations aim to strengthen biological security more broadly. 

“We are currently developing protection measures to mitigate unauthorized use or release of sensitive cell lines that can be potentially hazardous to human health or the environment,” Wilson said.

“As it stands, GeneLock represents an important shift in biological security, enabling, for the first time, protection of valuable cells at the genetic level, even after physical security measures have been bypassed,” he added. 

The work is already moving toward commercialization. The team filed a provisional patent application with the U.S. Patent and Trademark Office in February 2026 and is forming a company to deploy the technology.

This research was funded by a grant from the National Science Foundation.

CITATION:

Dowan Kim, Ishita Kumar, Mohamed Hassan, Luisa F. Barraza-Vergara, Christopher A. Voigt, and Corey J. Wilson, “Protecting cells at the genetic level and simulating unauthorized access via a biohackathon,” Science Advances, 2026.

Georgia Tech researchers think they have a better way with small metal tags that can signal when a door or drawer is opened, count reps in the gym, or even track bathroom use for elderly relatives. Their tags are battery-free, quiet, inherently private, and cost only a few cents each. They’re smaller than a penny.

Like other kinds of smart home sensors, the tags are designed to be mounted on a cabinet or doorframe, for example, using a 3D-printed base. A small tab is attached to the corresponding door or drawer. When it’s opened, the tab strikes the metal disk, triggering a brief ultrasonic pulse imperceptible to human ears but detectable by a wearable device that logs the activity.

Read the full story on the College of Engineering website.

Georgia Tech researchers are making AI easier to understand through their work on Transformer Explainer. The free, online tool shows non-experts how ChatGPT, Claude, and other large language models (LLMs) process language. 

Transformer Explainer is easy to use and runs on any web browser. It quickly went viral after its debut, reaching 150,000 users in its first three months. More than 563,000 people worldwide have used the tool so far.

Global interest in Transformer Explainer continues when the team presents the tool at the 2026 Conference on Human Factors in Computing Systems (CHI 2026). CHI, the world’s most prestigious conference on human-computer interaction, will take place in Barcelona, April 13-17.

[Related: GT @ CHI 2026]

“There are moments when LLMs can seem almost like a person with their own will and personality, and that misperception has real consequences. For example, there have been cases where teenagers have made poor decisions based on conversations with LLMs,” said Ph.D. student Aeree Cho.

“Understanding that an LLM is fundamentally a model that predicts the probability distribution of the next token helps users avoid taking its outputs as absolute. What you put in shapes what comes out, and that understanding helps people engage with AI more carefully and critically.”

A transformer is a neural network architecture that changes data input sequence into an output. Text, audio, and images are forms of processed data, which is why transformers are common in generative AI models. They do this by learning context and tracking mathematical relationships between sequence components.

Transformer Explainer demystifies how transformers work. The platform uses visualization and interaction to show, step by step, how text flows through a model and produces predictions.

Using this approach, Transformer Explainer impacts the AI landscape in four main ways:

• It counters hype and misconceptions surrounding AI by showing how transformers work.
• It improves AI literacy among users by removing technical barriers and lowering the entry for learning about AI.
• It expands AI education by helping instructors teach AI mechanisms without extensive setup or computing resources.
• It influences future development of AI tools and educational techniques by providing a blueprint for interpretable AI systems.

“When I first learned about transformers, I felt overwhelmed. A transformer model has many parts, each with its own complex math. Existing resources typically present all this information at once, making it difficult to see how everything fits together,” said Grace Kim, a dual B.S./M.S. computer science student. 

“By leveraging interactive visualization, we use levels of abstraction to first show the big picture of the entire model. Then users click into individual parts to reveal the underlying details and math. This way, Transformer Explainer makes learning far less intimidating.”

Many users don’t know what transformers are or how they work. The Georgia Tech team found that people often misunderstand AI. Some label AI with human-like characteristics, such as creativity. Others even describe it as working like magic.

Furthermore, barriers make it hard for students interested in transformers to start learning. Tutorials tend to be too technical and overwhelm beginners with math and code. While visualization tools exist, these often target more advanced AI experts.

Transformer Explainer overcomes these obstacles through its interactive, user-focused platform. It runs a familiar GPT model directly in any web browser, requiring no installation or special hardware. 

Users can enter their own text and watch the model predict the next word in real time. Sankey-style diagrams show how information moves through embeddings, attention heads, and transformer blocks.

The platform also lets users switch between high-level concepts and detailed math. By adjusting temperature settings, users can see how randomness affects predictions. This reveals how probabilities drive AI outputs, rather than creativity.

“Millions of people around the world interact with transformer-driven AI. We believe that it is crucial to bridge the gap between day-to-day user experience and the models' technical reality, ensuring these tools are not misinterpreted as human-like or seen as sentient,” said Ph.D. student Alex Karpekov. 

“Explaining the architecture helps users recognize that language generated by models is a product of computation, leading to a more grounded engagement with the technology.” 

Cho, Karpekov, and Kim led the development of Transformer Explainer. Ph.D. students Alec Helbling, Seongmin Lee, Ben Hoover, and alumni Zijie (Jay) Wang (Ph.D. ML-CSE 2024) and Minsuk Kahng (Ph.D. CS-CSE 2019) assisted on the project. 

Professor Polo Chau supervised the group and their work. His lab focuses on data science, human-centered AI, and visualization for social good.

Acceptance at CHI 2026 stems from the team winning the best poster award at the 2024 IEEE Visualization Conference. This recognition from one of the top venues in visualization research highlights Transformer Explainer’s effectiveness in teaching how transformers work.

“Transformer Explainer has reached over half a million learners worldwide,” said Chau, a faculty member in the School of Computational Science and Engineering. 

“I'm thrilled to see it extend Georgia Tech's mission of expanding access to higher education, now to anyone with a web browser.”

Wind turbines and solar panels have what economists call zero marginal cost, meaning producing additional units of electricity requires no fuel once installed. At the same time, this renewable energy varies greatly with the weather and can create operational challenges for grid operators.

A new review study from Georgia Tech examines how these characteristics are reshaping electricity markets and grid operations — and why addressing the challenge requires cross-disciplinary collaboration.

The study, published in Renewable and Sustainable Energy Reviews, synthesizes more than a decade of research. It analyzes over 200 studies on the engineering, economic, and policy implications of managing renewable energy sources that are both intermittent and effectively zero-cost to operate.

“Wind and solar are now among the lowest-cost sources of electricity in many parts of the world, but integrating them into the grid isn’t simple,” said Matthew Oliver, associate professor in the School of Economics and lead author of the study. “The wind doesn’t always blow, and the sun isn’t always shining, so output can fluctuate significantly, which complicates grid management.”

He added, “Historically, variation in electricity systems generally came from the demand side, and operators could simply ramp generation up or down. Now, we have variability on both supply and demand sides.”

Analyzing the Data

Looking at the problem, Oliver knew he would need to be familiar with engineering concepts to get at the heart of the issue. He created a research team with Daniel Matisoff, professor in the Jimmy and Rosalynn Carter School of Public Policy; Santiago Grijalva, professor in the School of Electrical and Computer Engineering; and graduate student co-authors Maghfira Ramadhani (economics), Oliver Chapman (public policy), and Amanda West (electrical and computer engineering).

Analyzing over 200 studies published since 2010, the team mapped the complex interactions between electricity market design, grid operations, and renewable technologies.

They also explored the economic implications of large amounts of zero-marginal-cost electricity entering wholesale electricity markets. Because wind and solar have very low operating costs, they can lower prices in wholesale electricity markets. That benefits consumers, but it can also make it harder for flexible conventional plants to earn enough revenue to stay available when renewable output falls.

Collaborating Across Disciplines

The team argues that successfully scaling renewable energy will depend on collaboration across traditionally separate fields.

“Engineering constraints affect how electricity markets work, markets influence investment decisions, and policy shapes how those investments happen,” Oliver said. “When it comes to complex topics like this, you can’t really treat engineering, economics, and policy as separate problems. They’re all part of the same system.”

The researchers found that electricity systems with high shares of renewable energy will require coordinated solutions that combine improved engineering practices, market reforms that value flexibility and reliability, and policies that align private investment with long-term decarbonization goals.

“Our hope is that this paper helps researchers across disciplines communicate more effectively,” Oliver said. “If we want electricity systems with high levels of renewable energy to work reliably, then engineers, economists, and policymakers all have to understand how their decisions affect the others.”

Citation: Oliver, Matthew E., et al. “Managing Zero-marginal-cost, intermittent renewable energy: A survey of the engineering, economic, and Policy Challenges.” Renewable and Sustainable Energy Reviews, vol. 226, Jan. 2026. 

DOI: https://doi.org/10.1016/j.rser.2025.116334

To help find answers, researchers at the Institute for Neuroscience, Neurotechnology, and Society (INNS) are using math, data, and AI to unlock the secrets of thought. Together they are helping turn the brain’s raw electrical “noise” into real insights about how people think, move, and perceive the world.

Fair warning: Prepare your neurons for the complexity of this brain research ahead.

Building AI Like a Brain

What if artificial neurons in AI programs were arranged as they are in the brain?

AI programs would then help us understand why the brain is organized the way it is. This neuro-AI synthesis would also work faster, use less energy, and be easier to interpret. Creating such systems is the goal of Apurva Ratan Murty, an assistant professor of Psychology who is creating topographic AI models like the one above of three domains — vision, audition, and language inspired by the brain. In the near future, he predicts doctors might be able to use these patterns to predict the effects of brain lesions and other disorders. “We’re not there yet,” he says. “But our work brings us significantly closer to that future than ever before.”

Computing Thought and Movement

How cats walk keeps Chethan Pandarinath on his toes. This biomedical engineer uses sensors to analyze how two sets of feline leg muscles — flexors and extensors — are controlled by the spinal cord. Understanding how that happens could help patients partially paralyzed from spinal cord injuries, strokes, or progressive neuro-degenerative diseases get back on their feet again. “My lab is using AI tools that allow us to turn complex spinal cord activity data into something we can interpret. It tells us there’s a simple underlying structure behind the complex activity patterns,” says the associate professor.

Revealing the Brain’s Spike Patterns

“The brain is like a symphony conductor,” says Simon Sponberg. “Individual instruments have some independent control, but most of the music comes from the brain’s precise coordination of notes among the different players in the body.” This physics professor studies the fantastically fast-beating wings of the hummingbird-sized hawk moth (Manduca sexta). Its agile flight movement comes as a result of spikes in electrical activity in 10 muscles. Sponberg found something that surprised him — the brain focuses less on creating the number of spikes than in orchestrating their precise patterns over time. To Sponberg, every millisecond matters. “We are just beginning to understand how the nervous system first acquires precisely timed spiking patterns during development,” he says.

Predicting Decisions Through Statistics

Put a mouse in a maze with food far away, and it will learn to find it. But life for mice — and people — isn’t so simple. Sometimes they want to explore, only want water, or just want to go home. What’s more, animals make decisions based on their history, not just on how they feel at the moment. To dig deeper into the decision-making process, Anqi Wu, an assistant professor in the School of Computational Science and Engineering, is giving mice more options. By using a new computational framework called SWIRL (Switching Inverse Reinforcement Learning), her findings have outperformed models that fail to take historical behavior into account. “We’re seeking to understand not only animal behavior but also human behavior to gain insight into the human decision-making process over a long period of time,” she says.

Modeling the Mind’s Wiring With Math

Connectivity shapes cognition in the cerebral cortex, a layered structure in the brain. The visual cortex, in particular, processes visual data from the retina relayed through the Lateral Geniculate Nucleus (LGN) in the thalamus, and directs it to the correct cognitive domain in the brain. How it does this is the mystery that computational neuroscientist Hannah Choi wants to solve. “The big question I’m interested in is how network connectivity patterns in the architecture of the LGN are related to computations,” says this assistant math professor. To find answers, she shows mice repeated image patterns such as flower-cat-dog-house and then disrupts the pattern. The goal? To grasp how the thalamus’s nonlinear dynamical system works. If scientists and doctors better understand how brain regions are wired together, such knowledge could lead to better disease treatment.

This story was originally published through the Georgia Tech Alumni Magazine. Read the original publication here.

A Spark of Curiosity

In 2017, faculty conversations began circulating about a new kind of capstone experience, one driven by student discovery and entrepreneurial thinking rather than predetermined client requirements. The idea intrigued Omojokun.

“I remember thinking, this is really different from anything I’ve ever taught,” he said.

In his previous courses, Omojokun took pride in providing the structured, rigorous framework students needed to master complex concepts. While those interactions were dynamic, the curriculum required a specific, focused trajectory. CREATE-X offered a different kind of challenge: the "X" of the program, representing undefined, endless potential.

“CREATE-X is full of unknowns. You don’t know what industry the students are diving into, what roadblocks they’ll run into and navigate out of, or what small- to large-scale successes they’ll achieve throughout the semester. It really had my blood pumping,” he said. As someone who loves the challenge of academia, it was an invigorating way to help the next generation apply what they’ve learned in a new context.

Omojokun co-taught the first CREATE-X Capstone section with College of Computing students in fall 2018 alongside Craig Forest, associate director of the Invention Studio. While the initial computer science cohort was small, the experience was immediately powerful.

“It was humble beginnings but deeply eye-opening,” he said.

In this new environment, students weren't just solving problems; they were seeking them and sometimes pivoting. Traditional client-driven capstones offer students invaluable experiences in delivering high-quality products, responding to clients’ often evolving needs, and adhering to professional standards. CREATE-X added a layer of venture-validation, requiring students to identify a gap in the market and build something with commercial viability.

As the semesters continued, CREATE-X grew from a program with an interesting capstone course Omojokun enthusiastically co-taught to a professional inflection point for him. He found himself talking about it frequently, with colleagues, with students, even with prospective undergraduates who may not see a capstone for years.

He began encouraging prospective and incoming students to take CREATE-X pathways. 

“I would tell students, down to first-year students, when you get that opportunity to engage with CREATE-X, take it. You don’t even have to wait until capstone, as there are multiple pathways; in fact, Startup Lab has no prerequisites. Whatever path you take, you’ll remember it for years to come. Whether you officially take a problem solution to market or not, the entrepreneurial confidence gained is priceless.”

Spreading CREATE-X Into the College of Computing

By 2020, when the first Jim Pope Faculty Fellowship cohort opened, applying felt natural. He had already become an unofficial ambassador for CREATE-X, helping students navigate options, promoting programs in classes, and rallying colleagues to engage.

“It was an opportunity to become more connected to this thing that I felt was changing the game on campus,” he said. “It cemented my affiliation with CREATE-X.”

The fellowship gave name and weight to the work he was already doing, while also expanding what was possible.

The Jim Pope Faculty Fellowship provides faculty with $15,000 in discretionary funding, which can support a one-semester break from teaching, along with structured training in evidence‑based entrepreneurship, dedicated mentorship, and the opportunity to work closely with students launching startups.

The fellowship also equips faculty to become entrepreneurial instructors and mentors through the CREATE‑X ecosystem, giving them tools to integrate entrepreneurship into their coursework and curricula. Each cohort of fellows is trained to embed entrepreneurial methods, develop new innovation‑focused assignments, and serve as advisors within programs like Startup Lab, Idea‑to‑Prototype, and Startup Launch.

For faculty across Georgia Tech, the fellowship offers something rare: institutional backing, resources, and formal recognition for bringing entrepreneurship into their teaching and shaping how students learn to become problem‑solvers.

Omojokun said he sees CREATE-X as the apex of applying technical fundamentals. 

As part of the fellowship, Omojokun brought the program’s ethos into his courses, even a foundational course like CS 1331: Introduction to Object Oriented Programming, where he created a CREATE-X–branded final project. Students built a “problem database” application as their final homework assignment, cataloging real issues they encountered in daily life, assessing their skills to solve them, evaluating markets and metrics, and then deciding potential pathways forward.

“It’s an innovation diary,” he said. “A tool that can get them closer to thinking like a founder.”

The response from students, including many non-computing majors who take his section each semester, has been overwhelmingly positive. While the project is challenging, the open-ended nature and real-world relevance motivate deeper engagement. 

“When students believe their work will solve a meaningful problem for a meaningful population, they bring passion to it,” he said. “They start observing the world differently.”

The more Omojokun saw, the deeper his enthusiasm grew.

Shaping the College of Computing

Even as he stepped into the role of inaugural chair of the School of Computing Instruction in 2022, CREATE-X remained at the forefront of Omojokun’s conversations. Interest in the program continued to grow significantly. Students stopped him in the hallways to talk about their ideas. Faculty reached out to ask about mentorship opportunities. And he continued championing the program in the many settings he entered.

“It turns out that the most engaged group of students in CREATE-X is computing undergraduates,” Omojokun said. “I wanted to make sure that high involvement continued, no matter what size we are,” he said.

Over time, Omojokun strengthened the partnership between the College of Computing and CREATE-X, weaving entrepreneurship deeper into the College's curricular fabric.

Last January, Omojokun was appointed as the associate dean for Undergraduate Education in the College of Computing. One of his priorities was highlighting CREATE-X’s curricular impact. In coordination with key stakeholders — including Kelly Ann Fitzpatrick (computing), Craig Forest (mechanical engineering), and Raul Saxena (CREATE-X) — he nominated the program for the ABET Innovation Award.  The award honors programs that challenge the status quo in technical education and demonstrate a measurable impact on student learning in ABET-accredited disciplines, such as natural sciences, computing, engineering, and engineering technology. CREATE-X won.

The CREATE-X Advantage With Faculty 

When faculty are considering something like the Jim Pope Fellowship, Omojokun said the biggest barrier he hears about from them is time. With courses that can enroll 300 students per section and extensive responsibilities beyond the classroom, time is a scarce resource.
He could relate. 

“There are always lots of things on my physical and virtual desktop. I always warn people before they enter my office,” he said.

However, Omojokun argued that participating in the fellowship program was time well spent because it helps them rediscover the most exciting parts of teaching.

“It’s worth the time. One of the goals of teaching is to see students passionate about what they’re learning, and CREATE-X makes that happen consistently,” he said. 

The Future With Technology

As AI reshapes industries, Omojokun believes that CREATE-X equips students to navigate the unknown and forge new paths as existing ones shift, providing a versatile skill set that transfers to employment, potentially self-employment, and beyond. 

“There’s a lot of uncertainty with AI in the workspace, but CREATE-X gives students the confidence and skills to succeed at whatever comes,” he said. “We are putting students through this process of finding a problem that’s meaningful and matters to the world; mastering that allows them to lead in any environment.”

Applications Now Open: Become a Jim Pope Faculty Fellow

The 2026 Jim Pope Faculty Fellowship is now accepting applications. For faculty who want to explore integrating entrepreneurship into their teaching, mentoring student founders, and helping shape a culture of innovation across campus, this fellowship offers resources and a supported pathway to begin. Faculty from all disciplines are encouraged to apply to the Jim Pope Fellowship. Priority deadline: July 1; final deadline: Aug. 11.

Before dawn on March 1, 2026, Iranian Shahed drones struck two Amazon Web Services data centers in the United Arab Emirates. A third commercial data center in Bahrain was hit, though it is less clear whether it was deliberately targeted. This is the first time that a country has deliberately targeted commercial data centers during wartime.

Iran state media issued a statement on March 31 that it will target American companies, including Microsoft, Google, Apple, Meta, Oracle, Intel, HP, IBM, Cisco, Dell, Palantir and Nvidia. The Financial Times reported that an additional Iranian drone struck an Amazon data center in Bahrain on April 1. And Iranian state media claimed that Iranian forces attacked an Oracle data center in Dubai on April 2.

Iran has also been on the receiving end of such attacks. A data center in Tehran operated by Iran’s state-run Bank Sepah was struck by a missile – apparently fired by U.S. or Israeli forces – on March 11, according to a report in The Jerusalem Post.

Data centers have been targets of espionage and cyberattacks in the past, notably when Ukrainian hackers destroyed data stored in a Russian military-affiliated data center in 2024. These strikes in the Persian Gulf region, however, were physical attacks. Drones damaged buildings.

Advances in artificial intelligence have increased the importance of data centers. The U.S. military, in particular, has made great use of AI systems for decision support in its attacks on Iran and Venezuela. Given how important data centers are, Iranian forces could be targeting the infrastructure Iran’s leaders believe is supporting strikes on Iran.

It is not altogether clear that these particular data centers were used by the U.S. military. Instead, the attacks may have been part of a broader effort to punish the United Arab Emirates for its ties with the U.S.

In my experience as a Ph.D. candidate at Georgia Tech studying how technology drives changes in international security, I don’t think the attacks signal any significant change in the nature of warfare. But they are forcing nations to recognize that data centers are targets of war – even if they don’t directly support military operations.

Data Centers and the Cloud

The United States military is increasingly incorporating advanced AI capabilities into its decision support systems. From the operation to capture Venezuelan President Nicolás Maduro to supporting military strikes against Iran, the U.S. has been using AI, especially Anthropic’s Claude, for intelligence analysis and operational support.

AI is unlocking faster ways to carry out operations in war, but the AI tools the military often uses are not located on a plane or ship. When a service member uses Claude, the computing infrastructure that powers the model and its analysis usually goes to a secure Amazon Web Services cloud that hosts secret government data and software tools.

Commercial data centers are where the cloud lives. The next time you pull up Netflix and watch your favorite shows, you are likely streaming the programming from a data center, possibly AWS. When AWS data centers go down, outages affect all sorts of entertainment, news and government functions.

With AI as a driver of economic growth, data centers are key forms of infrastructure. They ensure that AI can continue to run, as well as much of the underlying internet that governments and industry rely on. When Iran attacked the UAE’s data centers, it caused widespread disruption to the local banking system.

Commercial data centers enable most of the technology that runs the modern world, including AI systems. Disrupting them is key to disrupting a country’s military and society. Given that AWS provides and operates many of the commercial data centers where the cloud lives, it is likely that its data centers will continue to be targeted in conflict.

Going After US Allies

Researchers at Just Security noted on March 12, 2026, that the United States requires cloud-computing service providers to store government and military data within the U.S. or on Department of Defense bases: “Moving such data to Amazon data centers in the Gulf region would require special authorization; we are unaware if that has been granted.”

Nevertheless, Iran’s Islamic Revolutionary Guard Corps claimed the strikes were against data centers supporting “the enemy’s” military and intelligence activities. And 10 days after the initial attack on the data centers, an Iranian news agency claimed that major tech company data centers and other physical assets in the region were considered “enemy technology infrastructure.”

Instead of military reasons, Iran may well have targeted the UAE to rattle the global economy and garner attention. Given the prominence of the Gulf as a major recipient of U.S. technological investment, the attack may also have been a symbolic one aimed at the heart of U.S.-Gulf cooperation. AI infrastructure such as commercial data centers is a growing part of U.S. leadership in the region, and this war could jeopardize the future of AI infrastructure in the Gulf.

Growing Importance, Easy Targets

Though data centers are increasingly important for national security, the economy and society at large, it can be tempting to suggest these strikes represent a fundamental shift in the nature of war. While that is a possibility, it is important to remember that Iran launched thousands of missiles and drones at targets in the UAE and Bahrain. Though the vast majority were intercepted, the four that struck data centers are a small portion of the ones that got through to civilian targets in those countries, including strikes on airports and hotels.

The relative vulnerability of commercial data centers – they are large, relatively fragile and lack dedicated air defenses – suggests that the ones in the UAE and Bahrain may have been targets of opportunity or convenience. In other words, they were hit because they could be hit.

Nevertheless, it seems likely that as the use of AI tools and other cloud-based resources continues to grow in importance for countries around the world, commercial data centers will be targets in future conflicts.

This article has been updated to include news of Iran’s statement about targeting U.S. tech companies and subsequent drone strikes on other data centers.

This article is republished from The Conversation under a Creative Commons license. Read the original article.

Today, he is the chief executive officer of Andson Biotech, a growing biotools startup he co-founded with Andrei Fedorov, associate chair for graduate studies and the Rae S. and Frank H. Neely Chair at the George W. Woodruff School of Mechanical Engineering. The company is commercializing a breakthrough technology Chilmonczyk developed during his doctoral research that simplifies the development and production of cell and gene therapies.

Read the full story on the George W. Woodruff School of Mechanical Engineering website.

A 2025 AI in Education trend report found that 90% of college students use AI in their coursework, with nearly half using it during the drafting process. As AI becomes embedded in everyday writing, traditional tools like Grammarly or Turnitin for evaluating student learning fall short. If AI is to be expected in most student writing, then merely detecting its presence isn’t enough. 

DraftMarks, a new open‑source tool developed by Georgia Tech and Stanford researchers, makes the writing process itself visible. Instead of trying to assess how much of a finished document was written by AI, DraftMarks shows where a student iterated with AI prompts, what is fully AI, and how a piece evolved — illuminating the often-invisible collaboration between human writers and AI.

Functioning as an augmented reading tool, DraftMarks layers visual cues directly onto a document to indicate different kinds of AI involvement. Eraser crumbs mark heavily revised passages. Smudges signal AI-generated changes in the strength of the argument rather than content changes. Masking tape highlights passages initially generated by AI. Glue residue shows where AI‑generated text was later removed. Ghost text indicates when a writer prompted AI but chose not to use the output. Different fonts distinguish between human‑written and AI‑generated passages.

Together, the marks don’t just reveal AI’s presence. They tell a story about the writer’s process.

“By making the invisible parts of the process tangible, it forces writers to confront whether they are truly engaging with AI or just passively accepting it,” said Momin Siddiqui, a master’s student in the College of Computing and lead author on the project. “Ultimately, it helps writers make more intentional judgment calls about how they want to collaborate with AI in the future.”

The researchers debuted DraftMarks at the Association for Computing Machinery’s Conference on Human Factors in Computing Systems in Barcelona in April.

Designing for Educators

Rather than starting with detection algorithms, the researchers began with educators. In an initial 21-person study, they observed how instructors reviewed student writing and what cues they looked for when assessing learning, revision, and originality. Those insights informed the design of DraftMarks’ visual language, which deliberately mimics physical artifacts of writing — eraser debris, tape, smudges — to reflect processes instructors already recognize.

“These marks are meant to emulate the writing process in ways we’re already familiar with,” said Adam Coscia, a computing Ph.D. student. “They help students and teachers see the effort behind the writing, and whether students actually met the learning objective.”

Behind the scenes, DraftMarks tracks a document’s draft history and classifies different types of edits and AI interactions as they happen, allowing the visual cues to appear almost in real time. 

Reading DraftMarks

To evaluate how the tool functions beyond the lab, the team conducted a follow‑up study with 70 participants, including students, teachers, journalists, and general readers. Their reactions to reviewing a DraftMarks-annotated document varied in revealing ways.

Instructors were most interested in seeing the writing process unfold: how ideas developed, how heavily AI was used, and where students exercised judgment. General readers, meanwhile, used the marks to assess something less measurable but equally important — trust. For them, DraftMarks offered cues about authorial intent and authenticity, helping readers decide how much confidence to place in a piece of writing. 

A Shift From Detection to Reflection

Unlike AI detectors that merely offer a percentage, DraftMarks is designed to prompt reflection from writers and readers. 

“DraftMarks completely changed how I think about my own writing,” Coscia said. “I was surprised by how much I cared about authorial intent once I could actually see how AI affected my tone. It made me realize small AI choices can subtly reshape what I’m trying to say.”

As AI continues to reshape how writing happens, the research team hopes DraftMarks will help shift the conversation toward transparency. Tools like this could offer educators and students a clearer window into how learning happens when humans and AI write together.

This work is funded through the AI Research Institutes program by the National Science Foundation and the Institute of Education Sciences, U.S. Department of Education.

CITATION: Momin N. Siddiqui, Nikki Nasseri, Adam J. Coscia, Roy Pea, and Hari Subramonyam. 2026. DraftMarks: Enhancing Transparency in Human-AI Co-Writing Through Interactive Skeuomorphic Process Traces. In Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems (CHI '26). Association for Computing Machinery, New York, NY, USA, Article 862, 1–22. 

DOI: https://doi.org/10.1145/3772318.3791109

The two‑day event took place Feb. 4 – 5, coinciding with the Critical Minerals Ministerial hosted by U.S. Secretary of State Marco Rubio in Washington, D.C., on Feb. 4, which brought together more than 50 nations to strengthen and diversify global critical mineral supply chains. During this ministerial, U.K. Minister Seema Malhotra and U.S. Under Secretary of State Jacob Helberg signed a Critical Minerals Memorandum of Understanding, strengthening bilateral cooperation between the United States and the United Kingdom on critical mineral supply chains. 

These broad efforts are supported by White House Executive Order 14363, which defines the Genesis Mission and aims to accelerate scientific discovery through AI. The order identifies critical minerals supply chain resilience as a national security imperative.

In Atlanta, these themes were brought to life in real time. The GEMs-4 workshop brought together researchers, policymakers, national labs, industry leaders, and workforce organizations from both the U.S. and the U.K. to address shared challenges in technology translation, permitting, investment, and talent development. 

The state of Georgia’s integrated ecosystem, linking research universities, legacy industries, technical colleges, national labs, and public‑private partnerships, served as a case study. Presenters highlighted how existing industrial assets in the Southeast are being incorporated into emerging clean energy and critical minerals supply chains, offering a model for other regions seeking to build capabilities around extraction, processing, and manufacturing.

A U.K. member of Parliament representing Cornwall, where the U.K. has lithium reserves and deep critical mineral expertise, joined the convening, as well as representatives from the U.K. Critical Mineral Association, Camborne School of Mines, and the University of Kent. Together, they explored opportunities and challenges, from a fundamental science to a commercialization perspective grounded in real-world experience. 

The alignment between the ministerial in Washington and the expertise present in Atlanta demonstrated the value of state-level engagement and how national agreements translate into practical collaboration on the ground. 

“The Southeast has the research depth, industrial footprint, and collaborative spirit needed to lead in critical minerals innovation,” said Yuanzhi Tang, Georgia Power Professor in the School of Earth and Atmospheric Sciences, executive director of the Strategic Energy Institute, and founding director of the Center for Critical Mineral Solutions at Georgia Tech. “GEMs‑4 showed what’s possible when universities, industry, and government partners align around shared priorities.” 

Day one featured strategic dialogue on critical mineral resources, innovation pathways, and partnership models. A recurring theme was the co-production of critical minerals alongside major mineral commodities. “Many critical minerals are produced as byproducts of larger mining operations, making it essential to integrate recovery strategies into existing mineral industries rather than developing entirely new extraction systems,” noted Crawford Elliott, professor of geosciences at Georgia State University.

Day two transitioned to field‑based learning, led by Paul Schroeder, professor of geology at the University of Georgia. Participants visited active operations to better understand how regional industrial strengths can support national and international supply chain goals. Schroeder said, “Connecting people to the long-standing mineral extraction economy at the mining and plant sites, where the work gets done with an amazingly skilled workforce, underscores the unique role of Georgia’s place‑based capacity in advancing national and transatlantic supply chain goals.”

Organizers emphasized that resilient supply chains rely on regional capabilities built over time through university collaboration, industry partnerships, and community engagement. With three years of inter‑university coordination now underpinning the GEMS platform, the 2026 workshop demonstrated how the Southeast is contributing actionable models for U.S.-U.K. cooperation.

“Ecosystem-building at this scale requires participation from every part of the value chain, and we are encouraged by the model GEMs presents,” said Rachel Galloway, Consul General at British Consulate General Atlanta. “The collaboration across universities, industry, and government is exactly what enables long‑term impact on both sides of the Atlantic.”

Through focused dialogue and partnership-building, the symposium strengthened transatlantic collaboration, highlighted regional strengths, and accelerated innovation and translation across the critical minerals value chain, from resource characterization and processing to recycling, manufacturing, and deployment.

For more information about the GEMS initiative, visit: https://gems.research.gatech.edu/.

Artificial intelligence has been touted as the most transformative technology of our time. With only a few years of mainstream use, it’s changed how we work and communicate, generated billions of dollars in investments, and sparked global debate. But according to leading neuroethics expert Karen Rommelfanger, the race isn’t over yet. 

“Can you think of a more transformative technology than one that intervenes with the fundamental organ that drives your experience in the world?” 

That fundamental organ is the brain.  

Technologies interfacing directly with the brain have been reserved for treating severe injury or disease for decades. Now, neurotechnology is expanding into brain-responsive wearables meant to enhance, augment, and monitor everyday life. As these technologies accelerate and AI is incorporated, the question is no longer if neurotechnology will transform society, but how — and who will shape the boundaries. 

These are some of the questions on which Karen Rommelfanger has built her career. Trained as a biomedical researcher and neuroscientist, Rommelfanger went on to found the Institute for Neuroethics, the world’s first think and do tank devoted entirely to neuroethics, public engagement, and policy implementation.  

“The brain is special; it’s central to who we are,” says Rommelfanger, who was also an inaugural recipient of the Dana Foundation Neuroscience and Society Award. “And that means when you intervene with the brain, there are unique responsibilities. The field of neuroethics addresses things like: How do you ensure mental privacy? How do you protect free will? How do you ensure that people have the power to be narrators of their own lives and their cognitive experience?” 

Now, Rommelfanger is joining Georgia Tech’s Institute for Neuroscience, Neurotechnology, and Society (INNS) as a professor of the practice, where she will work to further embed neuroethics into Georgia Tech’s research and technology development ecosystem. 

“Georgia Tech is producing the next generation of neurotechnologists, and Karen’s expertise will help ensure we’re preparing them to think about societal impact as deeply as they think about the technical and scientific aspects of their work,” says Christopher Rozell, executive director of INNS. “Her leadership strengthens the Institute in exactly the way this moment in neurotechnology demands.”  

“Georgia Tech has many, many ways that it leads in the technology ecosystem. But one of the powerful, unique ways it can lead is through neurotechnology,” says Rommelfanger. “I hope that the INNS, given its unique mandate for neuroscience, neurotechnology, and society, can be a lighthouse for these types of conversations.” 

Neuroethics by Design 

The Earth and the Moon may look very different today, but they formed under similar conditions in space. In fact, a dominant hypothesis says that the early Earth was hit by a Mars-sized object, and it was this giant impact that spun off material to form the Moon. But unlike Earth, the Moon lacks plate tectonics and an atmosphere capable of reshaping its surface and recycling elements such as oxygen over billions of years.

As a result, the Moon preserves a record of the geological conditions that helped shape it and can give scientists insight into the world we live in today. Rocks that were formed during early volcanic activity on the Moon offer a window into events that occurred nearly 4 billion years ago. By uncovering the conditions under which the Moon’s rocks formed, scientists move closer to understanding the origins of our own planet.

In a study published March 2026 in the journal Nature Communications, our team of physicists and geoscientists investigated ilmenite, a mineral composed of iron, titanium and oxygen, in a Moon rock crystallized from an ancient lunar magma. We used cutting-edge electron microscopy to probe the chemical signature of titanium in this ilmenite, finding that about 15% of the titanium carries less of an electrical charge than expected.

Implications of Trivalent Titanium

In ilmenite, an atom of titanium typically loses four electrons when bonding with oxygen, resulting in a positive charge of 4+, known as the atom’s oxidation number. From the sample we studied, a rock collected during the Apollo 17 mission, we found that some of the titanium in ilmenite actually has a charge of only 3+, referred to as trivalent titanium. Our measurement of trivalent titanium confirms what geologists had long suspected: that some titanium in lunar ilmenite exists in a lower charge state.

Trivalent titanium occurs only when the amount of oxygen available for chemical reactions is low. Thus, the abundance of trivalent titanium in ilmenite could tell us about the relative availability of oxygen in the Moon’s interior when the rock formed, around 3.8 billion years ago.

A Link to the Moon’s Early Chemistry

Our team has closely studied only one Moon rock so far, but from published studies we have identified more than 500 analyses of lunar ilmenite that could contain trivalent titanium. Studying these samples could reveal new details about how the Moon’s chemistry varies across different locations and time periods.

While our work highlights a link based on prior studies, the relationship between trivalent titanium in ilmenite and oxygen availability has not yet been quantified with targeted experimental data.

By conducting experiments that explore that link, ilmenite could reveal more details about the Moon’s interior. We also expect this relationship to apply to other planets and asteroids that don’t contain much chemically available oxygen, relative to Earth.

What’s Next?

These methods can be used to study many Moon rocks collected during the Apollo missions over 50 years ago, as well as future samples from upcoming Artemis missions, or rocks collected from the far side of the Moon, returned in 2024 by China’s Chang’e-6 mission.

One of our team members plans to use their new experimental lab to explore how oxygen availability in magma affects the abundance of trivalent titanium in ilmenite. With experiments like this that build off our findings, we could potentially use ilmenite to reconstruct the history of ancient magmas from the Moon.

We believe future studies of lunar rocks using advanced scientific methods are essential for revealing the chemical conditions present on the ancient Moon. They could offer clues not only to its own history but also to the earliest chapters of Earth’s past – records that have since been erased from Earth.

This article is republished from The Conversation under a Creative Commons license. Read the original article.

The programming style relies on using generative artificial intelligence (AI) to create software code using tools like Claude, Gemini, and GitHub Copilot. According to graduate research assistant Hanqing Zhao of the Systems Software & Security Lab (SSLab), no one had been tracking these common vulnerabilities and exposures before the launch of their Vibe Security Radar.

“The vulnerabilities we found lead to breaches,” he said. “Everyone is using these tools now. We need a feedback loop to identify which tools, which patterns, and which workflows create the most risk.”

The radar extensively scans public vulnerability databases, finds the error for each vulnerability, and then examines the code’s history to find who introduced the bug. If they discover an AI tool's signature, the radar flags it. 

Of the 74 confirmed cases uncovered so far by the tool, 14 are critical risks, and 25 are high. These vulnerabilities include command injection, authentication bypass, and server-side request forgery. Zhao explained that since AI models tend to repeat the same mistakes, an attacker would need to find these bugs just once. 

“Millions of developers using the same models means the same bugs showing up across different projects,” he said. “Find one pattern in one AI codebase, you can scan for it across thousands of repositories.”

Despite its success, the team has only scratched the surface of the problem. The radar can trace metadata like co-author tags, bot emails, and other known tool signatures, but it can't identify an issue if these markers have been removed. 

The next step is behavioral detection. AI-written code has patterns in how it names variables, structures functions, and handles errors. 

“We're building models that can identify AI code from the code itself, no metadata needed,” said Zhao. “That opens up a lot of cases we currently can't touch.”

The team is also improving its verification pipeline and expanding its sources to include more vulnerability databases. The goal is to get a more complete picture of AI-introduced vulnerabilities across open source, not just the ones that happen to leave signatures behind. 

As more programmers rely on vibe coding, Zhao warns that it still needs to be reviewed as thoroughly as any other project. 

“The whole point of vibe coding is not reading it afterward, I know,” he said. “But if you're shipping AI output to production, review it the way you'd review a junior developer's pull request. Especially anything around input handling and authentication.”

When prompting AI, SSLab also recommends providing more detailed instructions to get it closer to production-ready. There are also tools to check the code for vulnerabilities after  code it has been generated. Not double-checking could lead to a catastrophe. 

“The attack surface keeps growing,” said Zhao. “More people running AI agents locally means the attacker doesn't need to break into the company infrastructure. They just need one vulnerability in a model context protocol server that someone installed and never reviewed.”

One reason the attack surfaces are expanding rapidly is AI’s evolution. In the second half of 2025, the Vibe Security Radar found about 18 cases across seven months. Then, in the first three months of 2026, it identified 56. March 2026 alone had 35, more than all of 2025 combined. 

Many tools, like Claude, are now more autonomous, allowing developers to write entire features, create files, and even make architecture decisions. 

“When an agent builds something without authentication, that's not a typo,” said Zhao. “It's a design flaw baked in from the start. Claude Code and Copilot together account for most of what we detect, but that's partly because they leave the clearest signatures.”

As during previous editions, this year’s conference featured more than two dozen scientists, engineers, policy experts, and thought leaders from Georgia Tech and beyond, illustrating how collaboration across fields – from science and engineering to public policy and international affairs – helps to advance strategic research priorities. 

“Frontiers is about discovery and connections across disciplines and generations,” says Susan Lozier, dean of the College of Sciences and Betsy Middleton and John Clark Sutherland Chair. “This edition provided an inspiring glimpse into the future of space exploration and the many ways Georgia Tech is contributing to research and missions seeking answers to what lies beyond our planet.” 

Commitment to Space

Space research is a key institutional priority at Georgia Tech, which is home to numerous academic and research programs in planetary sciences, robotics, mission design, space policy, and other areas. 

The recently established Space Research Institute (SRI) serves as the central hub connecting the broad range of space-related research across campus. Led by Jud Ready, who also serves as principal research engineer at the Georgia Tech Research Institute, SRI has expanded support for space research and commercialization through initiatives such as the CreationsVC Space Fellows Program and Centers, Programs, and Initiatives seed grant program.

SRI’s efforts are in line with Georgia Tech’s long-standing contribution to space exploration. Hundreds of Yellow Jacket alumni work in the space sector, including several graduates who are playing key roles in the Artemis program. To date, more than a dozen Georgia Tech alumni have traveled to space.

Exploring the Final Frontier

The conference featured a series of panels and discussions led by faculty and researchers from the Colleges of Sciences and Engineering as well as the Ivan Allen College of Liberal Arts. 

Sessions explored how researchers are studying the processes and conditions that support planetary habitability, seeking to answer one of humanity’s greatest questions: Does life exist beyond Earth? Speakers also examined how analog fieldwork in Earth’s extreme environments can inform space exploration, and how space research, in turn, can deepen our understanding of our own world.

Additional conversations centered on building better space missions through improved understanding of team and individual resilience, data collection, navigation, and the development of advanced technologies like the robots developed through the NASA LASSIE Project. 

Frontiers also highlighted Georgia Tech’s commitment to preparing the next generation of space scientists, engineers, and leaders. Student training and engagement were recurring themes throughout the day, with speakers emphasizing opportunities for student-led and student-run missions and research. A panel of Georgia Tech alumni shared their own STEM career journeys, challenging the idea of “one right path” to success — and acknowledging the resources and opportunities available at the Institute. 

A highlight of the conference was a fireside chat with Atlanta-native, retired U.S. Army Colonel and NASA Astronaut R. Shane Kimbrough (M.S. Operations Research 1998). Kimbrough, who spent a total of 388 days in space and performed nine spacewalks across three missions, reflected on his career and the evolution of spaceflight. He emphasized the expanding role of public-private and international partnerships in advancing ambitious goals, such as creating a permanent human outpost on the Moon. 

Policy and Public

The conference also explored how policy influences space discovery and innovation, with discussions touching on such issues as space security, access, governance, sustainability — and the influence of technology and science fiction on public perception and policy. 

Panelists described current policy frameworks governing outer space as struggling to keep pace with rapidly advancing technologies and expanding activities. According to these experts, increasing tensions among commercial, research, and recreational uses of space call for greater coordination among private and government entities to balance competing priorities while maximizing opportunities for innovation and exploration. 

The conference was punctuated by a networking lunch connecting attendees with Atlanta’s public astronomy community – including partners at several universities and the Georgia Tech Astronomy Club, which set up telescopes for attendees to safely observe the sun. Later that evening, the Georgia Tech Observatory hosted its Public Night, welcoming the broader Atlanta community to campus for telescope views of Jupiter, the Orion Nebula, and other celestial bodies. 

The Observatory Night was a fitting conclusion to a full day focused on Georgia Tech’s commitment and contributions to inspiring future generations of space explorers through research, education, and outreach. 

Experience the Frontiers conference in pictures on the College of Sciences’ Flickr account.

A research team led by Yuhang Hu, associate professor in the George W. Woodruff School of Mechanical Engineering and the School of Chemical and Biomolecular Engineering, has created a new material designed to do exactly that. In a new study published in Advanced Materials, Hu and her collaborators describe a groundbreaking class of “living” polymers that can grow, shrink, heal, and even regenerate long after fabrication.

Their work combines advances in chemistry, mechanics, and materials design into a polymer platform that could reshape how engineered products are built, maintained, and recycled.

Read the full story on the George W. Woodruff School of Mechanical Engineering website.

A team of researchers led by Ankur Singh, the Carl Ring Family Professor in the George W. Woodruff School of Mechanical Engineering and professor in the Wallace H. Coulter Department of Biomedical Engineering at Georgia Tech and Emory University, has been awarded up to $6 million from the Defense Threat Reduction Agency (DTRA) of the U.S. Department of Defense to accelerate the development of medical countermeasures (MCMs) against deadly biological threats that endanger public health, national security, and warfighters.

DTRA’s mission is to provide solutions that enable the Department of Defense, the U.S. government, and international partners to deter strategic threats. A key priority is advancing new or improved MCMs that can be deployed before or after exposure to biological or chemical agents.

Singh’s multi-year project, Systematic Human Immune Engineering for Lethal Disease (SHIELD) Countermeasures, aims to create a threat-agnostic platform that transforms how respiratory pathogens and toxins are studied. The platform is designed to speed up the discovery, development, and production of immune-based countermeasures.

Read the full story on the George W. Woodruff School of Mechanical Engineering website.

The award, named for the Iowa-based nonprofit’s founder, recognizes midcareer scientists and engineers for research impact, mentoring, scientific-community activities, and commitment to communicating science and technology. It will be formally presented to Erickson in May on the Georgia Tech campus.

Read the full story on the George W. Woodruff School of Mechanical Engineering website.

“It was frustrating, but it showed me how many people were being left out of the digital world,” Espinosa said. “In Colombia, only about two out of 10 people have a credit card. Cash is the main form of payment, but everything online requires digital access.”

That gap sparked the idea that would evolve into Loto Punto, a fintech startup building self-service kiosks to bridge the physical and digital worlds for unbanked communities. 

From a Single Problem to a Scalable Platform

Espinosa began his startup as an online platform for buying lottery tickets. He saw that customers didn’t trust the idea of a digital receipt because they were used to a printout, so he pivoted to a kiosk similar to the ones in U.S. grocery stores. Customers could walk up, insert cash, and print a lottery ticket instantly. 
“It worked, but it had a ceiling,” Espinosa said. “It only served people buying lottery tickets. We knew it wouldn’t scale.”

To address this, he expanded the kiosks to handle mobile phone top-ups, bill payments, and basic banking services. Then, in 2024, the company incorporated advanced technologies such as biometric recognition and blockchain. Stellar Blockchain, first a partner, later became an investor of the startup, which helped Loto Punto to enable low-cost, real-time digital transactions and remittances. 

Now, users can convert physical cash into digital value or withdraw cash from digital wallets through a single machine.

A Global Solo Founder

Espinosa is the sole founder of Loto Punto, supported now by a 10‑person team of highly specialized engineers, designers, and manufacturing experts. He is currently pursuing his master’s degree in computer science at Georgia Tech while leading the company through its next chapter as part of the CREATE-X Startup Launch Spring 2026 cohort. 

Finding CREATE-X and Finding a Community

Espinosa learned about CREATE-X during his first semester at Georgia Tech. In 2024, CREATE-X widened its Startup Launch program to include a spring cohort to give founders, particularly graduating seniors, another chance to go all-in on developing their startup.

Espinosa admits he didn’t expect much when he first learned about the program.

“I didn’t know universities had programs like this. In Colombia, we don’t have accelerators embedded inside universities with venture support and dedicated staff,” he said. “So, I assumed CREATE X would be small, maybe one office helping a few students.”

What Espinosa found was different.

“They’re leveraging every resource that Georgia Tech offers. They can help with any challenge by tapping the doors of the network they already have established,“ he said. “It’s an ecosystem.”

As a part of the Startup Launch program, CREATE-X brings in founders from its ecosystem to speak to participants and give them actionable insights — founders who have raised funds, been acquired, and have had other successes as entrepreneurs. 

“That’s different,” Espinosa said. “They’ve brought successful founders who have walked the talk. It’s different to interact with somebody who was already successful in doing what you’re doing.”

Testing, Measuring, and Learning Through Startup Launch

Even as a remote participant, Espinosa has connected well with his mentor, who meets with him weekly, and his mini-batch. During the program, startup teams are grouped together. They share their strategies, successes, and struggles as they develop throughout the program. Teams have weekly sprints where they focus on one or two activities and then measure those activities, which Espinosa said is helpful for maintaining focus and actually executing on ideas.

“If you, as an entrepreneur, start thinking of the whole world of activities that you must do to get somewhere with your startup, you won’t start,” he said. “By creating attainable goals, step by step, that’s how it compounds to reach bigger goals. But, you have to begin with something.”
Teams are also encouraged to take calculated risks.

“CREATE-X gives us a safe environment to test ideas,” Espinosa said. “As an entrepreneur, it’s a lonely road, but having someone who has been in your shoes before, it makes you brave to try things.”

One of the first major tests he shared with the cohort was an ad campaign timed around the Super Bowl. In Startup Launch, Espinosa learned how to structure the experiment: defining KPIs, iterating audiences, and evaluating performance compared to industry benchmarks.

“We got around 45,000 views and above-average click-through rates,” he said. “But the biggest lesson was that brand awareness alone can’t be our only marketing strategy.”

Espinosa said his mentor helped open doors for him and kept him accountable, and the program itself kept him from being overwhelmed by all that a founder has to do.

“In Startup Launch, you see how different approaches fit different phases,” he said. “They’re creating a path to grow and execute on your goals as a founder.”

Why Now Is the Easiest Time to Build

Espinosa also emphasized that the tools to build and test ideas have never been more accessible.

“When I started, we didn’t have AI. You had to do everything by hand. It was harder, and it took more resources,” he said. “Right now, it’s a matter of prompting. In one hour, you can file for a grant. Before, it took at least a week to get your documents together.”

He said the ability to test quickly and learn has also become inexpensive.

“You don’t need millions of dollars to do this,” Espinosa said. “It's very cheap to fail, right? If that doesn't work, you can just try again in the morning.”

Above all, Espinosa encouraged budding founders to take advantage of the opportunities around them.

“As a founder, you must tap every door that you have available to you. You have to explore different paths,” he said. “Some of those are networking, some are physical space, some are interest. Get your hands on every single resource that comes your way.”

Looking Ahead: The Future of Payments

As he thinks about where the finance world is going, Espinosa said the payments industry is rapidly converging toward blockchain, stablecoins, and faster, frictionless user experiences.

“We’re seeing a lot of movement around stablecoins. We’re seeing resource flow from one country to another. We believe things are converging to leverage blockchain and driving down the cost of moving money,“ he said. “That’s how we see the future of our industry.”

Meet Loto Punto and the Spring Cohort at Startup Launch Showcase

Espinosa will travel to Atlanta for the first time in May to present Loto Punto at the CREATE-X Spring Startup Launch Showcase, where the public can meet founders and see their ventures firsthand. The event will be held in The Biltmore Ballrooms on Thursday, May 21, from 5 to 7 p.m.

The showcase will feature dozens of startups built by Georgia Tech students and alumni. Tickets are free but limited. Register for the showcase today to grab your spot.
 

“The topic of the Suddath Symposium changes every year, which allows the Georgia Tech research community to annually learn about recent advances on a specific topic from across the immense fields of bioengineering and bioscience,” said Nicholas Hud, Regents’ Professor in the School of Chemistry and Biochemistry and Associate Director of IBB.

The symposium also included presentation of the 2026 Suddath Award, which recognizes outstanding graduate research. This year’s award was presented to Myeongsoo Kim, a Ph.D. candidate in the Bioengineering Graduate Program, for his work at the intersection of cell engineering, cancer treatment, and biomedical imaging. The award is presented each year by members of the Suddath family, including Vincent Suddath, grandson of Bud and a current freshman at Georgia Tech majoring in mathematics.

The symposium and award honor the legacy of F. L. “Bud” Suddath and his lasting contributions to the Institute and the wider Georgia Tech research community.

“Bud was influential in promoting the growth of bioscience research at Georgia Tech, efforts that helped establish IBB in the 1990s,” Hud said. “Bud’s research interests were at the forefront of structural biology, a field that laid the foundation for much of what we know today about biology at the molecular level. It’s fitting that we honor Bud’s contributions by annually providing the Georgia Tech community with the opportunity to learn about research on a timely topic within the biological sciences.”

Symposium co-chairs Tara Deans and Mark Styczynski said that in addition to upholding the legacy of Bud Suddath, the event also provides a unique setting and opportunity for both established researchers and trainees to interact over the course of the two day event. The intimate format of the symposium, which is limited to approximately 100 attendees, and the annual selection of a different interdisciplinary topic sets it apart from other symposia.

“The Suddath Symposium is an amazing opportunity to bring multiple world-class researchers right to our trainees’ front door, to hear about their work and connect with them in a small setting that you can’t really find at most conferences,” said Styczynski, who is a professor in the School of Chemical and Biomolecular Engineering. “We are really grateful to IBB and the Suddath family for supporting this unique event.”

Deans, who is an associate professor in the Wallace H. Coulter Department of Biomedical Engineering, highlighted how this year’s theme reflects a broader shift in the field.

“This year’s focus on biomedical applications of synthetic biology highlights a major inflection point in the field: the transition from proof-of-concept systems to human health-relevant technologies,” she said. “The theme also reflects increasing convergence across disciplines; synthetic biology is no longer operating in isolation, but it is deeply intertwined with immunology, machine learning, diagnostics, and clinical translation. Addressing real-world biomedical problems requires this kind of integration, and the symposium captured that shift very clearly.”

The Suddath Symposium annually serves as a cornerstone event for Georgia Tech’s bioengineering and bioscience community — connecting researchers, honoring scientific legacy, and spotlighting the next generation of scientific innovation.

Jie Wu, an engineering graduate student, was studying a type of striking white beetle found in Southeast Asia and attempting to figure out how to mimic its brilliant color when an unexpected discovery upended the experiment.

Jie and I had been hoping to identify naturally occurring whitening pigments that could be used in paper and paints. The beetle’s white exoskeleton is made from a compound called chitin, which is a type of carbohydrate – one that is also commonly found in crab and lobster shells.

Read the full article in The Conversation here: https://bit.ly/4uBteYr

Every day, food scraps disappear into trash bags, are hauled away and forgotten. But that waste could be turned into something productive.

Across the United States, about 97 million metric tons of food waste are discarded each year, of which about 37 million metric tons end up buried in landfills.

Once underground, that organic material breaks down without oxygen and releases methane, a short-lived yet powerful greenhouse gas.

At the same time, the nutrients and energy stored in that food are permanently lost. But there is a better way. Research my colleagues and I conducted found that communities across the country already operate facilities designed to handle organic matter: wastewater treatment plants. Many larger, well-funded plants already have the infrastructure to process food waste, though not every plant is ready to do so today.

Landfills Are Not Designed for Food Waste

Food waste is fundamentally different from plastics, metals or glass. It’s organic and can decompose naturally. But when it’s placed in a landfill, its decomposition emits significant greenhouse gases.

Modern landfills are designed to capture the methane emitted, but even the most efficient systems still allow almost 58% to escape into the atmosphere. That food waste could be turned into energy or fertilizer, but instead it contributes to global warming.

By contrast, wastewater treatment plants process sewage using microbial communities that naturally break down organic matter. Many also capture methane produced during treatment and convert it into usable energy. Others recover nutrients such as phosphorus that can be turned into agricultural fertilizer. Over time, many plants have evolved from simple sanitation systems into resource-recovery facilities that generate power, reclaim materials and reduce environmental pollution.

These existing systems already process organic matter and could handle food waste, too.

What Happens When Food Waste Goes to a Treatment Plant

Our research examined what would happen if food waste were sent to wastewater treatment plants rather than landfills. We used real data from a full-scale plant that handles food waste along with sewage.

When we compared greenhouse gas emissions for the same food waste composition, we found that sending food to a landfill would emit 58.2 kilograms (129 pounds) of carbon dioxide equivalent per ton of food waste.

In comparison, we looked at a conventional wastewater treatment plant, the type of plant most common in the U.S. It achieved net-negative emissions of –0.03 kilograms (about 1 ounce) of carbon dioxide equivalent per ton of food waste treated. The plant captures over 95% of methane, compared to roughly 50% at landfills, saving the atmosphere from additional greenhouse gases.

But we found that the advanced treatment plant we studied reduced emissions further. In our analysis, the advanced facility achieved net-negative emissions of –0.19 kilograms (about 7 ounces) of carbon dioxide equivalent per ton of food waste treated.

Both conventional and advanced plants achieve these benefits in similar ways. Treating food waste at either type of plant prevents the 58.2 kilograms of carbon dioxide equivalent per ton that would otherwise escape from landfills. The plants capture biogas to generate renewable electricity, reducing the need to purchase power from the grid. They also recover enough nutrients to fertilize about 23 acres of farmland annually, reducing the need for synthetic fertilizers, which require energy-intensive mining and processing.

How the Logistics Work

Getting the food waste to a wastewater plant doesn’t mean people put their food scraps in the drain or grind them up with an in-sink disposal. At the plant we studied, food waste was collected separately, much like recycling or yard waste, and transported by truck to treatment plants. Our emissions calculations don’t include truck emissions, because trucks are used in the other methods of food waste disposal as well.

Some cities already collect food waste by truck to go to composting facilities. San Francisco has done so since 1996. And New York City has the nation’s largest curbside organics collection, which composts food waste from 3.4 million households.

At the southeastern U.S. treatment plant we studied, trucks deliver food waste to a receiving station, where it’s processed to remove plastics, metals and other nonorganic materials before being blended into a slurry with the sewage solids. This mixture is then added to anaerobic digesters – sealed tanks where microorganisms break down organic material.

The methane that is produced is captured to generate electricity and heat. The remaining solid material is rich in nutrients and can be used to produce useful material, such as fertilizer.

We also found that adding food waste did not overload the plant or cause problems in its operation. The facility processed all of the county’s landfilled food waste – 107,320 tons annually, representing 38% of the county’s total food waste generation. Because of food waste’s lower density compared to wastewater, this added only 0.43% to the plant’s daily capacity. The plant consistently met effluent water regulatory standards. And at certain points, treatment efficiency improved as a result of the additional organic material, which supported the system’s biological processes.

The Economics May Surprise Cities

Local officials, as well as taxpayers, are often worried about the potential costs of a project like this. Wastewater treatment is already expensive, and communities’ existing plants may be nearing capacity.

But the economic results from our analysis suggest that handling food waste in wastewater treatment plants can be financially viable. Towns already pay landfills and incinerators what are called “tipping fees,” based on the weight of the waste delivered. Wastewater treatment plants can also charge these fees.

They can also sell, or use themselves, the methane produced and sell the fertilizer. That additional income means plants can make money even if they charge lower tipping fees than landfills.

Not every wastewater plant is ready to accept food waste immediately. The facility we analyzed is large and well equipped. Smaller operations would likely require new or upgraded equipment, which would involve planning and local investment.

The overall finding of our research is that the limitation isn’t technological or financial. The core systems already exist to transform food waste into a recoverable resource: Cities already handle organic material every day. And they operate complex biological treatment systems. Our evidence suggests these facilities could, in fact, handle food waste in ways that are environmentally beneficial and economically realistic.

This article is republished from The Conversation under a Creative Commons license. Read the original article.

The U.S. military was able “to strike a blistering 1,000 targets in the first 24 hours of its attack on Iran” thanks in part to its use of artificial intelligence, according to The Washington Post. The military has used Claude, the AI tool from Anthropic, combined with Palantir’s Maven system, for real-time targeting and target prioritization in support of combat operations in Iran and Venezuela.

While Claude is only a few years old, the U.S. military’s ability to use it, or any other AI, did not emerge overnight. The effective use of automated systems depends on extensive infrastructure and skilled personnel. It is only thanks to many decades of investment and experience that the U.S. can use AI in war today.

In my experience as an international relations scholar studying strategic technology at Georgia Tech, and previously as an intelligence officer in the U.S. Navy, I find that digital systems are only as good as the organizations that use them. Some organizations squander the potential of advanced technologies, while others can compensate for technological weaknesses.

Myth and Reality in Military AI

Science fiction tales of military AI are often misleading. Popular ideas of killer robots and drone swarms tend to overstate the autonomy of AI systems and understate the role of human beings. Success, or failure, in war usually depends not on machines but the people who use them.

In the real world, military AI refers to a huge collection of different systems and tasks. The two main categories are automated weapons and decision support systems. Automated weapon systems have some ability to select or engage targets by themselves. These weapons are more often the subject of science fiction and the focus of considerable debate.

Decision support systems, in contrast, are now at the heart of most modern militaries. These are software applications that provide intelligence and planning information to human personnel. Many military applications of AI, including in current and recent wars in the Middle East, are for decision support systems rather than weapons. Modern combat organizations rely on countless digital applications for intelligence analysis, campaign planning, battle management, communications, logistics, administration and cybersecurity.

Claude is an example of a decision support system, not a weapon. Claude is embedded in the Maven Smart System, used widely by military, intelligence and law enforcement organizations. Maven uses AI algorithms to identify potential targets from satellite and other intelligence data, and Claude helps military planners sort the information and decide on targets and priorities.

The Israeli Lavender and Gospel systems used in the Gaza war and elsewhere are also decision support systems. These AI applications provide analytical and planning support, but human beings ultimately make the decisions.

The Long History of Military AI

Weapons with some degree of autonomy have been used in war for well over a century. Nineteenth-century naval mines exploded on contact. German buzz bombs in World War II were gyroscopically guided. Homing torpedoes and heat-seeking missiles alter their trajectory to intercept maneuvering targets. Many air defense systems, such as Israel’s Iron Dome and the U.S. Patriot system, have long offered fully automatic modes.

Robotic drones became prevalent in the wars of the 21st century. Uncrewed systems now perform a variety of “dull, dirty and dangerous” tasks on land, at sea, in the air and in orbit. Remotely piloted vehicles like the U.S. MQ-9 Reaper or Israeli Hermes 900, which can loiter autonomously for many hours, provide a platform for reconnaissance and strikes. Combatants in the Russia-Ukraine war have pioneered the use of first-person view drones as kamikaze munitions. Some drones rely on AI to acquire targets because electronic jamming precludes remote control by human operators.

But systems that automate reconnaissance and strikes are merely the most visible parts of the automation revolution. The ability to see farther and hit faster dramatically increases the information processing burden on military organizations. This is where decision support systems come in. If automated weapons improve the eyes and arms of a military, decision support systems augment the brain.

Cold War era command and control systems anticipated modern decision support systems such as Israel’s AI-enabled Tzayad for battle management. Automation research projects like the United States’ Semi-Automatic Ground Environment, or SAGE, in the 1950s produced important innovations in computer memory and interfaces. In the U.S. war in Vietnam, Igloo White gathered intelligence data into a centralized computer for coordinating U.S. airstrikes on North Vietnamese supply lines. The U.S. Defense Advanced Research Projects Agency’s strategic computing program in the 1980s spurred advances in semiconductors and expert systems. Indeed, defense funding originally enabled the rise of AI.

Organizations Enable Automated Warfare

Automated weapons and decision support systems rely on complementary organizational innovation. From the Electronic Battlefield of Vietnam to the AirLand Battle doctrine of the late Cold War and later concepts of network-centric warfare, the U.S. military has developed new ideas and organizational concepts.

Particularly noteworthy is the emergence of a new style of special operations during the U.S. global war on terrorism. AI-enabled decision support systems became invaluable for finding terrorist operatives, planning raids to kill or capture them, and analyzing intelligence collected in the process. Systems like Maven became essential for this style of counterterrorism.

The impressive American way of war on display in Venezuela and Iran is the fruition of decades of trial and error. The U.S. military has honed complex processes for gathering intelligence from many sources, analyzing target systems, evaluating options for attacking them, coordinating joint operations and assessing bomb damage. The only reason AI can be used throughout the targeting cycle is that countless human personnel everywhere work to keep it running.

AI gives rise to important concerns about automation bias, or the tendency for people to give excessive weight to automated decisions, in military targeting. But these are not new concerns. Igloo White was often misled by Vietnamese decoys. A state-of-the-art U.S. Aegis cruiser accidentally shot down an Iranian airliner in 1988. Intelligence mistakes led U.S. stealth bombers to accidentally strike the Chinese embassy in Belgrade, Serbia, in 1999.

Many Iraqi and Afghan civilians died due to analytical mistakes and cultural biases within the U.S. military. Most recently, evidence suggests that a Tomahawk cruise missile struck a girls school adjacent to an Iranian naval base, killing about 175 people, mostly students. This targeting could have resulted from a U.S. intelligence failure.

Automated Prediction Needs Human Judgment

The successes and failures of decision support systems in war are due more to organizational factors than technology. AI can help organizations improve their efficiency, but AI can also amplify organizational biases. While it may be tempting to blame Lavender for excessive civilian deaths in the Gaza Strip, lax Israeli rules of engagement likely matter more than automation bias.

As the name implies, decision support systems support human decision-making; AI does not replace people. Human personnel still play important roles in designing, managing, interpreting, validating, evaluating, repairing and protecting their systems and data flows. Commanders still command.

In economic terms, AI improves prediction, which means generating new data based on existing data. But prediction is only one part of decision-making. People ultimately make the judgments that matter about what to predict and how to use predictions. People have preferences, values and commitments regarding real-world outcomes, but AI systems intrinsically do not.

In my view, this means that increasing military use of AI is actually making humans more important in war, not less.

This article is republished from The Conversation under a Creative Commons license. Read the original article.

679670 image

AI is helping U.S. forces find and choose targets in Iran, like this airfield. U.S. Central Command via AP

]]> image/jpeg 1773852352 2026-03-18 16:45:52 1773852352 2026-03-18 16:45:52

The high cost of renting and buying homes in U.S. cities is no secret. But this affordability problem isn’t limited to urban regions – it affects rural areas as well.

Rural areas, home to about 25% of Americans, benefit from federally supported rental housing programs – particularly a U.S. Department of Agriculture program to provide affordable homes for low-income residents.

The USDA’s Section 515 program is the primary way that the U.S. government finances affordable rental homes in rural communities. Since its inception in 1963, the program has supported the construction of over 533,000 apartments, townhouses and other small, multifamily rental homes.

The program offers below-market-rate loans to private and nonprofit developers who build and manage residential housing for low-income residents in small towns and rural counties. The terms of the deal between property owners and the government obliges these landlords to keep rents affordable for their occupants for decades, generally restricting rent to about 30% of tenants’ income.

Last New Loans Were in 2011

People who live in Section 515 housing typically pay around US$325 per month. That’s much less than rural market-rate rents, which typically run $800-$1,100 per month for modest homes.

Because the USDA stopped issuing new Section 515 loans in 2011, this arrangement is phasing out now as existing loans mature.

Loans for about 90% of all remaining Section 515 homes will mature by 2045, according to the Housing Assistance Council, a national nonprofit that supports affordable housing efforts throughout rural America. By 2050, the owners of nearly all properties currently in the program’s portfolio are projected to have paid off their mortgages.

And once most of the owners of these homes exit the Section 515 program, it will have been fully phased out.

An Often-Overlooked Housing Program

As a public policy professor who studies housing, I wanted to understand what happens when Section 515 loans mature. I also was interested in what determines whether properties remain affordable or leave the program after the loans are paid off.

To find out, I worked with three other housing policy researchers on a national study that was peer-reviewed and published in Housing Policy Debate in September 2025.

As of 2024, these loans were still supporting some 400,000 homes on almost 13,000 properties across 87% of all U.S. counties.

The roughly 750,000 Americans in those homes are among the nation’s poorest. The average household income of someone living in Section 515 housing in 2023 was just about $16,000 per year, which was only about one-fifth of the national median household income, which hovered around $76,600 during the same period in inflation-adjusted 2023 dollars.

In addition to having a very low income, more than 60% of the people enrolled in the program are over 62, have disabilities, or fall into both of those categories.

Market-Rate Options After Maturity

The vast majority of these affordable rental homes were built in the 1970s through the 1990s and financed with USDA loans that last between 30 and 50 years.

By 2050, there will be no Section 515 housing left.

The owners of these rental properties no longer have to keep rents affordable once they have paid off their loans. And their owners and tenants may also lose access to a USDA rental assistance program, which helps keep tenants’ housing costs low.

They can refinance the homes or sell the properties. They also can continue to charge affordable rents to occupants or convert those units to market rate. Because of this flexibility, a large share of rural affordable housing units could soon be converted to properties rented at market rates.

What the Data Shows So Far

For this study, our research team analyzed data from nearly 15,000 of the Section 515 properties throughout the country, which have been placed in service since 1963 – including many that are no longer providing rural affordable housing.

We found that the largest factors determining whether a building remains affordable after a Section 515 loan matures are who owns and manages that property. Buildings owned by for-profit companies are far more likely to leave the program than those that belong to nonprofit housing organizations.

Nonprofit-owned buildings, after accounting for building age and local market conditions, are 30% to 40% less likely to convert formerly Section 515 affordable housing into market-rate properties after the owners pay off their loans.

After analyzing this data, we also concluded that buildings run by small property management companies are more likely to leave the program than those managed by larger ones. Properties where the owner manages the homes are also more likely to exit.

Landlords owning more residential properties were also more likely to exit the program. This indicates that larger landlords may be able to afford the renovations and upgrades required to turn their buildings into market-rate housing once restrictions end.

Why Subsidies and Local Markets Matter

Having subsidies through other government programs can help keep affordable housing units from being converted to market-rate housing.

One-third of Section 515 properties also get support from other programs, including Section 8 vouchers and low-income housing tax credits. Those tax credits are another federal incentive that’s provided to developers who build and rehabilitate affordable rental housing while allowing lower rents for low-income tenants.

Those properties are more likely to remain affordable, even years after some of these tax incentives expire.

Local economic conditions can play a role too. In areas with high unemployment rates, large military populations and low housing inventory, properties are also more likely to exit the program.

That means the same rural counties experiencing economic or demographic pressures are often the most likely to have a decline in affordable housing units when owners pay off their Section 515 loans.

Steps That Can Be Taken

Congress and the USDA have taken some steps to slow the loss of affordable housing in rural areas.

For example, the USDA has funded preservation efforts such as the Multifamily Housing Preservation and Revitalization pilot program, which provides grants, loan restructuring and other financing tools to help repair aging Section 515 properties and extend their affordability.

These efforts have helped preserve some buildings and support ownership transfers from private sector landlords to nonprofit housing groups. But they spend only tens of millions of dollars per year and focus mainly on maintaining existing properties rather than building new housing.

Researchers estimate that about $5.6 billion in repairs would be needed to preserve the affordable housing currently tied to the Section 515 program.

Some lawmakers have proposed reforms aimed at doing more than chipping away at the loss of this kind of affordable housing. The bipartisan Rural Housing Service Reform Act, first introduced in 2023 and reintroduced in 2025, would modernize USDA rural housing programs and allow certain rental assistance contracts to continue after mortgages mature. As of early 2026, the bill remains under consideration.

Over the next two decades, most of these landlords will pay off their Section 515 loans. Unless the government reinvigorates the program or replaces it with something else, much of rural America’s affordable rental housing could gradually disappear as owners convert all Section 515 properties to market-rate housing.

Whether rural communities retain affordable housing will depend not only on what the federal government does, but also on the properties’ owners.

This article is republished from The Conversation under a Creative Commons license. Read the original article.

“The effects move slowly and appear in places people do not connect to energy,” said Tibor Besedes, professor in the School of Economics. “Oil and natural gas are part of the cost structure for an enormous range of goods.”

About 20% of global oil and liquefied natural gas flows through the waterway linking the Persian Gulf to world markets. When that flow is constrained, the impact ripples outward across industries most people never associate with an energy crisis.

“In complex supply chains, a disruption in one critical link, even if only briefly, can cascade through the system, well beyond the initial event,” says Pinar Keskinocak, chair and professor in the H. Milton Stewart School of Industrial and Systems Engineering. “As delays persist and compound, interconnected systems often take a long time to recover, rebalance, and return to normal.”

Price Pressures That Arrive Quietly

Early effects are already visible. 

Jet fuel availability is tightening, and diesel prices are rising across Asia. China has ordered refineries to stop exporting fuel, creating shortages that are increasing shipping costs for U.S. imports, from consumer electronics to pharmaceuticals.

The strait is also a key corridor for naphtha, a feedstock used to produce plastics, packaging, solvents, textiles, and pharmaceutical components. Roughly 85% of Middle Eastern polyethylene exports move through the strait. 

“Consumers won't see the effect of this quickly,” Besedes says, “but the longer the strait is closed, the higher the cost will be of all of these products naphtha is used for.”

Aluminum is equally exposed. 

“Smelters require sustained, low-cost energy,” said Chris Gaffney, a professor of the practice in the Stewart School. “The Middle East accounted for roughly 21% of U.S. unwrought aluminum imports in 2025. When energy prices spike or supply is constrained, capacity is reduced or shut down, and those decisions are difficult and slow to reverse.”

Fertilizer is one of the clearest examples of delayed inflation. Natural gas is essential for its production, and Persian Gulf states account for one-third of global urea exports and half of global sulfur exports. Urea prices at the New Orleans import hub have already climbed sharply.

“We won't see the effects quickly, but rather in six to 12 months, depending on the crop and its cycle,” Besedes says. “Without or with less fertilizer, crop yields will decrease, resulting in higher prices.”

Why Hormuz Is Different From Other Chokepoints

On top of all those factors, the strait closure presents a uniquely dangerous vulnerability. 

“Unlike a port strike or canal blockage, there is no meaningful way to reroute volume,” says Gaffney. “If it is disrupted, flow is constrained rather than redirected.” Pipeline alternatives replace only a fraction of the 20 million barrels per day that normally transit the strait.

“Choke point vulnerability arises when a large portion of flow depends on a route that is hard to substitute,” said Mathieu Dahan, associate professor in the Stewart School. “Hormuz has no scalable alternatives with sufficient capacity.” 

Alan Erera, senior associate chair in the Stewart School expanded on Dahan’s point, noting that strait disruptions raise costs across manufacturing and distribution.

“Ships are rerouted onto longer paths, which drives up fuel and labor costs, ties up vessels and containers for longer periods, and ultimately raises inventory costs for shippers because capital is locked up while goods are still in transit,” Erera said.

When Geopolitics Meets Global Supply Chains

Additionally, the strait closure raises the risk of wartime miscalculation. 

“We haven’t seen a disruption on this scale since the tanker wars of the late 1980s,” said Larry Rubin, associate professor in the Sam Nunn School of International Affairs. Gulf states' dependence on the strait constrains both regional actors and U.S. strategy, raising risks around crisis decision-making.

Rubin also points to a dimension most coverage has missed entirely. “One thing that has been overlooked by many commentators is the fact that the Iranian people have probably been hit the hardest economically,” he says. “They were already in a challenging situation. The Iranian economy won't recover quickly after the war.”

Resilience Has a Short Memory

Meanwhile, for the United States, “The Strategic Petroleum Reserve provides a buffer, and domestic energy production has improved resilience,” says Gaffney. “But the gap remains between enabling capacity and sustaining resilience. Policy can support infrastructure, but it cannot ensure private sector participants invest in resilience when cost pressures rise.”

For policymakers and industry leaders, the disruption reinforces a familiar pattern. "The supply chain remains optimized for efficiency rather than resilience, in part due to the high investment costs required to build flexibility," says Dahan. 

Gaffney added that resilience does improve after disruption, but that “it erodes over time if not actively maintained.”

Even if the strait reopens, higher costs and slow restart timelines mean the system will not snap back. Experts suggest that when headlines have moved on from this disruption, it will still be shaping prices across the economy. 

The approaches of over a dozen quantum computing companies are now being evaluated through the Quantum Benchmarking Initiative (QBI), a project of the U.S. Defense Advanced Research Projects Agency (DARPA). According to the agency, QBI “aims to rigorously verify and validate whether any quantum computing approach can achieve utility-scale operation – meaning its computational value exceeds its cost – by the year 2033.”
 

Supporting the effort, a 40-person interdisciplinary research team from the Georgia Tech Research Institute (GTRI) has joined the test and evaluation component of QBI, providing unbiased subject-matter experts to work with 13 other research organizations in evaluating the R&D plans of participating quantum computer companies. Through this collaboration, the GTRI team is working with more than 400 other third-party experts on the project.
 

Read the complete article on the GTRI news site

TokenSmith is a citation-supported large language model (LLM) tutor that can be hosted locally on a user’s personal computer. The tutor only provides answers based on course materials, such as the textbook or lecture slides.  

Associate Professor Joy Arulraj began the project with support from the Bill Kent Family Foundation AI in Higher Education Faculty Fellowship last year. The fellowship, led by Georgia Tech’s Center for 21st Century Universities, supports faculty projects exploring innovative and ethical uses of AI in teaching.   

Arulraj has enlisted assistant professors Kexin Rong and Steve Mussmann to help build TokenSmith.  

Mussmann said TokenSmith is a synergistic blend of a database system and a machine learning system. The model stores textbooks, textbook annotations by course staff, common questions and answers, a learning state of the student, and student feedback in a structured database system. However, machine learning plays a key role in the answer generation as well as adapting the system to the student, course staff guidance, and user feedback.

"What excites me most is demonstrating how data-driven ML and principled database systems design can reinforce each other — one providing adaptability and flexibility, the other providing structure and traceability — in a way that benefits students," Mussmann said.

Keeping the model local has been an important focus of the project. The team wanted to create an AI tutor that helps students learn from their class resources rather than just giving answers. With each response, TokenSmith cites the origin of the answer in the provided documents.  

“One problem with LLMs is that they can hallucinate and provide wrong answers, but in this controlled environment, we can add these guardrails to make sure it’s actually helpful in an educational setting,” Rong said.  

Rong said she feels that students often undervalue textbooks, and she hopes TokenSmith can motivate students to make better use of them.  

“Textbooks can sometimes be daunting, but maybe if we combine them with the model, students might be more willing to read a paragraph or page in the textbook, and that could help clarify something for them,” she said.  

Running the model locally is more cost-effective and helps preserve the user’s privacy. But running the new tool locally comes with technical challenges.  

One challenge with creating the model is speed. Since it is a locally based model, TokenSmith depends solely on the user’s computer memory.  Tests have also shown that the tutor currently struggles to answer more complex questions. 

“We are interested in pushing the boundaries of these local models so that they give students good answers and also run fast enough to keep students engaged,” Arulraj said.  

A team of researchers led by Ankur Singh, the Carl Ring Family Professor in the George W. Woodruff School of Mechanical Engineering and professor in the Wallace H. Coulter Department of Biomedical Engineering at Georgia Tech and Emory University, has been awarded up to $6 million from the Defense Threat Reduction Agency (DTRA) of the U.S. Department of Defense to accelerate the development of medical countermeasures (MCMs) against deadly biological threats that endanger public health, national security, and warfighters.

DTRA’s mission is to provide solutions that enable the Department of Defense, the U.S. government, and international partners to deter strategic threats. A key priority is advancing new or improved MCMs that can be deployed before or after exposure to biological or chemical agents.

Singh’s multi-year project, Systematic Human Immune Engineering for Lethal Disease (SHIELD) Countermeasures, aims to create a threat-agnostic platform that transforms how respiratory pathogens and toxins are studied. The platform is designed to speed up the discovery, development, and production of immune-based countermeasures.

Singh leads a collaborative team that includes Cornell University’s Matthew DeLisa and Stanford University’s Michael Jewett. Together, they will integrate immune-engineering technologies with advanced cell-free protein synthesis platforms to discover and manufacture protein-based MCMs. Cell-free protein synthesis is a laboratory technique that efficiently produces proteins without relying on living cells, which can be unpredictable and technically demanding when it comes to expressing complex or toxic proteins and scaling production quickly. The team expects the SHIELD Countermeasures platform to reduce the time and cost of MCM development by more than tenfold.

“The foundational science and cutting-edge tools we develop will ignite future discoveries, ensuring a robust pipeline of advanced protein-based MCMs for chemical and biological defense,” said Singh, who also directs the Center for Immunoengineering at Georgia Tech. “This will significantly enhance national security and equip our warfighters with next-generation biodefense capabilities."

Traditional animal models often fail to accurately replicate human immune responses, and standard tissue cultures lack the complexity required to study how immune cells interact with pathogens. In contrast, human immune organoids and immune-competent devices — built from human cells — are emerging as groundbreaking research tools. These systems recreate key immune features, such as lymph nodes and mucosal environments, within three-dimensional or microengineered platforms.

“Many organoid and engineering devices, often called organ-on-chip platforms, lack immune integration,” Singh said. “Because immunity sits at the center of human health, these limitations have broad consequences. Immune-competent organ-on-chip platforms extend this concept by combining human cells with microfluidic engineering that simulates blood flow, tissue barriers, and chemical gradients.”

Singh has previously published studies on a synthetic human immune chip and an immunocompetent lung on a chip, and has also teamed up with DeLisa previously to use synthetic immune organoids for immuno-profiling antibacterial MCMs.

“It’s about being able to test far larger numbers of candidate protein-based MCMs in a single experiment—and to do it much faster,” DeLisa said. “Cell-free systems allow us to produce MCMs at unprecedented speed and scale, but traditional evaluation methods can’t keep up with those numbers. By combining cell-free MCM production with immune organoid technology, we can assess the potency of dozens or even hundreds of candidates at a time and characterize the resulting immune responses within just a few days.”

By integrating immune cells with tissues such as lung, gut, skin, or vascular systems, these devices allow scientists to observe immune responses in real time, including cell migration, inflammation, and interactions with pathogens or therapeutics. As biological threats evolve, the development and deployment of immune-competent platforms will be critical for rapid, effective countermeasures.

DTRA’s investment in Singh’s work highlights the urgent national priority of strengthening U.S. biodefense capabilities. The SHIELD Countermeasures platform and its cutting-edge technologies promise to transform the nation’s response to biological threats and help safeguard communities from biological and chemical attacks.

A philanthropic gift from the family of J.P. Singh is helping researchers at Georgia Tech push the boundaries of biomedical innovation.  

With imitation learning, humans demonstrate a task and robots learn to copy what they see through cameras and sensors. While at the leading edge of robotics research, this approach is limited by a major constraint: Robots can only work as fast as the people who taught them. 

Now, Georgia Tech researchers have created a tool that smashes that speed barrier. The system allows robots to execute complex tasks significantly faster than human demonstrations while maintaining precision, control, and safety.

The team addresses a central challenge in modern robotics: how to combine the flexibility of learning from humans with the speed and reliability required for real-world deployment. The technology could lead to wider adoption of imitation learning in industrial and household applications and even enable robots to execute humanlike tasks better than ever before. 

“The thing we’re trying to create — and I would argue industry is also trying to create — is a general-purpose robot that can do any task that human hands can do,” said Shreyas Kousik, assistant professor in the George W. Woodruff School of Mechanical Engineering and a co-lead author on the study. “To make that work outside the lab, speed really matters.”

The new tool, SAIL (Speed Adaptation for Imitation Learning), was born out of a cross-campus, interdisciplinary collaboration that brought together expertise in mechanical engineering, robotics systems, and machine learning. The research team includes Kousik; Benjamin Joffe, senior research scientist at the Georgia Tech Research Institute; and Danfei Xu, assistant professor in the School of Interactive Computing, along with graduate students and researchers from multiple labs.

Speed Without Sacrifice

Teaching robots to work faster than the speed of human demonstrations is challenging. Robots can behave differently at higher speeds, and small changes in the environment can cause errors. 

“The challenge is that a robot is limited to the data it was trained on, and any changes in the environment can cause it to fail,” Kousik said.

SAIL addresses this challenge through a modular approach, with separate components working together to accelerate beyond the training data. The system keeps motions smooth at high speed, tracks movements accurately, adjusts speed dynamically based on task complexity, and schedules actions to account for hardware delays. This combination allows robots to move quickly while staying stable, coordinated, and precise.

“One of the gaps we saw was that our academic robotics systems could do impressive things, but they weren’t fast or robust enough for practical use,” Joffe said. “We wanted to study that gap carefully and design a system that addressed it end to end.”

He added, “The goal is not just to make robots faster, but to make them smart enough to know when speed helps and when it could cause mistakes.” 

The team evaluated SAIL’s performance across 12 tasks, both in simulation and on two physical robot platforms. Tasks included stacking cups, folding cloth, plating fruit, packing food items, and wiping a whiteboard. In most cases, SAIL-enabled robots completed tasks three to four times faster than standard imitation-learning systems without losing accuracy.

One exception was the whiteboard-wiping task, where maintaining contact made high-speed execution difficult.

 “Understanding where speed helps and where it hurts is critical,” Kousik said. “Sometimes slowing down is the right decision.”

While SAIL does not make robots universally adaptable on its own, it represents an important step toward robotic systems that can learn from humans without being constrained by human pace.

By showing how learned robotic behaviors can be accelerated safely and systematically, SAIL brings imitation learning closer to real-world use — where speed, precision, and reliability all matter.

Citation: Ranawaka Arachchige, et. al. “SAIL: Faster-than-Demonstration Execution of Imitation Learning Policies,” Conference on Robot Learning (CoRL), 2025. 

DOI: https://doi.org/10.48550/arXiv.2506.11948

Funding: The authors would like to acknowledge the State of Georgia and the Agricultural Technology Research Program at Georgia Tech for supporting the work described in this paper. 

The new study is the first to visualize mosquito flight patterns and provides hard data for improving capture and control strategies. In addition to being a nuisance, mosquitoes transmit diseases such as malaria, yellow fever, and Zika, which cause more than 700,000 deaths every year.

“It’s like a crowded bar,” said David Hu, a professor in Georgia Tech’s George W. Woodruff School of Mechanical Engineering and the School of Biological Sciences, with an adjunct appointment in the School of Physics. “Customers aren’t there because they followed each other into the bar. They’re attracted by the same cues: drinks, music, and the atmosphere. The same is true of mosquitoes. Rather than following the leader, the insect follows the signals and happens to arrive at the same spot as the others. They’re good copies of each other.”

Read more and watch: 
Georgia Tech College of Engineering newsroom and The Conversation

ISyE researchers are applying AI to complex manufacturing environments, including multistage production systems, asset management, quality improvement, and human‑centered manufacturing. Faculty leaders emphasize the importance of contextualizing large volumes of manufacturing data so AI can support reliable decision‑making, efficient operations, and sustainable outcomes. At the same time, the initiative acknowledges challenges such as data integration, system complexity, and the need to balance automation with human involvement. Together, these efforts position ISyE at the forefront of shaping AI‑powered manufacturing systems that are innovative, resilient, and socially responsible.

Read the full article in ISyE Magazine 

Is the whole universe just a simulation? – Moumita B., age 13, Dhaka, Bangladesh

How do you know anything is real? Some things you can see directly, like your fingers. Other things, like your chin, you need a mirror or a camera to see. Other things can’t be seen, but you believe in them because a parent or a teacher told you, or you read it in a book.

As a physicist, I use sensitive scientific instruments and complicated math to try to figure out what’s real and what’s not. But none of these sources of information is entirely reliable: Scientific measurements can be wrong, my calculations can have errors, even your eyes can deceive you, like the dress that broke the internet because nobody could agree on what colors it was.

Because every source of information – even your teachers – can trick you some of the time, some people have always wondered whether we can ever trust any information.

If you can’t trust anything, are you sure you’re awake? Thousands of years ago, Chinese philosopher Zhuangzi dreamed he was a butterfly and realized that he might actually be a butterfly dreaming he was a human. Plato wondered whether all we see could just be shadows of true objects. Maybe the world we live in our whole lives inside isn’t the real one, maybe it’s more like a big video game, or the movie “The Matrix.”

The Simulation Hypothesis

The simulation hypothesis is a modern attempt to use logic and observations about technology to finally answer these questions and prove that we’re probably living in something like a giant video game. Twenty years ago, a philosopher named Nick Bostrom made such an argument based on the fact that video games, virtual reality and artificial intelligence were improving rapidly. That trend has continued, so that today people can jump into immersive virtual reality or talk to seemingly conscious artificial beings.

Bostrom projected these technological trends into the future and imagined a world in which we’d be able to realistically simulate trillions of human beings. He also suggested that if someone could create a simulation of you that seemed just like you from the outside, it would feel just like you inside, with all of your thoughts and feelings.

Suppose that’s right. Suppose that sometime in, say, the 31st century, humanity will be able to simulate whatever they want. Some of them will probably be fans of the 21st century and will run many different simulations of our world so that they can learn about us, or just be amused.

Here’s Bostrom’s shocking logical argument: If the 21st century planet Earth only ever existed one time, but it will eventually get simulated trillions of times, and if the simulations are so good that the people in the simulation feel just like real people, then you’re probably living on one of the trillions of simulations of the Earth, not on the one original Earth.

This argument would be even more convincing if you actually could run powerful simulations today, but as long as you believe that people will run those simulations someday, then you logically should believe that you’re probably living in one today.

Signs We’re Living in a Simulation …Or Not

If we are living in a simulation, does that explain anything? Maybe the simulation has glitches, and that’s why your phone wasn’t where you were sure you left it, or how you knew something was going to happen before it did, or why that dress on the internet looked so weird.

There are more fundamental ways in which our world resembles a simulation. There is a particular length, much smaller than an atom, beyond which physicists’ theories about the universe break down. And we can’t see anything more than about 50 billion light-years away because the light hasn’t had time to reach us since the Big Bang. That sounds suspiciously like a computer game where you can’t see anything smaller than a pixel or anything beyond the edge of the screen.

Of course, there are other explanations for all of that stuff. Let’s face it: You might have misremembered where you put your phone. But Bostrom’s argument doesn’t require any scientific proof. It’s logically true as long as you really believe that many powerful simulations will exist in the future. That’s why famous scientists like Neil deGrasse Tyson and tech titans like Elon Musk have been convinced of it, though Tyson now puts the odds at 50-50.

Others of us are more skeptical. The technology required to run such large and realistic simulations is so powerful that Bostrom describes such simulators as godlike, and he admits that humanity may never get that good at simulations. Even though it is far from being resolved, the simulation hypothesis is an impressive logical and philosophical argument that has challenged our fundamental notions of reality and captured the imaginations of millions.

Hello, curious kids! Do you have a question you’d like an expert to answer? Ask an adult to send your question to CuriousKidsUS@theconversation.com. Please tell us your name, age and the city where you live.

And since curiosity has no age limit – adults, let us know what you’re wondering, too. We won’t be able to answer every question, but we will do our best.

This article is republished from The Conversation under a Creative Commons license. Read the original article.

The paper examines various strategies for enhancing the flexibility of data center energy use. One approach is to use backup power systems, such as uninterruptible power supplies, to support the grid during emergencies. Another method involves rerouting computing jobs to different data centers in other locations to balance energy demand. The authors also discuss implementing smart scheduling techniques that shift workloads to off-peak hours, reducing strain on the grid. Additionally, they highlight adjusting processor speeds by lowering CPU (central processing unit) and GPU (graphics processing unit) clock rates to limit power consumption when needed. Finally, the paper suggests pre-cooling data center equipment to limit the energy required for cooling during peak demand periods. Notably, experimental evidence shows that underclocking GPUs can cut power consumption by 40% with only a 22% performance loss, suggesting technical feasibility for demand-response interventions.

Despite these technical options, the authors find that real-world cost considerations and reliability concerns limit widespread adoption. Data center operators generally do not change their behavior in response to electricity prices, as job revenue far outweighs energy costs under normal conditions. For example, a GPU rented at $2 per hour consumes only $0.04 worth of electricity at average prices, making curtailment unattractive except during extreme price spikes. Surveys indicate that operators are reluctant to compromise reliability or deploy backup systems for ancillary services. Consequently, price-based incentives alone are unlikely to drive meaningful flexibility.

Read more on the EPIcenter Webpage
Listen to a podcast on the research here

This Thursday, April 2, the College of Sciences is hosting an inspiring look at the future of space exploration and life beyond Earth. Frontiers in Science: Advancing Space Exploration will convene leading scientists, engineers, policy experts, and thought leaders from across Georgia Tech and beyond to share research that’s guiding discovery and innovation. 

That’s one of the main findings from a study by AI Caring on what older adults expect from explainable AI (XAI).

AI Caring is one of three AI Institutions led by Georgia Tech and funded by the National Science Foundation (NSF). The institution supports AI research that benefits older adults and their caregivers.

Niharika Mathur, a Ph.D. candidate in the School of Interactive Computing, was the lead author of a paper based on the study. The paper will be presented in April at the 2026 ACM Conference on Human Factors in Computing Systems (CHI) in Barcelona.

Mathur worked with the Cognitive Empowerment Program at Emory University to interview 23 older adults who live alone and use voice-activated AI assistants like Amazon’s Alexa and Google Home.

Many of them told her they feel excluded from the design of these products.

“The assumption is that all people want interactions the same way and across all kinds of situations, but that isn’t true,” Mathur said. “How older people use AI and what they want from it are different from what younger people prefer.”

One example she gave is that young people tend to be informal when talking with AI. Older people, on the other hand, talk to the agent like they would a person.

“If Older adults are talking to their family members about Alexa, they usually refer to Alexa as ‘she’ instead of ‘it,’” Mathur said. “They tend to humanize these systems a lot more than young people.”

Good Explanations

The study evaluated AI explanations that drew information from four sources of data:

• User history (past conversations with the agent)
• Environmental data (indoor temperature or the weather forecast)
• Activity data (how much time a user spends in different areas of the home)
• Internal reasoning (mathematical probabilities and likely outcomes)

Mathur said older users trust the agent more when it bases its explanations on data from the first three sources. However, internal reasoning creates skepticism.

Internal reasoning means the AI doesn’t have enough data from the other sources to give an explanation. It provides a percentage to reflect its confidence based on what it knows.

“The overwhelming response was negative toward confidence scores,” Mathur said. “If the AI says it’s 92% confident, older adults want to know what that’s based on.”

This is another example that Mathur said points to generational preferences.

“There’s a lot of explainable AI research that shows younger people like to see numbers in explanations, and they also tend to rely too much on explanations that contain numerical confidence. Older adults are the opposite. It makes them trust it less.”

Knowing the Context

Mathur said that AI agents interacting with older adults should serve a dual purpose. They should provide users with companionship and support independence while reducing the caretaking burden often placed on family members. 

Some studies have shown that engineers have tended to favor caretakers in the design of these tools. They prioritize daily tasks and routines, leaving some older adults to feel like they are merely a box to be checked.

She discovered that in urgent situations, older users prefer the AI to be straightforward, while in casual settings, they desire more conversation.

“How people interact with technological systems is grounded in what the stakes of the situation are,” she said. “If it had anything to do with their immediate sense of safety, they did not want conversational elaboration. They want the AI to be very direct and factual.”

Not Just Checking Boxes

Mathur said AI agents that interact with older adults are ideally constructed with a dual purpose. They should provide companionship and autonomy for the users while alleviating the burden of caretaking that is often placed on their family members. 

Some studies have shown that engineers have strayed toward favoring caretakers in the design of these tools. They prioritize daily tasks and routines, leaving some older adults to feel like they are a box to be checked.

“They’re not being thought of as consumers,” Mathur said. “A lot of products are being made for them but not with them.”

She also said psychological well-being is one of the most important outcomes these tools should produce. 

Showing older adults that they are listened to can significantly help in gaining their trust. Some interviewees told Mathur they want agents who are deliberate about understanding their preferences and don’t dismiss their questions.

Meeting these needs reduces the likelihood of protesting and creating conflict with family members.

“It highlights just how important well-designed explanations are,” she said. “We must go beyond a transparency checklist.”

As new data centers continue to be built and proposed in Georgia, counties and municipalities across the state are considering how to guide this growth. EPIcenter’s data center dashboard provides policymakers, planners, researchers, and community stakeholders with a centralized resource to better understand how data center regulations are being developed and applied across Georgia and the U.S.

“Our Data Center Hub provides Georgia communities with a one-stop shop to understand how their neighbors are managing land-use regulations for data centers,” said Laura Taylor, director of EPIcenter. “It brings together clear, accessible information to help jurisdictions plan when data center growth occurs in their area.”

The dashboard is organized around five thematic areas commonly addressed in data center land-use regulations: Site Planning and Building Design, Infrastructure and Utilities, Environmental and Community Protections, Public Safety and Security, and Lifecycle Governance. Within each theme, users can explore specific regulatory topics and access the relevant ordinances enacted by Georgia communities.

To build the dashboard, EPIcenter researchers conducted a comprehensive review of municipal codes across the state.

“We reviewed municipal codes for about 180 cities and counties across Georgia and identified ordinances that specifically address data center development,” said Yang You, EPIcenter’s research associate who developed the project. “In total, we found 19 data center-specific topics that ordinances tend to cover. We analyzed ordinances across jurisdictions and organized their ordinance provisions into topics such as building placement, setbacks, infrastructure, and environmental considerations to make it easier to compare how different jurisdictions regulate data centers.”

You added that the dashboard also incorporates examples from outside of Georgia. By gathering ordinances from other states and pairing them with Georgia-specific examples, EPIcenter aims to provide a clear framework to help communities efficiently address data center land-use regulation.

The Georgia Data Center Ordinance Hub is available through the Energy Policy and Innovation Center website.

That support, however, begins to disappear in these restrictive cultures once women reach menopause, according to new research from Georgia Tech

Naveena Karusala, an assistant professor in Georgia Tech’s School of Interactive Computing, and master’s student Umme Ammara are working toward improving existing technologies and designing new ones for a demographic they believe has been neglected.

Karusala and Ammara co-authored a paper based on a study they conducted with women in urban Pakistan experiencing menopause.

“Women’s health is understudied in general, but menopause is more neglected than other women’s health issues,” Karusala said. “Our choice to focus on menopause is motivated by expanding how we holistically think about women’s well-being across their lifespan.”

Karusala and Ammara will present their paper in April at the 2026 ACM Conference on Human Factors in Computing Systems (CHI) in Barcelona.

Masking Symptoms

Menopause is diagnosed after 12 consecutive months without a period, vaginal bleeding, or spotting. The transition to menopause, called perimenopause, usually happens over two to eight years.

Hormone changes may cause symptoms such as irregular periods, vaginal dryness, hot flashes, night sweats, trouble sleeping, mood swings, and brain fog.

These symptoms can be debilitating in some cases and affect daily life. However, Ammara said women are pressured to remain silent, maintain appearances, and regulate their emotions to meet social expectations.

“Understanding menopause is important because a woman would be experiencing all these symptoms, and people will not understand those as actual symptoms,” Ammara said. “There’s been resistance to the idea of the medicalization of menopause. People don’t view it as an illness, but as a life transition and something that happens naturally.”

Feeling Isolated

The women interviewed by Karusala and Ammara either stayed at home full-time or were part of the workforce.

The researchers discovered that trusted family members might be the only sources women who stay at home and do not work turn to for disclosure. 

“Women at home have the flexibility to take breaks or work at their own pace, so a lot of their experience is shaped by the emotional barriers they face,” Ammara said. 

“That could come from their husbands and family members. Some are supportive and some are not. They might weaponize it and use that term against them, or they might dismiss what they’re going through.”

Ammara said it might be easier for women in the workforce to confide in their coworkers, but explaining to an employer that they need sick leave for menopause symptoms can be intimidating.

Even in online communities that have enabled women to anonymously share their health experiences, menopause is seldom discussed.

Raising Awareness

Karusala and Ammara argue in their paper that a public health approach could be the most effective way to spark conversation about menopause in a patriarchal culture in which technology use varies.

They said the challenge in implementing technologies geared toward menopause support is that the condition isn’t well understood in public. Improving maternal health, for example, is easier to promote within these societies because of the general understanding that motherhood is important.

“There must be an existing infrastructure to build on,” Karusala said. “For example, menstrual and maternal health are taught in schools and regularly discussed in primary care. Cultural and social meaning and importance are placed on motherhood.

“A lot of that doesn’t exist for menopause. Primary care doctors are unprepared to talk about menopause compared to other health issues.”

Design Solutions

Ammara said that the most effective way for technologies to make an impact on women going through menopause is to directly address systemic power structures around women’s health within Pakistani culture.

It can start with the husbands. 

“Framing the issue for husbands to understand menopause should be at the forefront of designing technology solutions,” she said. 

“In Islamic contexts, we suggest using faith-based framings. This has been proposed for maternal health in prior works that draw on Islamic principles to engage expectant fathers in providing care and support. Framing it around religious responsibility to involve men in the journey can also be done for menopause.”

The darkness that swept over the Venezuelan capital in the predawn hours of Jan. 3, 2026, signaled a profound shift in the nature of modern conflict: the convergence of physical and cyber warfare. While U.S. special operations forces carried out the dramatic seizure of Venezuelan President Nicolás Maduro, a far quieter but equally devastating offensive was taking place in the unseen digital networks that help operate Caracas.

The blackout was not the result of bombed transmission towers or severed power lines but rather a precise and invisible manipulation of the industrial control systems that manage the flow of electricity. This synchronization of traditional military action with advanced cyber warfare represents a new chapter in international conflict, one where lines of computer code that manipulate critical infrastructure are among the most potent weapons.

To understand how a nation can turn an adversary’s lights out without firing a shot, you have to look inside the controllers that regulate modern infrastructure. They are the digital brains responsible for opening valves, spinning turbines and routing power.

For decades, controller devices were considered simple and isolated. Grid modernization, however, has transformed them into sophisticated internet-connected computers. As a cybersecurity researcher, I track how advanced cyber forces exploit this modernization by using digital techniques to control the machinery’s physical behavior.

Hijacked Machines

My colleagues and I have demonstrated how malware can compromise a controller to create a split reality. The malware intercepts legitimate commands sent by grid operators and replaces them with malicious instructions designed to destabilize the system.

For example, malware could send commands to rapidly open and close circuit breakers, a technique known as flapping. This action can physically damage massive transformers or generators by causing them to overheat or go out of sync with the grid. These actions can cause fires or explosions that take months to repair.

Simultaneously, the malware calculates what the sensor readings should look like if the grid were operating normally and feeds these fabricated values back to the control room. The operators likely see green lights and stable voltage readings on their screens even as transformers are overloading and breakers are tripping in the physical world. This decoupling of the digital image from physical reality leaves defenders blind, unable to diagnose or respond to the failure until it is too late.

Historical examples of this kind of attack include the Stuxnet malware that targeted Iranian nuclear enrichment plants. The malware destroyed centrifuges in 2009 by causing them to spin at dangerous speeds while feeding false “normal” data to operators.

Another example is the Industroyer attack by Russia against Ukraine’s energy sector in 2016. Industroyer malware targeted Ukraine’s power grid, using the grid’s own industrial communication protocols to directly open circuit breakers and cut power to Kyiv.

More recently, the Volt Typhoon attack by China against the United States’ critical infrastructure, exposed in 2023, was a campaign focused on pre-positioning. Unlike traditional sabotage, these hackers infiltrated networks to remain dormant and undetected, gaining the ability to disrupt the United States’ communications and power systems during a future crisis.

To defend against these types of attacks, the U.S. military’s Cyber Command has adopted a “defend forward” strategy, actively hunting for threats in foreign networks before they reach U.S. soil.

Domestically, the Cybersecurity and Infrastructure Security Agency promotes “secure by design” principles, urging manufacturers to eliminate default passwords and utilities to implement “zero trust” architectures that assume networks are already compromised.

Supply Chain Vulnerability

Nowadays, there is a vulnerability lurking within the supply chain of the controllers themselves. A dissection of firmware from major international vendors reveals a significant reliance on third-party software components to support modern features such as encryption and cloud connectivity.

This modernization comes at a cost. Many of these critical devices run on outdated software libraries, some of which are years past their end-of-life support, meaning they’re no longer supported by the manufacturer. This creates a shared fragility across the industry. A vulnerability in a single, ubiquitous library like OpenSSL – an open-source software toolkit used worldwide by nearly every web server and connected device to encrypt communications – can expose controllers from multiple manufacturers to the same method of attack.

Modern controllers have become web-enabled devices that often host their own administrative websites. These embedded web servers present an often overlooked point of entry for adversaries.

Attackers can infect the web application of a controller, allowing the malware to execute within the web browser of any engineer or operator who logs in to manage the plant. This execution enables malicious code to piggyback on legitimate user sessions, bypassing firewalls and issuing commands to the physical machinery without requiring the device’s password to be cracked.

The scale of this vulnerability is vast, and the potential for damage extends far beyond the power grid, including transportation, manufacturing and water treatment systems.

Using automated scanning tools, my colleagues and I have discovered that the number of industrial controllers exposed to the public internet is significantly higher than industry estimates suggest. Thousands of critical devices, from hospital equipment to substation relays, are visible to anyone with the right search criteria. This exposure provides a rich hunting ground for adversaries to conduct reconnaissance and identify vulnerable targets that serve as entry points into deeper, more protected networks.

The success of recent U.S. cyber operations forces a difficult conversation about the vulnerability of the United States. The uncomfortable truth is that the American power grid relies on the same technologies, protocols and supply chains as the systems compromised abroad.

Regulatory Misalignment

The domestic risk, however, is compounded by regulatory frameworks that struggle to address the realities of the grid. A comprehensive investigation into the U.S. electric power sector my colleagues and I conducted revealed significant misalignment between compliance with regulations and actual security. Our study found that while regulations establish a baseline, they often foster a checklist mentality. Utilities are burdened with excessive documentation requirements that divert resources away from effective security measures.

This regulatory lag is particularly concerning given the rapid evolution of the technologies that connect customers to the power grid. The widespread adoption of distributed energy resources, such as residential solar inverters, has created a large, decentralized vulnerability that current regulations barely touch.

Analysis supported by the Department of Energy has shown that these devices are often insecure. By compromising a relatively small percentage of these inverters, my colleagues and I found that an attacker could manipulate their power output to cause severe instabilities across the distribution network. Unlike centralized power plants protected by guards and security systems, these devices sit in private homes and businesses.

Accounting for the Physical

Defending American infrastructure requires moving beyond the compliance checklists that currently dominate the industry. Defense strategies now require a level of sophistication that matches the attacks. This implies a fundamental shift toward security measures that take into account how attackers could manipulate physical machinery.

The integration of internet-connected computers into power grids, factories and transportation networks is creating a world where the line between code and physical destruction is irrevocably blurred.

Ensuring the resilience of critical infrastructure requires accepting this new reality and building defenses that verify every component, rather than unquestioningly trusting the software and hardware – or the green lights on a control panel.

This article is republished from The Conversation under a Creative Commons license. Read the original article.

Read more »

Verkhovodova enrolled in courses on space policy and space sustainability taught by Thomas González Roberts, an assistant professor in the Sam Nunn School of International Affairs and the Daniel Guggenheim School of Aerospace Engineering (AE). Although Roberts is new to Georgia Tech, he is deeply connected within the international space community and regularly brings outside experts into his classroom. Guest speakers introduce students to the breadth of careers in the field, from technical analysis to national and multinational policymaking.

One lecture in the policy class, delivered by a representative from the Matthew Isakowitz Commercial Space Scholarship program, opened a door for Verkhovodova. She later won the scholarship while in Roberts’ sustainability course and spent a summer in Washington, D.C., on the government affairs team for Voyager Technologies Inc., the space technology company.

“These courses gave me a new perspective on how we use and consider the space environment,” Verkhovodova said. “They revealed the interdisciplinary nature of the field of space sustainability to me. Now, I see myself working at that intersection of policy and engineering.”

Georgia Tech’s space sustainability course is the first of its kind in the United States, and each year, it focuses on a different theme. In 2025, it was space congestion in low Earth orbit; this year, it’s lunar surface coordination among nation-states.

Building a New Kind of Class

Roberts designed the course around three components: foundations of space sustainability, an introduction to the principal sustainability challenges in the space domain and how space actors try to solve them; a signature guest lecture series he calls “Space Sustainability According To…” to show students how these solutions work in practice; and a project workshop, where students break into small groups to answer research questions under the mentorship of Roberts and an external partner organization.

The guest lecture series brings in professionals from a wide range of organizations — economists, astronomers, diplomats, and industry leaders — to discuss what sustainability means within their part of the space ecosystem. Past speakers have represented institutions including NASA, the United Nations, and Northrop Grumman.

“They all have different perspectives on what it means to be a sustainable steward of the space domain,” Roberts said. “A company needs to be profitable, while NASA’s mission focuses on expanding human knowledge. I want students to see the full spectrum of career paths that will let them work on space sustainability for the rest of their careers, if they choose to.”

These conversations expose students to the tools, ideas, and people shaping the emerging discipline — connections that often extend well beyond the classroom.

Modeling the Future of Space

Some guest speakers are part of the course’s external partnerships with leading space sustainability organizations, like last year’s collaboration with The Aerospace Corporation and this year’s with the Open Lunar Foundation. 

In 2025, The Aerospace Corporation showed students how to use important research tools and also mentored student research teams as they developed their final projects. One of these tools was the MIT Orbital Capacity Assessment Tool (MOCAT), an influential model used to study the effects of space debris on the long-term usability of the most popular portion of the space domain. Space debris and the resulting congestion for satellites and spacecraft navigating around this debris are some of the most pressing challenges in space sustainability.

“One of the most unique experiences was that our professor used his connections to bring the original architects of MOCAT into the class,” said aerospace engineering Ph.D. student Neel Puri.

Among those architects was Miles Lifson. A graduate school colleague of Roberts’ at MIT, Lifson is now a project leader in flight mechanics at The Aerospace Corporation. While Aerospace Corporation already collaborates with Georgia Tech through internships and lab partnerships, Lifson saw the class as a rare chance to work directly with students.

“When I heard about this class, I was really excited,” he said. “Space situational awareness, space debris, spacecraft coordination — these issues are becoming increasingly important as we put more spacecraft into orbit. It’s immensely rewarding to work with students because they’re passionate about solving problems and full of ideas. These are skills the space industry really needs.”

From Classroom to Conference Stage

Lifson also supported students in their final projects, helping them use the MOCAT model to analyze real-world problems and craft policy recommendations. One project, led by Puri, grew into a published conference paper, “Space Sustainability Implications of Combining Space Environment Pathways With Shared Socioeconomic Pathways," which he presented at the American Institute of Aeronautics and Astronautics SciTech Conference in January.

Their research builds on recent findings that climate change is thinning the upper atmosphere, reducing drag and causing debris to remain in orbit longer. Their work shows that, depending on future climate scenarios, predicted debris in low Earth orbit could vary by 15% to 100%, underscoring the significance of climate factors in long-term analysis and planning for space traffic management.

Even though sustainability is already part of Puri’s research focus, he credits Roberts and the course with opening another door in the field and providing valuable context to his doctoral dissertation.

A New Model for Tech-Driven Policymaking

Roberts sees the course as part of a larger mission.

“Georgia Tech can be a factory for producing tech‑driven policymakers,” he said. “When I was choosing where to go in my career as a faculty member, I wanted to be part of that factory. I get to help shape it, both in my lab and new course offerings like this one.”

With its blend of policy, engineering, real-world tools, and direct access to leading practitioners, Georgia Tech’s space sustainability course is not just pioneering a new curriculum. It’s preparing the next generation of space leaders to navigate and protect an increasingly crowded frontier.

More than 300 leaders from industry, government, and academia gathered on Georgia Tech’s campus for Energy Day, a one-day conference focused on one of today’s most urgent challenges: meeting the rapidly growing energy demands of artificial intelligence (AI).  

Tens of millions of brackets have been filled out ahead of the NCAA men’s and women’s basketball tournaments. Some fans will choose winners based on the higher seed, others will try to predict shocking upsets, and some may choose who advances based on which mascot would win a fight, but a Georgia Tech professor has his bracket down to a (data) science.   

Published today in the journal Nature Communications, the paper “Trivalent Titanium in High-Titanium Lunar Ilmenite” confirms titanium in a reduced, trivalent state in a black, metal-rich lunar mineral called ilmenite. It’s a state only possible in low-oxygen environments, conditions researchers refer to as “reducing.”

“Models have suggested that these reducing conditions may have varied at different locations and times across the surface of the Moon,” says lead author Advik Vira, a graduate student in the School of Physics who recently earned his doctoral degree. “We hope our microscopy technique can be a valuable step in mapping and understanding the Moon’s 4.5-billion-year history.”

The team anticipates that their technique could be used on many of the lunar samples collected more than 50 years ago by the Apollo missions in addition to the Apollo Next Generation Samples — a group of lunar samples that have been stored under pristine conditions — and new samples from the planned Artemis missions, with Artemis II slated for launch this spring. The technique might also be applicable to samples collected from the far side of the Moon and returned in 2024 by the Chang’e-6 mission.

“The Moon holds clues not only to its own past, but also to the earliest eras of Earth’s evolution — history that has long since been erased from our planet,” Vira says. “This study is a step toward understanding the history of both and a reminder that there is still so much left to learn from the lunar rocks we’ve brought back to Earth.”

The School of Physics research team included corresponding authors Vira and Professor Phillip First; in addition to graduate student Roshan Trivedi; undergraduate students Gabriella Dotson, Keyes Eames, Dean Kim, and Emma Livernois; and Professor Zhigang Jiang, along with Institute for Matter and Systems Materials Characterization Facility Senior Research Scientist Mengkun Tian; School of Chemistry and Biochemistry Senior Research Scientist Brant Jones and Thom Orlando, Regents' Professor in the School of Chemistry and Biochemistry with a joint appointment in the School of Physics. 

The Georgia Tech team was joined by Addis Energy Senior Geochemist Katherine Burgess; Macalester College Assistant Professor of Geology Emily First; along with Lawrence Berkeley National Laboratory Research Scientist Harrison Lisabeth, Senior Scientist Nobumichi Tamura, and Postdoctoral Fellow Tyler Farr, who recently earned a Ph.D. from Georgia Tech’s George W. Woodruff School of Mechanical Engineering.

CLEVER research

The investigation began with a dark gray rock called a lunar basalt. Formed when ancient magma erupted on the Moon’s surface, minerals crystallized as it cooled — preserving key information in their structures. Billions of years later, the rock was brought to Earth by the 1972 Apollo 17 mission, where a small piece is now stored at Georgia Tech’s Center for Lunar Environment and Volatile Exploration Research (CLEVER), a NASA Solar System Exploration Research Virtual Institute (SSERVI) center led by Orlando.

As a NASA virtual institute, CLEVER supports researchers exploring lunar conditions and developing tools for the upcoming crewed Artemis missions, and provided the lunar samples for this research. The SSERVI also plays a critical role in training the next generation of planetary researchers: both Vira and Farr earned their Ph.D.s while on the CLEVER team.

“At CLEVER, we are very interested in understanding the impacts of space weathering,” Vira says. “We implemented modern sample preparation and advanced microscopy techniques to image samples at the atomic level, and were curious to apply it more broadly to the collection of Apollo rocks in the Orlando Lab. This sample caught our attention.”

“When we imaged an ilmenite crystal from the lunar basalt, what struck us first was how uniform and perfect the crystal structure was,” he recalls. “We found no defects from space weathering and instead saw an undamaged, pristine crystal — undisturbed for 3.8 billion years.”

To investigate further, the team analyzed small chips of the rock with Burgess, a member of the RISE2 SSERVI team and then a geologist at the U.S. Naval Research Laboratory. Using state-of-the-art electron microscopy and spectroscopy techniques, Vira determined the oxidation state of the elements in the ilmenite present. 

In spectroscopy measurements, each element leaves a distinct ‘signature,’ Vira explains. “When we brought our results back to Georgia Tech’s Materials Characterization Facility, Mengkun (Tian) noticed something unusual: the signature showed titanium might be present in the trivalent state.”

The presence of trivalent titanium had long been suspected in this lunar mineral. The team was intrigued. 

A new window into old rocks

With funding from Georgia Tech’s Center for Space Technology and Research (CSTAR), Vira returned to the U.S. Naval Research Laboratory to analyze additional samples. The results confirmed that more titanium was present than the mineral’s formula (FeTiO₃) predicts — indicating a portion of the titanium present was trivalent.

“That led me to place our measurements in terms of the broader geological context,” Vira shares. Working with First, Vira explored how ilmenite with trivalent titanium could help reconstruct the nature of ancient magmas from the Moon, especially the chemical availability of oxygen.

“Because its location on the Moon was noted during the Apollo mission, we know exactly where this rock is from, and we can determine how old the rock is,” he explains. “When coupled with our trivalent titanium measurements, we can use that information to estimate the reducing conditions for this specific region at the specific time our rock formed.”

If the upcoming Artemis missions return samples suitable for the team’s technique, these rocks could provide a new window into ancient lunar geology. The research also highlights that many lunar samples already on Earth could be reexamined to look for trivalent titanium.

“There is still so much to learn from the lunar samples we have already brought to Earth,” Vira says. “It’s a testament to the long-term value of each sample return mission. As technology continues to advance, this type of work will continue to give us critical insights into our planet and our place in the universe for years to come.”

DOI: 10.1038/s41467-026-69770-w

Funding: This work was directly supported by the NASA SSERVI under CLEVER. Researchers were also supported by the NASA RISE2 SSERVI and the Heising-Simons Foundation. Funding for collaborations between the U.S. Naval Research Laboratory and Georgia Tech for the investigation of lunar minerals was provided by the Georgia Tech Center for Space Technology and Research. Sample preparation was performed at the Georgia Tech Institute for Matter and Systems, which is supported by the National Science Foundation. This work utilized the resources of the Advanced Light Source, a user facility supported by the U.S. Department of Energy, Office of Science, Office of Basic Energy Sciences, and was supported in part by previous breakthroughs obtained through the Laboratory Direct.

The Georgia Scientific Computing Symposium (GSCS) held its annual meeting on February 21 in Athens. Since 2009, the event has hosted researchers from across the Peach State to showcase homegrown advances in scientific computing.

The symposium highlighted Georgia’s reputation as a computing innovation hub. People from around the world come to Georgia universities to lead computing research. By advancing science, engineering, medicine, and technology, their work improves communities at home and abroad.

Faculty and students from Georgia Tech, UGA, Georgia State University, and Emory University presented at the symposium. Georgia Tech participants came from the colleges of Computing, Engineering, and Sciences.

This year’s organizers agreed to meet in Atlanta for the 2027 symposium. Georgia Tech’s School of Computational Science and Engineering (CSE) will host the 19th GSCS.

“From healthcare to computer chip design, scientific computing underpins many of the technological advances we see in our lives,” said Professor Edmond Chow, associate chair of the School of CSE.

“Scientific computing provides the mathematical models, simulations, and data‑driven tools that make modern innovation possible. It allows people to analyze complex systems, test ideas virtually before building them, and make faster, more accurate decisions across nearly every sector of society.”

Professor Haomin Zhou and Assistant Professor Helen Xu delivered two of the symposium’s five plenary talks. 

Zhou presented a new method for solving the Schrödinger equation, a landmark equation in quantum mechanics. Drawing inspiration from the mathematics used in generative artificial intelligence models, his approach develops an algorithm that more effectively simulates waves, particle motion, and other physical systems.

Xu focused on improving how computers move and organize data during complex calculations. Her work uses “cache-friendly” layouts that help computers access data more efficiently, boosting performance for scientific and engineering applications.

“Speaking at GSCS was a great opportunity,” Xu said. “The symposium fostered connections within the scientific computing community and gave us a chance to share exciting research.”

The symposium showcased student work through a poster blitz and a poster session. During the blitz, 36 students each had one minute to introduce their research to the full audience. They then shared more details about their research during the poster session.

The student projects showed the range of fields supported by scientific computing. The session also provided attendees with an opportunity to connect and expand their professional networks, helping grow the field’s future impact.

“As an aerospace engineer by training and aspiring computational scientist, GSCS gave me the platform to network with other researchers in the field while showcasing my own research,” said M.S. student Kashvi Mundra. 

“I was able to connect with scientists across different disciplines whose work intersects with my own in unexpected ways. Those conversations pushed my thinking beyond my own lab's perspective, helping me see my work on physics-informed machine learning for inverse problems in a broader scientific computing context.”

Georgia Tech students who presented posters included:

Abir Haque (CSE), Massively Parallel Random Phase Approximation Correlation Energy via Lanczos Quadrature

Antonio Varagnolo (CSE), Physics-Enhanced Deep Surrogates for the Phonon Boltzmann Transport Equation

Ben Burns (CSE), Infinite-Dimensional Stein Variational Inference with Derivative-Informed Neural Operators

Ben Wilfong (CSE), Shocks without Shock Capturing; Compressible Flow at 1 quadrillion Degrees of Freedom without Loss of Accuracy

Daniel Vickers (CSE), Highly-Parallel Fluid-Solid Interactions for Compressible Flows

Eric Fowler (CSE), High-Performance Tensor Contractions in Computational Chemistry

Haoran Yan (Math), Understanding Denoising Autoencoders through the Manifold Hypothesis: A Geometric Perspective

Kashvi Mundra (CSE), Autoregressive Multifidelity Neural Surrogate Modeling under Scarce Data Regimes

Sebastián Gutiérrez Hernández (Math/CSE), PDPO: Parametric Density Path Optimization

Vivian Zhang (AE), Multifidelity Operator Inference: Non-Intrusive Reduced Order Modeling from Scarce Data

Xian Mae Hadia (CSE), Data Efficiency of Surrogate Models: Learning Physics Data from Full Field Data vs. Inductive Bias from Approximate PDE Solvers

Xiangming Huang (CSE), Neural Operator Accelerated Evolutionary Strategies for PDE-Constraint Optimization

Zhaiming Shen (Math), Understanding In-Context Learning on Structured Manifolds: Bridging Attention to Kernel Methods

Zhongjie Shi (Math), Towards Understanding Generalization in DP-GD: A Case Study in Training Two-Layer CNNs

New cybersecurity research from the Georgia Institute of Technology, however, revealed that crews aboard commercial vessels were often not adequately prepared to manage cyberattacks effectively due to systemic training gaps.

The findings are based on interviews conducted by researchers with more than 20 officer-level mariners to assess the maritime industry’s readiness to handle cybersecurity attacks at sea.

"Historically, cybersecurity research has focused heavily on cyber-physical systems like cars, factories, and industrial plants, but ships have largely been overlooked,” said Anna Raymaker, Ph.D. student and lead researcher.

“That gap is concerning when more than 90% of the world’s goods travel by sea. Recent incidents, from GPS spoofing to ships linked to subsea cable disruptions, show that maritime systems are increasingly part of the global cyber threat landscape.”

The researchers proposed four practical strategies to strengthen maritime cyber defenses and close the training gaps. Their findings were presented recently at the ACM SIGSAC Conference on Computer and Communications Security (CCS).

1. Make Cybersecurity Training Actually Maritime

Many of those interviewed for the study described current cybersecurity training as “boilerplate” — generic modules that don’t reflect real shipboard risks. 

Researchers recommend:

• Role-specific instruction: Navigation officers should learn to detect and identify GPS spoofing. Engineers should focus on vulnerabilities in remotely monitored systems.
• Bridging IT and Operational Technology: Crews need to understand how attacks on IT systems can trigger physical consequences in operational technology — including collisions, groundings, or explosions.
• Hands-on delivery: Replace passive PowerPoints with drills and in-person exercises that build muscle memory.
• Accessible standards: Training must account for the wide range of educational backgrounds across crews and be standardized across ranks.

2. Move Beyond “Call IT”

At sea, crews can’t simply escalate a cyber incident to a shore-based IT department and wait. Operational resilience requires onboard readiness.

Researchers recommend:

• Vessel-specific response plans: Ships need clear, actionable protocols for threats such as AIS jamming or radar manipulation.
• Military-style drills: Adopting MCON (Emission Control) exercises — used by the U.S. Military Sealift Command — can train crews to operate safely without electronic systems.
• Stronger connectivity controls: High-bandwidth satellite systems like Starlink introduce new risks. Clear policies and network segregation are essential to prevent new entry points for attackers.

Related Article: When GPS lies at sea: How electronic warfare is threatening ships and their crews by Anna Raymaker

3. Create Unified, Ship-Specific Regulations

Maritime cybersecurity regulations are often reactive and fragmented. Researchers argue the industry needs a cohesive, domain-specific framework.

Key recommendations include:

• A unified global model: Like the energy sector’s NERC CIP standards, a maritime framework could mandate baseline controls such as encryption, network segmentation, and anonymous incident reporting.
• Rules built for real crews: Regulations designed for large naval operations don’t translate well to smaller merchant or research vessels. Standards must reflect actual shipboard conditions.
• Future-proofing requirements: Autonomous ships and remotely operated vessels expand the cyber-physical attack surface. Regulations must proactively address these emerging technologies.

4. Invest in Maritime-Specific Cyber Research

Finally, the researchers stress that long-term resilience requires deeper technical research focused on maritime systems.

Priority areas include:

• Real-time intrusion detection systems tailored to shipboard protocols.
• Proactive security risk assessments of interconnected onboard systems.
• Cyber-physical modeling to better understand cascading failures in complex maritime environments.

The Bottom Line

Cyber threats at sea are no longer hypothetical. Mariners report real-world incidents ranging from GPS spoofing to ransomware that disrupts global trade.

“Through our interviews with mariners, I saw firsthand how much dedication and pride they take in their work,” said Raymaker. “Our goal is for this research to serve as a call to action for researchers, policymakers, and industry to invest more attention in maritime cybersecurity and support the people who risk their lives every day to keep global trade, food, and energy moving."

A Sea of Cyber Threats: Maritime Cybersecurity from the Perspective of Mariners was presented at CCS 2025. It was written by Raymaker and her colleagues, Ph.D. students Akshaya Kumar, Miuyin Yong Wong, and Ryan Pickren; Research Scientist Animesh Chhotaray, Associate Professor Frank Li, Associate Professor Saman Zonouz, and Georgia Tech Provost and Executive Vice President for Academic Affairs Raheem Beyah.

Read more »

Amino acids also play a critical role commercially where they are manufactured and added to pharmaceuticals, dietary supplements, cosmetics, animal feeds, and industrial chemicals — an energy-intensive process leading to greenhouse gas emissions, resource consumption, and pollution.

A landmark new system developed at Georgia Tech could lead to an alternative: a commercially scalable, environmentally sustainable method for amino acid production that is carbon negative, using more carbon than it emits.

The breakthrough builds on a method that the team pioneered in 2024 and solves a key issue – increasing efficiency to an unprecedented 97% and reducing the bioprocess cost by over 40%. It’s the highest reported conversion of CO2 equivalents into amino acids using any synthetic biology system to date.

Published in the journal ACS Synthetic Biology, the study, “Cell-Free-Based Thermophilic Biocatalyst for the Synthesis of Amino Acids From One-Carbon Feedstocks,” was led by Bioengineering Ph.D. student Ray Westenberg and Professor Pamela Peralta-Yahya, who holds joint appointments in the School of Chemistry and Biochemistry and School of Chemical and Biomolecular Engineering. The team also included Shaafique Chowdhury (Ph.D. ChBE 25) and Kimberly Wennerholm (ChBE 23); alongside University of Washington collaborators Ryan Cardiff, then a Ph.D. student and now a Chain Reaction Innovations Fellow at Argonne National Laboratory, and Charles W. H. Matthaei Endowed Professor in Chemical Engineering James M. Carothers; in addition to Pacific Northwest National Laboratory Synthetic Biology Team Leader Alexander S. Beliaev.

"This work shifts the narrative from simply reducing carbon emissions to actually consuming them to create value,” says Peralta-Yahya. “We are taking low-cost carbon sources and building essential ingredients in a truly carbon-negative process that is efficient, effective, and scalable.”

Heat-Loving Organisms

The work builds on the cell-free technology the team used in their earlier study. “Previously, we discovered that a system that uses the machinery of cells, without using actual living cells, could be used to create amino acids from carbon dioxide,” Peralta-Yahya explains. “But to create a commercially viable system, we needed to increase the system’s efficiency and reduce the cost.”

The team discovered that bits of leftover cells were consuming starting materials, and — like a machine with unnecessary gears or parts — this limited the system’s efficiency. To optimize their “machine,” the team would need to remove the extra background machinery.

"Leftover cell parts were using key resources without helping produce the amino acids we were looking for,” says Peralta-Yahya. “We knew that heating the system could be one way to purify it because heat can denature these components.”

The challenge was in how to protect the essential system components from the high temperatures, she adds. “We wondered if introducing enzymes produced by a heat-loving bacterium, Moorella thermoacetica, might protect our system, while still allowing us to denature and remove that inefficient background machinery.”

The results were astounding: after introducing the enzymes, heating and “cleaning” the system, and letting it cool to room temperature, synthesis of the amino acids serine and glycine leaped to 97% yield — nearly three times that of the team’s previous system.

Scaling for Sustainability

To make the system viable for large-scale use, the team also needed to reduce costs. “One of the most costly components in this system is the cofactor tetrahydrofolate (THF),” Peralta-Yahya shares. “Reducing the amount of THF needed to start the process was one way to make the system more inexpensive and ultimately more commercially viable.”

By linking reaction steps so waste from one step fueled the next, the team devised a method to recycle THF within the system that reduces the amount of THF needed by five-fold — lowering bioprocessing costs by 42%.

“This decrease in cost and increase in yield is a critical step forward in creating a method with real potential for use in industry and manufacturing,” Peralta-Yahya says. “This system could pave the way for moving this carbon-negative technology out of the lab and onto the continuous, industrial scale."

Funding: The Advanced Research Project Agency-Energy (ARPA-E); U.S. Department of Energy; and the U.S. Department of Energy, Office of Science, Biological and Environmental Research Program.

DOI: https://doi.org/10.1021/acssynbio.5c00352

Applying the Scheimpflug technique, the researchers are developing inexpensive rangefinder camera technology, advanced sensors and computational techniques to both complement and provide an alternative to established light detection and ranging (LiDAR) technology in certain applications. The technique works best in short- and medium-distance metrology, and can be used passively or in collaboration with laser-based techniques.
 

“The Scheimpflug technique is a complete alternative to time-of-flight (ToF) LiDAR, and we’re looking for everything we can do with it,” said Nathan Meraz, a GTRI senior research scientist who has been refining the new applications for several years. “It measures things differently, and since it’s a camera sensor, there’s a lot more information to process compared to a LiDAR signal. And there are also data fusion aspects.”
 

A paper on the technique and its potential remote sensing applications was presented during 2025 at the SPIE Defense + Commercial Systems (DCS) Conference. The research was supported by GTRI’s Independent Research and Development (IRAD) program and also has been advanced by teams of student researchers from the GTRI Research Internship Program (GRIP).

See the complete article on the GTRI news site
 

Thinking about polymers in that way has led Georgia Tech materials scientists to create new generative artificial intelligence tools that are like Claude or ChatGPT for new materials. 

These are the first foundational models for generative polymer design that have also been validated through physical experiments: users specify the properties they need in a polymer and the model will suggest a chemical structure.

Led by Regents’ Entrepreneur Rampi Ramprasad, the researchers described their latest model this month in the Nature journal npj Artificial Intelligence — including a test material they created and validated in the lab to prove the models work.

Read the full story on the College of Engineering website.

The Advanced Technology Development Center (ATDC) in Georgia Tech’s Office of Commercialization announced two of its health technology (HealthTech) portfolio companies, Nephrodite and OrthoPreserve, earned the designation. 

Achieving this rare milestone underscores the caliber of founders, science, and support in ATDC’s 30-company HealthTech portfolio, the incubator’s largest focus area. It’s also a win for Georgia because it reflects the strength of the state’s health innovation ecosystem. 

“This designation is one of the strongest signals the FDA gives that a technology could change the standard of care,” said Greg Jungles, HealthTech catalyst at ATDC. “For ATDC to have two in the same year is remarkable.” 

The Breakthrough Device Program doesn’t waive evidence requirements, but it accelerates learning with the FDA, ATDC’s Jungles said. “That means shorter response times, more frequent meetings, and prioritized review. Teams avoid dead ends and align earlier on study designs and endpoints.” 

For the founders of both startups, their technologies come one step closer to moving their innovations to market. Nephrodite’s technology improves the lives of dialysis patients. OrthoPreserve’s device addresses challenges faced by those who suffer from chronic knee pain. 

Nephrodite: Advancing Continuous Artificial Kidney Technology 

Dr. Nikhil Shah and Dr. Hiep Nguyen, cofounders of Nephrodite, aim to improve care for dialysis patients with end-stage kidney disease who need transplants. These patients often spend three to four hours in a dialysis clinic up to three times a week. Being tethered to stationary machines with needles drawing blood via arm grafts complicates everyday activities — from work tasks to the ability to travel. 

Dialysis addresses chronic kidney disease, which means kidneys no longer work properly. The treatments filter out toxins, waste, and other fluids in the blood. Kidney disease costs Medicare $124.5 billion every year, according to the Centers for Disease Control and Prevention. And those costs are expected to rise because of increasing rates of kidney failure and chronic kidney disease. 

“Dialysis, while lifesaving when it was pioneered in 1952, is incredibly burdensome,” Shah said. Besides being a long process that keeps the patient in a fixed location, it’s physically tiring. “Taking out your blood continually many, many times over, and over the course of four hours is the equivalent of running the Boston Marathon, hitting the finish line, and then someone saying, ‘You're not done; go do it again,’ ” he said. 

A surgeon by training, with expertise in transplantation and oncology, Shah is also an adjunct associate professor in Tech’s School of Interactive Computing. He worked with Nguyen to develop a continuously functioning mechanical artificial kidney, leading to Nephrodite’s formation. 

The FDA’s breakthrough designation on its artificial kidney allows the company to pursue approvals to begin tests in human trials. 

The company traces its beginnings to a German aerospace facility outside Munich, where Nguyen and Shah watched engineers demonstrate a pediatric artificial heart — the Berlin Heart. 

“That’s how we got started,” Shah said. “Seeing an artificial heart that led us to think about doing this for kidneys — because the kidney space has been largely ignored for 70 years.” 

Backed by a German federal grant, Nephrodite grew, moving from Germany to Boston, Massachusetts, then to Austin, Texas, before calling Atlanta home. The company joined ATDC and tapped into other Georgia Tech programs. This included the Center for MedTech Excellence and the Georgia Manufacturing Extension Partnership. Nephrodite also drew on student talent as the researchers quietly worked on their continuous mechanical artificial kidney. 

Nephrodite began interviewing patients to find out what they wanted the artificial kidney needed to solve. 

They learned patients want the ability to be mobile. Patients also desire an alternative therapy to large needles being inserted into arm grafts because the injection sites are prone to infection and the grafts can fail. In addition, the process can be painful and disfiguring. Finally, patients want a quality of life independent of machines. 

“Those quality-of-life needs, especially being free and mobile, were absolutely universal,” Shah said.  

Nephrodite began developing the technology to build its device — a filter surgically implanted in the pelvis area. 

“We developed an implant designed to run constantly, connected to larger blood vessels in the pelvis to avoid arm graft failures, and paired with an external interface that lets patients sleep at night while the system removes toxins and excess fluid,” Shah explained. 

The device also has built-in sensors, with data uploaded to the cloud, enabling medical care teams to remotely monitor their patients while freeing patients from frequent in-clinic visits. 

Shah said Nephrodite’s device could restore everyday independence, while potentially lowering infection risk. 

“It's like having an actual kidney, but without all the issues of an unhealthy one,” Shah said.  

OrthoPreserve: Innovating a Minimally Invasive Meniscus Implant 
 
OrthoPreserve’s technology aims to address issues from people have with their meniscus, the C‑shaped piece of cartilage in a knee joint that acts as a shock absorber between the thigh bone and shin bone. 

Though patients undergo a now-routine surgery to address it, incomplete recoveries are also common. An estimated quarter of patients later experience recurring knee pain. No FDA-approved implant currently exists for this population. Now, OrthoPreserveis developing a minimally invasive, artificial meniscus implant to restore cushioning, relieve pain, and delay — or even prevent — knee replacement for some patients. 

“There are a million meniscus surgeries every year, and 25% of those patients still live with recurring pain,” said Jonathan Schwartz, OrthoPreserve’s founder and CEO. 

Patients can face daily pain from ordinary activities, such as prolonged standing or walking a dog. Other activities like jogging and recreational sports can trigger flares that can lead to swelling and prolonged discomfort, Schwartz said. “Those patients have no reliable options today,” he said. “We’re building a minimally invasive implant to restore cushioning and help people get back to the activities they love.” 

OrhoPreserve’s durable implant restores cushioning, and it could help people return to normal activities and delay invasive knee replacement. Along with this comes potential cost and recovery benefits for the healthcare system.   

Schwartz created the implant as his Georgia Tech master’s thesis in the lab of David Ku in the Lawrence P. Huang Endowed Chair for Engineering Entrepreneurship and Regents' Professor in the George W. Woodruff School of Mechanical Engineering. After industry experience, Schwartz returned to further develop the technology, building on Georgia Tech’s translational expertise 

OrthoPreserve has completed mechanical testing and a successful study. The company is raising a $2 million seed to complete validations and begin human trials, which Schwartz expects to start in 18 months. 

“The FDA breakthrough designation validates that nothing like this technology exists, and that it has the potential to disrupt the standard of care,” Schwartz said, adding the U.S.’ market opportunity is roughly $1.5 billion. “We finally have a minimally invasive option to bridge the gap between meniscus surgery and knee replacement.” 

What FDA Breakthrough Designation Means for ATDC’s HealthTech Startups 

Having a faster and clearer path is a derisking milestone for investors who are evaluating capital intensive medical device technologies, Jungles said. 

“This breakthrough device designation is a really big deal for medical device companies,” Jungles said, adding that startups often fear navigating the FDA approval process. “But this designation adds to the legitimacy of their technologies and the problemsthey are solving. The designation will help them get to market faster, assuming their data continues to meet expectations.” 

ATDC launched its HealthTech vertical in 2018, which is now sponsored by Catalyst by Wellstar ATDC’s HealthTech portfoilo companies include medical devices, biotech, and digital health, among other segments. 

ATDC’s Role in Accelerating HealthTech Innovation 

Nephrodite and OrthoPreserve’s founders noted ATDC’s coaching and programming as critical in navigating fundraising and regulatory milestones. Another factor, they said, was ATDC’s connection to Georgia Tech’s labs and facilities and prototyping support and clinical advisors from across metro Atlanta.  

“We meet with ATDC coaches every two to four weeks to troubleshoot and plan,” Schwartz said. “Having that level of seasoned guidance, all without consultant-level costs, has been huge.” 

Jungles added that two Breakthrough device designations in the same year reflects ATDC’s selection rigor, noting he’s evaluated hundreds of technologies since the HealthTech vertical launched. 

“It reflects the caliber of the companies in ATDC, specifically in the medical device space,” Jungles said. “It’s the strength of their teams, the persistence of the founders, and the collaboration of the ecosystem in Georgia and Atlanta.” 

Reliable energy is required to keep safe in cold winters and hot summers, making it a matter of national security. There are also vying economic policies to consider, political and financial incentives to navigate, and questions of social and economic inequality.

Experts in Georgia Tech’s Ivan Allen College of Liberal Arts examine the challenges we face with the U.S. energy transition, and work to help make it safe, fair, and effective for all.

• Challenge No. 1: Managing National Security — with Adam N. Stulberg, professor and chair of the Sam Nunn School of International Affairs.
• Challenge No. 2: Confronting Inequality — with Bijesh Mishra, a postdoctoral scholar in the Jimmy and Rosalynn Carter School of Public Policy.
• Challenge No. 3: Choosing the Right Economic Policies — with Bobby Harris, an assistant professor in the School of Economics.
• Challenge No. 4: Navigating Financial and Political Incentives — with Kate Pride Brown, a sociologist in the School of History and Sociology.

Read the article on the Ivan Allen College website.

According to the study, published in Energy Policy, widespread adoption of electric vehicles, or EVs, by 2035 would cut energy bills for U.S. households by more than 6% — including more than 4% at the gas pump. It also would drive oil imports down by 7% and increase exports by nearly 4%, the researchers say.

However, those benefits are imperiled by the repeal of national electric vehicle incentives and the recent decision by the federal government to roll back EV-boosting rules meant to increase vehicle fuel efficiency and reduce pollution, according to the study’s authors, Ph.D. candidate Niraj K. Palsule; Marilyn A. Brown, Regents’ Professor and Brook Byers Professor of Sustainable Systems; and former graduate student Suprita Chakravarthy. Their study was conducted prior to the federal decisions.

“Proponents of eliminating fuel efficiency standards and other EV-boosting policies often frame those regulatory approaches as consumer-unfriendly, but our analysis shows that such policies have many long-term benefits, both for consumers and for the nation’s energy security,” Palsule said.

For more on the study, read the full story.

A new mobile app will soon put the ability to monitor a baby’s prenatal heartbeat in the hands of pregnant women who may worry about their baby’s health in between doctor’s visits. 

Set in the heart of Tech Square on the Georgia Tech campus, this year’s event explores how energy systems, materials, technologies, supply chains, and policy must evolve in response to AI’s accelerating impact. As digital infrastructure expands and computation intensifies, the need for reliable, resilient, and sustainable power has never been more urgent. 

“Energy Day reflects Georgia Tech’s strength in connecting world-class research in materials and components with the infrastructure and partnerships needed to translate discovery into scalable energy technologies that serve industry, society, and the future economy,” said Eric Vogel, executive director of the IMS and the Hightower Professor in Materials Science and Engineering. 

Energy Day 2026 also marks an important milestone with the introduction of its first group of corporate sponsors: GE Vernova, Southern Company, Georgia Power, ExxonMobil, Southwire Spark, Gems Setra, and Tektronix. Their support reflects a shared commitment to advancing energy solutions. 

“Tektronix is excited to be part of Energy Day because advancing the future of energy starts with precise measurement and trusted insights,” said Christopher Bohn, president of Tektronix. “From power electronics and high voltage systems to grid scale renewables and AI driven control technologies, the breakthroughs discussed here directly align with the innovations we support through our products and solutions. Collaborating with Georgia Tech allows us to engage early with emerging research and the next generation of engineers—critical collaborators in building a cleaner, smarter, and more resilient energy ecosystem.”

The keynote address will be delivered by Vanessa Z. Chan, a nationally recognized leader at the intersection of innovation, commercialization, and emerging technologies. Chan will provide insights on accelerating technological discovery, emphasizing how AI is transforming energy and materials design. She will discuss how commercialization strategies must rapidly evolve across multidisciplinary energy domains from grid modernization to advanced batteries and clean manufacturing.

Building on the themes introduced in the keynote, the program transitions into a fireside chat with Georgia Tech EVPR Tim Lieuwen featuring Amit Kulkarni and Jim Walsh. Kulkarni is vice president of Product Management and Strategy for the Gas Power business within GE Vernova, where he oversees the world’s largest portfolio of power generation equipment. Walsh, vice president of GE Vernova’s Consulting Services, leads teams providing innovative solutions across the full spectrum of power generation, delivery, and utilization.

Next comes a policy-focused panel that will explore the surge in power demand driven by AI, how the United States is addressing today’s most urgent energy challenges, and the long-term implications of today’s decisions for a sustainable energy future. Bringing together leading voices in U.S. environmental and energy policy, the panel features Joe Aldy of Harvard University and former special assistant to the president for Energy and Environment; Al McGartland of New York University’s Institute for Policy Integrity and former Environmental Protection Agency lead economist and director of the National Center for Environmental Economics; and Kevin Rennert, fellow and director of the Comprehensive Climate Strategies Program at Resources for the Future and former staff member on the U.S. Senate Committee on Energy and Natural Resources.

The second panel focuses on critical materials — the foundation of advanced energy systems and digital technologies. As AI, data centers, and advanced energy technologies drive demand for critical materials, securing them now requires integration and coordination across the entire value chain. Panelists include Rachel Galloway, British consul general in Atlanta; Vijay Murugesan, head of Materials Intelligence and Digital Innovation at Amazon; Colin Spellmeyer, executive strategic sourcing leader at GE Vernova;  Charles Sims, Tennessee Valley Authority Distinguished Professor of Energy and Environmental Policy at the University of Tennessee; and Nortey Yeboah, principal engineer at Southern Company. Together, they will offer perspectives on the policy and economic frameworks shaping the energy supply chain, from developing raw resources to manufacturing the technologies essential to future energy systems.

In the afternoon, participants can dive deeper into specialized topics through three focused technical tracks. 

• “Meeting the Demand for Power” will examine how emerging technologies, advanced nuclear systems, and renewable integration can work together to deliver reliable, resilient electricity.
• “Data Center Infrastructure and Resources” will explore innovations in thermal management technologies, energy-efficient computing, and the broader resource impacts of expanding digital infrastructure.
• “Grid Technologies and Markets” will highlight strategies for strengthening grid capacity, incorporating demand-side management, and optimizing carbon performance as energy systems evolve.

“Meeting the rapidly rising electricity demand driven by AI requires bold ideas, coordinated action, and research that moves at the speed of innovation,” said Yuanzhi Tang, executive director of the SEI. “Energy Day 2026 brings together the people and expertise needed to shape resilient, sustainable energy systems for the future. At Georgia Tech, we see this event as a catalyst for new partnerships, new solutions, and a shared commitment to strengthening the nation’s energy foundation.”

Energy Day 2026 is designed for researchers advancing emerging energy technologies, policymakers navigating shifting regulatory and geopolitical landscapes, industry professionals seeking insight into emerging tools and supply chains, and students preparing to enter one of the most consequential sectors of the decade. It also welcomes anyone interested in AI, sustainability, electrification, and critical materials. 

Join us to explore the future of energy. To learn more and register, visit: Energy Day 2026.

Georgia’s forest industry has long been a pillar of the state’s rural economy. But in recent years, mill closures and shifting markets have put pressure on landowners, workers, and entire communities, particularly in south Georgia. A recently approved $8.9 million Georgia Forestry Innovation Initiative will help chart a new path forward, creating more value from Georgia’s abundant forest resources and expanding opportunities for the people and regions depending on them. 

Read more »

But as carbon removal grows, so does a core problem: The carbon removal industry is largely unregulated, particularly for more novel technologies without long-standing norms around reporting and verification. In today’s “voluntary carbon market,” a private company can claim it removed a certain amount of carbon, list that amount for sale, and allow another company to buy it to offset its emissions — with little independent oversight or transparency.

A new Nature NPJ Climate Action article argues that this system isn’t enough to meet global climate goals, and could even end up causing harm. In the paper, Chris Reinhard, Georgia Power Chair and associate professor in Georgia Tech’s School of Earth and Atmospheric Sciences, and Noah Planavsky of the Yale Center for Natural Carbon Capture call for a fundamental shift: Carbon removal should be quantifiable, economically viable, and pursued in ways that create benefits for local communities — and greater transparency in carbon removal practice is necessary.

“We argue that it’s important to understand and quantify carbon removal practices that can benefit local communities, like better crop yields, and that this understanding is really only possible if these practices are pursued transparently,” Reinhard said. “The data used to quantify carbon removal and how much it costs need to be transparent — the surest route toward learning what works and building public trust in carbon removal as a solution.”

Transparency Trouble

Reinhard and Planavsky bring a unique technical and policy perspective to the issue. As geochemists, they study how Earth’s chemical composition and geological processes control the carbon cycle. Reinhard also co-founded a carbon removal startup he has since divested from. That insider experience and academic background helped them see the disconnect between what’s technologically possible and what market logic culturally or commercially incentivizes.

Today’s carbon removal startups often guard their methods and data as proprietary intellectual property. Without regulatory requirements or pressure from corporate carbon buyers, these startups have little reason to disclose carbon accounting practices, cost structures, or actual long-term impacts. The researchers argue that policy guidance and advocacy are needed to shift the industry toward meaningful openness.

“Our expertise is most firmly grounded in the technical dimensions of these carbon removal processes,” Reinhard said, “but we saw an opportunity here to push for better policy and start this dialogue about what transparency really means, in part to foster more public debate about what carbon removal ought to be doing for society.”

Community Beyond Carbon

The authors also stress that carbon removal should deliver benefits beyond atmospheric cleanup that communities can see and advocate for. For example, liming, or adding limestone to soil, can remove carbon while also improving crop yields and reducing erosion. Coastal ecosystem restoration can sequester carbon while strengthening shorelines and supporting fisheries. Georgia Tech’s own direct air capture work builds community engagement into the process to ensure that carbon removal is equitable. 

Reinhard and Planavsky say the next best step for the carbon removal industry is to identify which removal pathways offer the clearest benefits, what they cost, and where transparency gaps are most damaging. This foundation will help create policies that make carbon removal reliable, verifiable, and community-centered. 

Without oversight, they argue, carbon removal risks remaining a niche, market-defined practice — when the climate challenge demands a trusted, scalable, and democratically governed solution.

CITATION: Reinhard, C.T., Planavsky, N.J. The importance of radical transparency for responsible carbon dioxide removal. npj Clim. Action 5, 7 (2026). https://doi.org/10.1038/s44168-025-00324-4

“This first set of CreationsVC Fellows offers an exciting cross-section of innovative hardware and software technologies built on Georgia Tech’s legacy of space exploration, hardware development, and product commercialization,” said Jud Ready, SRI executive director. 

In the first year of the three-year program, CreationsVC provides $125,000 to promote and accelerate innovations that have both space and terrestrial applications. The series offers participants training focused on customer discovery, engaging and compelling storytelling, value proposition design and quantification, and lean/agile project/product management.

“CreationsVC is centered on a deep appreciation for innovation and big thinking,” said Steve Braverman, co-founder and managing partner of CreationsVC. “We felt this was the right time to align our efforts in sourcing and supporting dual-value technologies that will have an impact on both Earth and space.” 

The six startups tackle real-world space research problems like supply chain management, how artificial intelligence works in space, and navigation.

“We are excited CreationsVC is providing us with an opportunity to try new approaches to accelerate deep tech development,” said Jonathan Goldman, Quadrant-i’s director. “These are the toughest kinds of startups to build, and we look forward to the learning we will gain from forcing our innovators out of their comfort zones to embrace some new and valuable skills.”

Meet the cohort:
 

Company: CIMTech.ai
 

Founders: Shimeng Yu, James Read

School: School of Electrical and Computer Engineering (ECE)

Objective: To develop energy-efficient, radiation-tolerant artificial intelligence processors using a persistent type of ferroelectric memory. The startup aims to improve applications requiring high power efficiency, such as battery-powered devices and space-based systems.

Why Q-i: “The advantage of Q-i is in helping technical founders turn their research into products that solve customers’ problems,” noted James Read. “For us, that means talking with potential customers and hearing their pain points directly from the source. Now we’re use that information to build a convincing narrative around our startup’s value for stakeholders and investors.” 

Company: SkyCT
 

Founders: Morris Cohen, Matthew Strong

School: ECE

Objective: To provide up-to-date mapping of the electrical properties of the upper atmosphere, with applications to GPS-free navigation, long-range communication, and satellite and launch vehicle viability. The startup uses the radio energy released by lightning strikes to create this map. 

Why Q-i: “This weird region about 50 miles up from Earth’s surface is both really hard to track and measure, and also impacts a surprising array of applications,” said Cohen. “It’s sometimes called the `ignorosphere’ because of how difficult it is to measure, and it’s time we change that.” 

Company: Penumbra Autonomy
 

Founders: Panagiotis Tsiotras, Juan Diego Florez-Castillo, Iason Velentzas 

School: Daniel Guggenheim School of Aerospace Engineering (AE)

Objective: To commercialize algorithms that help spacecraft maneuver when they have limited information on their environment. The algorithms use state-of-the-art computer vision and localization techniques. This could benefit manufacturing, assembly, and refueling in orbit, as well as enable monitoring, situational awareness, and debris removal. 

Why Q-i: “The program offers a conduit to entrepreneurship opportunities and spinoff companies in the space domain by providing guidance and commercialization ‘know-how,’” said Panagiotis Tsiotras. 

Company: TerraMorph

 
Founders: Yashwanth Kumar Nakka, Sadhana Kumar, Vincent Griffo, Sachin Kelkar

School: AE

Objective: To create an autonomous rover platform with adaptive, reconfigurable mobility. The rover will implement software and sensing algorithms to automatically detect terrain type and improve traction and energy usage. This could be used on the moon or Mars, or even terrestrial search and rescue. 

Why Q-i: “TerraMorph was developed to address fundamental challenges in mobility and autonomy across uncertain terrain,  but successfully translating that work into impact requires creative guidance, critical feedback, and experienced perspectives beyond the lab,” said Yashwanth Kumar Nakka. “Q-i’s culture of leading by example and fostering strong, ethical teams aligns closely with how we want to build TerraMorph: iteratively, thoughtfully, and with a focus on real-world deployment.” 

Company: OpenWerks
 

Founders:  Shreyes Melkote, Mike Yan

School: George W. Woodruff School of Mechanical Engineering

Objective: To deliver real-time manufacturing supply chain visibility for the space and national security industries. OpenWerks technology aims to dramatically reduce current sourcing cycles from eight months down to weeks by connecting corporate buyers directly with verified supplier manufacturing capability and capacity data. 

Why Q-i: “From the very beginning, principals at VentureLab and  Q-i offered a clear pathway to translate academic research into a viable business,” said Mike Yan. “Their reputation for guiding Georgia Tech startups through both business and technology derisking, combined with their comprehensive ecosystem of programs and coaches, made them the natural partner for our entrepreneurial journey.”

Company: 8Seven8
 

Founders: Chandra Raman

School: School of Physics

Objective: To manufacture quantum hardware in Georgia. 8Seven8 aims to put high-precision atomic clocks and gyroscopes on a chip for applications ranging from aircraft navigation to industrial automation.  

Why Q-i: “They have mentored me and my students through the commercialization process, providing opportunities such as the Space Fellows Cohort,” Chandra Raman said. “One of my former students, Alexandra Crawford, gained valuable business experience through a Q-i entrepreneur’s assistantship, and is now working at 8Seven8 full-time. They have also guided me through the process of obtaining funding through the Georgia Research Alliance for our commercialization effort.”

While chess doesn’t have moral stakes, more serious ethical issues could arise in everything from medicine to self-driving cars as AI becomes even more pervasive. So, what does it mean for AI to be safe? 

“No one is saying developing safe AI will be easy, but we need to make sure we cover as many ethical concerns as possible,” said Tyler Cook, a research affiliate at the Jimmy and Rosalynn Carter School of Public Policy at Georgia Tech and assistant program director of the Center for AI Learning at Emory University. “Humans also care about being treated fairly. We care about not being deceived. We should aim for much more than safety.”

AI is too complex for simple guardrails, Cook argues in a recent Science and Engineering Ethics paper. But AI still needs to be limited and incorporated with human values of fairness, honesty, and transparency so it doesn’t make ethically dubious decisions.

AI is not just a problem to manage. It’s a technology whose impact depends on the values we choose to build in it, Cook claims. Developers must think carefully about the world their systems will shape. AI shouldn’t make our world, but instead integrate into it.

Safe vs. Autonomous AI

Some computer scientists would say “safe” AI, or AI that doesn’t cause harm, is the answer. But AI is not a simple machine like a lawnmower that needs just a blade guard to prevent harm. 

Establishing AI safety is more complex than adding protective features. Being prudent with how much autonomy AI gets is also paramount.

“We don't want AI systems deciding that they don't want to pursue fairness anymore,” Cook said. “We don't want AI to be autonomous with respect to its ethical goals or values.” 

Such ethical autonomy could lead to unpredictable or undesirable outcomes. Consider algorithmic bias: Human biases, combined with machine automation, can lead to unequal consequences. An AI mortgage lender could favor certain applicant demographics over others, for example. 

Cook posits there is a middle ground between merely safe AI and autonomous ethical AI — “end-constrained ethical AI.” 

“As designers of AI systems, computer scientists should choose what we want the AI to prioritize: fairness, honesty, transparency,” Cook said. “That's why I use the language of constraint. We're constraining the AI’s values so they can actually benefit society.”

End‑constrained ethical AI asks designers to set those boundaries intentionally, not as an afterthought. And if developers take that responsibility seriously, AI doesn’t have to reinvent our world — it can strengthen the one we already have.

"A Case for End-Constrained Ethical Artificial Intelligence." Science and Engineering Ethics 32.7 (2026).

DOI: 10.1007/s11948-025-00577-6

In the International Disaster Reconnaissance (IDR) course, students now use Filio, a platform built by School of Computing Instruction Senior Lecturer Max Mahdi Roozbahani, to capture immersive 360° media, photos, and video that transform real disaster sites in India and Nepal into living digital classrooms. 

Offered by the School of Civil and Environmental Engineering and taught by IDR director and Regents’ Professor David Frost, the course pairs traditional fieldwork with Roozbahani’s expertise in immersive technology and data-driven learning, transforming on-the-ground observations into reusable, interactive educational resources. 

How Computing Can Capture Data 

Disasters are not only physical events; they are also information events, Roozbahani says. Effective response and long-term resilience depend on the ability to observe, record, and communicate critical data under pressure. Georgia Tech’s IDR course pairs structured on-campus preparation with international field experiences, enabling students to study the cascading effects of major disasters, including how local building practices, governance, and culture shape damage and recovery. 

“When students step into a disaster zone, they learn quickly that resilience is a systems problem: physical, social, and informational. Our job in computing is to help them capture and reason about that system responsibly,” Roozbahani said. 

Learning from the 2025 Himalayas Expedition 

During spring break last year, the cohort traveled along the Teesta River corridor in Sikkim, India. The region is shaped by steep terrain, fast-moving water, and critical infrastructure in narrow valleys. 

The visit followed the October 2023 glacial lake outburst flood from South Lhonak Lake, which destroyed the Teesta III hydropower dam and impacted downstream towns, including Dikchu and Rangpo. Field stops across India included Lachung, Chungthang, Dikchu, Rangpo, Gangtok, and New Delhi. 

Students explored both upstream and downstream consequences. 

Upstream, the team examined how steep terrain and river confinement amplify flood forces, creating cascading risks for infrastructure. Using Filio’s interactive 360° media, students captured conditions in Lachung and Chungthang, allowing viewers to explore the landscape through a 360° photo and 360° video that reveal how topography and river dynamics intensify disaster impacts. 

They studied community-scale effects downstream, including damaged buildings, disrupted access, and prolonged recovery timelines. 

Rangpo offered a glimpse of recovery in motion, with materials staged for rebuilding bridges and roads essential to commerce and emergency response.

Indoor farms, also known as vertical farms, are popular among agricultural researchers and are expanding across the agricultural industry. Some benefits they have over outdoor farms include:

• Year-round production of food crops
• Less water and land requirements
• Not needing pesticides
• Reducing carbon emissions from shipping
• Reducing food waste

Additionally, some studies indicate that indoor farms produce more nutritious food for urban communities. 

However, these farms are often inaccessible to birds, bees, and other natural pollinators, leaving the pollination process to humans. The tedious process must be completed by hand for each flower to ensure the indoor crop flourishes.

Ai-Ping Hu, a principal research engineer at the Georgia Tech Research Institute (GTRI), has spent years exploring methods to efficiently pollinate flowering plants and food crops in indoor farms to find a way to efficiently pollinate flower plants and food crops in indoor farms.

Hu, Assistant Professor Shreyas Kousik of the George W. Woodruff School of Mechanical Engineering, and a rotating group of student interns have developed a robot prototype that may be up to the task.

The robot can efficiently pollinate plants that have both male and female reproductive parts. These plants only require pollen to be transferred from one part to the other rather than externally from another flower.

Natural pollinators perform this task outdoors, but Hu said indoor farmers often use a paintbrush or electric tootbrush to ensure these flowers are pollinated. 

Knowing the Pose

An early challenge the research team addressed was teaching the robot to identify the “pose” of each flower. Pose refers to a flower’s orientation, shape, and symmetry. Knowing these details ensures precise delivery of the pollen to maximize reproductive success. 

“It’s crucial to know exactly which way the flowers are facing,” Hu said.

“You want to approach the flower from the front because that’s where all the biological structures are. Knowing the pose tells you where the stem is. Our device grasps the stem and shakes it to dislodge the pollen.

“Every flower is going to have its own pose, and you need to know what that is within at least 10 degrees.”

Computer Vision Breakthrough

Harsh Muriki is a robotics master’s student at Georgia Tech’s School of Interactive Computing, who used computer vision to solve the pose problem while interning for Hu and GTRI.

Muriki attached a camera to a FarmBot to capture images of strawberry plants from dozens of angles in a small garden in front of Georgia Tech’s Food Processing Technology Building. The FarmBot is an XYZ-axis robot that waters and sprays pesticides on outdoor gardens, though it is not capable of pollination.

“We reconstruct the images of the flower into a 3D model and use a technique that converts the 3D model into multiple 2D images with depth information,” Muriki said. “This enables us to send them to object detectors.”

Muriki said he used a real-time object detection system called YOLO (You Only Look Once) to classify objects. YOLO is known for identifying and classifying objects in a single pass.

Ved Sengupta, a computer engineering major who interned with Muriki, fine-tuned the algorithms that converted 3D images into 2D.

“This was a crucial part of making robot pollination possible,” Sengupta said. “There is a big gap between 3D and 2D image processing.

“There’s not a lot of data on the internet for 3D object detection, but there’s a ton for 2D. We were able to get great results from the converted images, and I think any sector of technology can take advantage of that.”

Sengupta, Muriki, and Hu co-authored a paper about their work that was accepted to the 2025 International Conference on Robotics and Automation (ICRA) in Atlanta.

Measuring Success

The pollination robot, built in Kousik’s Safe Robotics Lab, is now in the prototype phase. 

Hu said the robot can do more than pollinate. It can also analyze each flower to determine how well it was pollinated and whether the chances for reproduction are high.

“It has an additional capability of microscopic inspection,” Hu said. “It’s the first device we know of that provides visual feedback on how well a flower was pollinated.”

For more information about the robot, visit the Safe Robotics Lab project page.

Georgia Stoica is one of 38 Ph.D. students worldwide researching machine learning who were named a 2025 Google Ph.D. Fellow.

Stoica is designing AI training methods that bypass fine-tuning, which is the process of adapting a large pre-trained model to perform new tasks. Fine-tuning is one of the most common ways engineers update large-language models like ChatGPT, Gemini, and Claude to add new capabilities. 

If an AI company wants to give a model a new capability, it could create a new model from scratch for that specific purpose. However, if the model already has relevant training and knowledge of the new task, fine-tuning is cheaper.

Stoica argues that fine-tuning still uses large amounts of data, and that other methods can help models learn more effectively and efficiently.

“Full fine-tuning yields strong performance, but it can be costly, and it risks catastrophic forgetting,” Stoica said. “My research asks if we can extend a model’s capabilities by imbuing it with the expertise of others, without fine-tuning?

“Reducing cost and improving efficiency is more important than ever. We have so many publicly available models that have been trained to solve a variety of tasks. It’s redundant to train a new model from scratch. It’s much more efficient to leverage the information that already exists to get a model up to speed.”

Stoica said the solution is a cost-effective method called model merging. This method combines two or more AI models into a single model, improving performance without fine-tuning.

On a basic level, Stoica said an example would be combining a model that is efficient at classifying cats with one that works well at dogs.

“Merging is cheap because you just take the parameters, the weights of your existing models, and combine them,” he said. “You could take the average of the weights to create a new model, but that sometimes doesn’t work. My work has aimed to rearrange the weights so they can communicate easily with each other.”

Through his Google fellowship, Stoica seeks to apply model merging to create a cutting-edge vision encoder. A vision encoder converts image or video data into numerical representations that computers can understand. This enables tasks such as image or facial recognition and generative image captioning.

“I want to be at the frontier of the field, and Google is clearly part of that,” Stoica said. “The vision encoder is very large-scale, and Google has the infrastructure to accommodate it.”