Coca-Cola, a neighbor to Georgia Tech since 1920, expects to sell a building and adjacent land in a transaction valued at $31.3 million. The company chose to work directly with Georgia Tech on the planned transaction, reflecting the long-standing relationship between the two organizations and a shared commitment to Atlanta’s continued growth and innovation.

The expected sale includes a two-story brick building, part of Coca-Cola’s holdings since 1988, and an adjoining two-acre park along North Avenue. 

“This strategic addition to our core campus will support our growth in enrollment and research activity for years to come,” said Georgia Tech President Ángel Cabrera. “I appreciate our long relationship with The Coca-Cola Company that allowed us to pursue this opportunity as we continue to invest in our campus, our neighborhood, and Atlanta’s innovation ecosystem.”  

James Quincey, Coca-Cola’s executive chair and Georgia Tech’s 2020 Commencement speaker, said the company wanted the property to continue contributing to Atlanta’s innovation ecosystem.

“When we decided this space was no longer needed for our corporate campus, our goal was to work with Georgia Tech, as this site offers a great opportunity for them to expand,” Quincey said. “Coca-Cola has a long legacy of involvement and partnership with Georgia Tech, and we are excited to see them redevelop this important area in Atlanta.”

Georgia Tech will evaluate how the property can best support academic, research, and student needs as part of its long-term campus planning efforts. The acquisition represents a strategic step in ensuring Georgia Tech has the space needed to educate future leaders and advance research that strengthens Georgia’s economy.

About Georgia Tech

The Georgia Institute of Technology, or Georgia Tech, is one of the top public research universities in the U.S., developing leaders who advance technology and improve the human condition.

The Institute offers business, computing, design, engineering, liberal arts, and sciences degrees, as well as professional development and K-12 programs for fostering success at every stage of life. Its more than 56,000 undergraduate and graduate students represent 54 U.S. states and territories and more than 146 countries. They study at the main campus in Atlanta, at instructional sites around the world, and through distance and online learning.

As a leading technological university, Georgia Tech is an engine of economic development for Georgia, the Southeast, and the nation, conducting more than $1 billion in research annually for government, industry, and society.

About The Coca-Cola Company

The Coca-Cola Company (NYSE: KO) is a total beverage company with products sold in more than 200 countries and territories. Our company’s purpose is to refresh the world and make a difference. We sell multiple billion-dollar brands across several beverage categories worldwide. Our portfolio of sparkling soft drink brands includes Coca-Cola, Sprite, and Fanta. Our water, sports, coffee, and tea brands include Dasani, smartwater, vitaminwater, Topo Chico, BODYARMOR, Powerade, Costa, Georgia, Fuze Tea, Gold Peak, and Ayataka. Our juice, value-added dairy, and plant-based beverage brands include Minute Maid, Simply, innocent, Del Valle, fairlife, and Santa Clara. We’re constantly transforming our portfolio, from reducing sugar in our drinks to bringing innovative new products to market. We seek to positively impact people’s lives, communities, and the planet through water replenishment, packaging recycling, sustainable sourcing practices, and carbon emissions reductions across our value chain. Together with our bottling partners, we employ more than 700,000 people, helping bring economic opportunity to local communities worldwide. Learn more at www.coca-colacompany.com and follow us on Instagram, Facebook, and LinkedIn.

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.

Atlanta is consistently ranked among the top cities for congestion, but new projects and a commitment to improving transportation on campus and in the city have earned Georgia Tech several honors and a reputation as a transportation infrastructure leader.  

Georgia Tech researchers say HPC and artificial intelligence (AI) advances this year are poised to improve how people power their homes, design safer buildings, and travel through cities.

According to Qi Tang, scientists will take progressive steps toward cleaner, sustainable energy through nuclear fusion in 2026. 

“I am very hopeful about the role of advanced computing and AI in making fusion a clean energy source,” said Tang, an assistant professor in the School of Computational Science and Engineering (CSE). 

“Fusion systems involve many interconnected processes happening across different scales. Modern simulations, combined with data-driven methods, allow us to bring these pieces together into a unified picture.”

Tang’s research connects HPC and machine learning with fusion energy and plasma physics. This year, Tang is continuing work on large-scale nuclear fusion models.

Only a few experimental fusion reactors exist worldwide compared to more than 400 nuclear fission reactors. Tang’s work supports a broader effort to turn fusion from a promising idea into a practical energy source.

Nuclear fusion occurs in plasma, the fourth state of matter, where gas is heated to millions of degrees. In this extreme state, electrons are stripped from atoms, creating a hot soup of fast-moving ions and free electrons. In plasma, hydrogen atoms overcome their natural electrical repulsion, collide, and fuse together. This releases energy that can power cities and homes.

Computers interpret extreme temperatures, densities, pressures, and plasma particle motion as massive datasets. Tang works to assimilate these data types from computer models and real-world experiments.

To do this, he and other researchers rely on machine learning approaches to analyze data across models and experiments more quickly and to produce more accurate predictions. Over time, this will allow scientists to test and improve fusion reactor designs toward commercial use. 

Beyond energy and nuclear engineering, Umar Khayaz sees broader impacts for HPC in 2026.

“HPC is the need of the day in every field of engineering sciences, physics, biology, and economics,” said Khayaz, a CSE Ph.D. student in the School of Civil and Environmental Engineering. 

“HPC is important enough to say that we need to employ resources to also solve social problems.”

Khayaz studies dynamic fracture and phase-field modeling. These areas explore how materials break under sudden, rapid loads. 

Like nuclear fusion, Khayaz says dynamic fracture problems are complex and data-intensive. In 2026, he expects to see more computing resources and computational capabilities devoted to understanding these problems and other emerging civil engineering challenges.

CSE Ph.D. student Yiqiao (Ahren) Jin sees a similar relationship between infrastructure and self-driving vehicles. He believes AI will innovate this area in 2026.

At Georgia Tech, Jin develops efficient multimodal AI systems. An autonomous vehicle is a multimodal system that uses camera video, laser sensors, language instructions, and other inputs to navigate city streets under changing scenarios like traffic and weather patterns.

Jin says multimodal research will move beyond performance benchmarks this year. This shift will lead to computer systems that can reason despite uncertainty and explain their decisions. In result, engineers will redefine how they evaluate and deploy autonomous systems in safety-critical settings.

“Many foundational problems in perception, multimodal reasoning, and agent coordination are being actively addressed in 2026. These advances enable a transition from isolated autonomous systems to safer, coordinated autonomous vehicle fleets,” Jin said. 

“As these systems scale, they have the potential to fundamentally improve transportation safety and efficiency.”

“It has been a pleasure for the Center for Programs to Increase Engagement in the Sciences (C-PIES) to collaborate with Google and the College of Sciences Advisory Board to bring this fellowship, which will positively impact our community and highlight how science can align with public good,” says Lewis A. Wheaton, professor in the School of Biological Sciences and director of C-PIES. 

In the year ahead, the fellows will work with C-PIES and community partners on campus and in the metro Atlanta area to develop projects in one of three priority areas: civic and policy engagement, community-engaged research, and K-12 research outreach. 

The fellowship was open to all graduate students in the College of Sciences, and four inaugural fellows — Aniruddh Bakshi, Katherine Slenker, Miriam Simma, and Nikolai Simonov — were named based on their exciting, yet feasible applications.

Fellow Aniruddh Bakshi: Strengthening trust in science 

Ph.D. student Aniruddh Bakshi studies the problem of drug delivery at the intersections of organic chemistry, biochemistry, and immunology. As mRNA vaccines are closely related to his area of research, he sees the need for a grassroots outreach movement from young academics to help bolster public confidence in rigorous scientific methodology. 

In collaboration with local hospitals and nonprofits, his proposed project is to start a social media content series, titled “A Day in the Life of a Ph.D. Student,” to show the realities of graduate school for those interested in this career path while connecting his research to broader public issues. 

“Science has the power to solve urgent problems, but only if people understand and trust it,” says Bakshi. “Through this fellowship, I will use my research and outreach efforts to help strengthen that trust — showing how discoveries in drug delivery and vaccine design can make a real difference in people’s lives.” 

Fellow Katherine Slenker: Creating a biodiversity data network 

Atlanta is often referred to as “the city in a forest,” but according to Ph.D. student Katherine Slenker, wildlife has a difficult time navigating across roads and housing developments, often resulting in human-wildlife conflict. 

“Conservation ecologists have long recommended that the movement of wildlife could be eased through the creation of ‘ecological corridors,’ which connect greenspaces and wildlife populations,” she explains. “Determining the movement patterns of wildlife, and where such corridors may be best situated, requires that we first understand what species reside in the metro Atlanta area as well as how they are expected to disperse.”

As a fellow, Slenker plans to build a biodiversity data network by comparing wildlife monitoring at Davidson-Arabia Mountain Nature Preserve and Stone Mountain Park and increasing the coalition of metro Atlanta researchers. This data can be used in the development of ecological corridors to reduce clashing between humans and wildlife, notably animals struck by vehicles, and improve ecosystem health at these parks. 

Fellow Miriam Simma: Making structural biology research more accessible 

The study of crystallography is vital in academia, industry, and medicine because it enables researchers to decipher the atomic structures of proteins, but it is scarcely taught outside of graduate school. Ph.D. student Miriam Simma wants to change that. 

Her proposed project is to introduce protein crystallography to K-12 students and teachers through hands-on activities in local high school classrooms and to the public during the Atlanta Science Festival at Georgia Tech.

“My vision is to make structural biology research accessible, so everyone can engage with cutting-edge scientific research — fostering curiosity and interest in STEM careers,” says Simma. “Long term, I will synthesize these activities into a chemical education article that introduces K-12 students to protein structure and function.” 

Fellow Nikolai Simonov: Mentoring middle school scientists 

Last year, Ph.D. student Nikolai Simonov became involved in the GoSTEM Club at Lilburn Middle School — leading student activities and recruiting other graduate student volunteers. In partnership with Georgia Tech’s Center for Education Integrating Science, Mathematics and Computing, the club is a weekly afterschool program for students, many of whom come from underserved backgrounds, to grow their scientific curiosity. 

“I assembled a team of 10 Tech graduate students who could explain complex scientific concepts in approachable ways for middle school students. Through this fellowship, we are excited to enrich the GoSTEM Club with an ongoing mentorship program and materials for more ambitious science fair projects,” shares Simonov. 

As part of the program, club members can meet one-on-one with Georgia Tech mentors to discuss their educational and career goals. “By sharing their stories and connecting scientific ideas to real-world applications, our mentors aim to show students that STEM is not only accessible but a path toward a fulfilling life,” he adds.

Some were still alive, but most of the birds were dead. They were all too easy to find.

“I knew birds hit buildings, but I didn’t know much more about the issue at that time, and I was surprised how easily I just found birds,” Betuel said.

Birds flying into windows aren’t isolated events. Environmentalists estimate between 365 million and one billion birds die each year from colliding with structures in the U.S.  

“That statistic is hard for most people to comprehend,” Betuel said. “When you think about the millions of homes we have and these high-rise buildings, and if each one is killing a few a year, that number can get big pretty quick.”

Betuel is the executive director of Birds Georgia, a nonprofit affiliate of the Audubon network that leads bird conservation efforts in Georgia. For 10 years, volunteers from the organization have combed Atlanta’s streets, collecting bird specimens.

Birds Georgia launched Project Safe Flight in 2015 to reduce bird building-collision mortality through data collection. Through legislation, the group aims to make building construction bird-friendly and reduce light pollution.

Environmentalists who study the issue have ranked Atlanta, which sits squarely on a migration route, as the fourth-most dangerous city for birds during fall migration. It is the ninth-most dangerous city during spring migration.

The number of bird deaths from collisions in Atlanta and across the state remains unknown. However, new data tools developed by student researchers in the College of Computing at Georgia Tech are helping Birds Georgia get a clearer picture of the issue.

“We’ve been working with different folks at Georgia Tech for years now, but it’s really picked up lately,” Betuel said. “There’s a lot of momentum and interest on campus to try to make the city safer for birds.”

Pushing for Policy

Ashley Boone, a Ph.D. student in human-centered computing in Tech’s School of Interactive Computing, has led the student effort to help Birds Georgia organize its data. 

Boone said organizing data and knowing how to use it is critical to spark conversations about adopting legislation.

“We often see a gap between data collection and data advocacy,” she said. “Birds Georgia has done an amazing job of tracking collisions in Atlanta over the last 10 years. My goal is to understand the role technology can play in making data useful for policy change.”

User-interface tools designed by computer science undergraduate students James Kemerait and Ian Wood have ramped up that process. One tool converts data input into visualizations optimized for social media, while another consolidates the data collected by volunteers and external sources.

Boone said the desired legislation would mirror policies implemented by New York City. Those policies require the use of bird-safe materials — like window film with patterned designs that break up reflections — in new buildings and buildings undergoing significant renovations. 

What Can Residents Do?

Residents, whose homes account for about 40% of bird collision deaths in the U.S., can also make an impact.

“Households are an underexamined cause of bird collisions,” Boone said. “We focus on the big buildings because it’s easier to convince one manager of a large building to use bird-safe materials, and it’s easier for a policy to address a commercial building. But the sheer volume of residential buildings in the U.S. has a tremendous impact on the number of collisions.”

Steps that homeowners can take include:

• Buying bird-safe film or making do-it-yourself versions of it to put on windows.
• Placing attractive objects like birdhouses and birdfeeders very close or very far away from windows.
• Turning off lights after 9 p.m. on the busiest migration nights of the year.

Betuel said millions of birds can fly over Atlanta on a single night during migration, and they are attracted to the city lights.

“They’ll come into urban centers and collide with an illuminated building, or maybe they overnight somewhere that isn’t safe,” he said. “The next day, they’re surrounded by glass, and birds don’t understand reflection.”

Residents can visit the Birds Georgia website to sign up for the Lights Out Pledge. Those who sign up will receive a text on the 10 busiest migratory nights of the year, and they will be asked to turn their lights off early.

The tools provided by Georgia Tech gave Birds Georgia insight into the number of bird species affected by collisions — more than 140, according to Betuel.

Betuel said that when the organization reaches an estimate of bird collisions, he hopes the number will raise alarms and turn people’s attention to the ecological impact. 

“All these birds being lost results in fewer birds to eat pest insects, fewer birds to pollinate flowers, fewer birds to disperse seeds — all the ecological functions that we need, that they’re doing in the background that most people aren’t keen to,” he said. “If this decline in bird life continues to happen, at some point, there will be issues with our ecosystems functioning as they always have.”

The assessment, funded by the city’s Tree Recompense Fund, uses advanced remote sensing tools such as WorldView-2 satellite data and a random forest classification model to categorize land into three land cover types. These include tree canopy, non-tree vegetation (grass, shrubs, and low lying vegetation) and non-vegetation (water, pervious surface). The methodology delivers a detailed spatial picture of land cover across the city.

“This is simply a tool in their planning arsenal,” said Anthony Giarrusso, who has led every canopy study since 2008. “Before they did any of this work in 2008, everything was anecdotal. It was reactionary.”

The new study is not advocacy — it’s information. Giarrusso emphasized that while researchers stay neutral in the politics of urban growth and conservation, their work equips city leaders with science-based knowledge to make more effective zoning and planning decisions.

In addition to mapping existing conditions, the Georgia Tech team developed the Potential Planting Index (PPI), a scalable tool that identifies where tree planting is physically possible based on current land cover. The tool quantifies the difference between tree canopy and non-tree vegetation, indicating zones with restoration potential.

Another key insight is the challenge of interpreting canopy change without understanding land use patterns. “It gives you a false sense of stability if you don’t understand the underlying land use,” said Giarrusso. “You might see canopy regrowth on paper, but that land could be cleared again tomorrow.” He explained that this false signal is particularly common in stalled development sites: “We saw a lot of properties where trees had regrown after initial clearing, but it was temporary and monoculture, low quality canopy. Several of those areas were cleared again for construction later.”

Giarrusso pointed to these “loss-gain-loss” cycles as one of the more misleading aspects of tree canopy analysis without strong land use context. “Some of them were pipe farms — land cleared for development with infrastructure like water and sewer lines installed, but then construction never happened. So trees grow back, and you get a canopy gain that doesn’t last and is nowhere near the quality of the trees originally cleared.”

He stressed that policymakers need to consider the permanence of canopy when using the data. “If it’s just going to be cleared again in two years, it’s not really a gain. That’s why long-term tracking and land use analysis together are so important.”

The city has incorporated these tools into broader planning efforts, including zoning reform and tree ordinance revisions. The research supports recommendations such as restricting full lot clearing in certain zoning categories and adjusting setback or lot coverage limits to better preserve existing canopy.

Giarrusso underscored the urgency of protecting larger, intact forested tracts. “If you can see it from space and it’s still forest — save it,” he said. “Once it’s cleared, you don’t get it back.”

311 systems allow residents to report potholes, broken fire hydrants, and other municipal issues. In recent years, the use of artificial intelligence (AI) to provide 311 services to community residents has boomed across city and state governments. This includes an artificial virtual assistant (AVA) developed by third-party vendors for the City of Atlanta in 2023.

Through survey data, researchers from Tech’s School of Interactive Computing found that many residents are generally positive about 311 chatbots. In addition to eliminating long wait times over the phone, they also offer residents quick answers to permit applications, waste collection, and other frequently asked questions.

However, the study, which was conducted in Atlanta, indicates that 311 chatbots could be causing residents to feel isolated from public officials and less aware of what’s happening in their community.

Jieyu Zhou, a Ph.D. student in the School of IC, said it doesn’t have to be that way.

Uniting Communities

Zhou and her advisor, Assistant Professor Christopher MacLellan, published a paper at the 2025 ACM Designing Interactive Systems (DIS) Conference that focuses on improving public service chatbot design and amplifying their civic impact. They collaborated with Professor Carl DiSalvo, Associate Professor Lynn Dombrowski, and graduate students Rui Shen and Yue You.

Zhou said 311 chatbots have the potential to be agents that drive community organization and improve quality of life.

“Current chatbots risk isolating users in their own experience,” Zhou said. “In the 311 system, people tend to report their own individual issues but lose a sense of what is happening in their broader community. 

“People are very positive about these tools, but I think there’s an opportunity as we envision what civic chatbots could be. It’s important for us to emphasize that social element — engaging people within the community and connecting them with government representatives, community organizers, and other community members.”

Zhou and MacLellan said 311 chatbots can leave users wondering if others in their communities share their concerns.

“If people are at a town hall meeting, they can get a sense of whether the problems they are experiencing are shared by others,” Zhou said. “We can’t do that with a chatbot. It’s like an isolated room, and we’re trying to open the doors and the windows.”

Adding a Human Touch

In their paper, the researchers note that one of the biggest criticisms of 311 chatbots is they can’t replace interpersonal interaction.

Unlike chatbots, people working in local government offices are likely to:

• Have direct knowledge of issues
• Provide appropriate referrals
• Empathize with the resident’s concerns

MacLellan said residents are likely to grow frustrated with a chatbot when reporting issues that require this level of contextual knowledge.

One person in the researchers’ survey noted that the chatbot they used didn’t understand that their report was about a sidewalk issue, not a street issue.

“Explaining such a situation to a human representative is straightforward,” MacLellan said. “However, when the issue being raised does not fall within any of the categories the chatbot is built to address, it often misinterprets the query and offers information that isn’t helpful.”

The researchers offer some design suggestions that can help chatbots foster community engagement and improve community well-being:

• Escalation. Regarding the sidewalk report, the chatbot did not offer a way to escalate the query to a human who could resolve it. Zhou said that this is a feature that chatbots should have but often lack.
• Transparency. Chatbots could provide details about recent and frequently reported community issues. They should inform users early in the call process about known problems to help avoid an overload of user complaints.
• Education. Chatbots can keep users updated about what’s happening in their communities.
• Collective action. Chatbots can help communities organize and gather ideas to address challenges and solve problems.

“Government agencies may focus mainly on fixing individual issues,” Zhou said, “But recognizing community-level patterns can inspire collective creativity. For example, one participant suggested that if many people report a broken swing at a playground, it could spark an initiative to design a new playground together—going far beyond just fixing it.”

These are just a few examples of things, the researchers argue, that 311 services were originally designed to achieve.

“Communities were already collaborating on identifying and reporting issues,” Zhou said. “These chatbots should reflect the original intentions and collaboration practices of the communities they serve.

“Our research suggests we can increase the positive impact of civic chatbots by including social aspects within the design of the system, connecting people, and building a community view.”

Georgia Tech researchers say the new policy marks a major step forward in climate adaptation, especially for heat-vulnerable communities, and could help position Atlanta as a national leader in urban resilience.

How Cool Roofs Can Help Hotlanta 

”On any given summer afternoon, temperatures in Atlanta’s intown neighborhoods can be as much as 15 degrees Fahrenheit higher than in the city’s most forested areas,” said Brian Stone, professor in the School of City and Regional Planning and associate director of Georgia Tech’s Center for Urban Resilience and Analytics.

That spike is partly due to the urban heat island effect — a phenomenon driven by heat-trapping materials like concrete, asphalt, and dark rooftops, combined with the loss of trees and natural landscapes. The impacts are not just uncomfortable — they’re dangerous. Extreme heat is now one of the deadliest forms of weather in the U.S., with disproportionate effects on low-income communities, elderly residents, and those without access to air conditioning.

According to Patrick Kastner, assistant professor in the School of Architecture, rooftops are key contributors. “A major driver [of heat buildup] is dark, heat-absorbing material that stores solar energy during the day and then re-radiates it at night. If you look at a satellite image, for most of the day rooftops have more exposure to the sun than building facades — so the material choice there matters a lot.”

The Power of Reflective Roofs — and Trees

Stone and his students conducted modeling that found that widespread adoption of cool roofs across Atlanta could lower summer afternoon temperatures by more than 2 degrees Fahrenheit in many neighborhoods. That’s comparable to findings in other global cities like London, where cool roofs have reduced average temperatures by up to 2 degrees Celsius (3.6 F).

But cool roofs are only one part of a broader urban cooling strategy. In the same study, Stone’s team showed that planting trees in just half of Atlanta’s available planting zones could yield an even more dramatic effect, reducing temperatures by 4 F or more in some areas.

“Cool roofs are highly effective, but pairing them with increased urban tree cover would multiply the benefits, especially for neighborhoods currently lacking shade,” Stone said.

Equity and Energy Impacts

Atlanta’s ordinance requires cool roofing materials on new commercial construction and when existing commercial roofs are replaced. While that may sound like a technical design tweak, Stone emphasized its equity implications.

“Residents in South and West Atlanta, where tree canopy is sparse, and energy costs take up a larger share of household income, stand to gain the most,” Stone said. “When a cool roof is installed as part of a required roof replacement, those households will see meaningful reductions in cooling costs month after month.”

Kastner added that cool roofs could ease pressure on the electrical grid, lowering peak energy demand required for cooling during extreme heat and possibly reduce the risk of outages.

Durability, Maintenance, and Design Trade-offs

Stone noted that cool roofs tend to extend the life of roofing materials by limiting thermal degradation. However, he and Kastner also flagged some trade-offs.

For example, highly reflective coatings can create glare, especially on sloped roofs near neighboring buildings. The ordinance accounts for this by setting different standards for flat and pitched roofs. Maintenance is another consideration: over time, reflective coatings may degrade or become dirty, requiring periodic cleaning to maintain performance.

“Aesthetics and material compatibility may also challenge adoption when it comes to historic buildings or for roofs already outfitted with solar panels,” Kastner said. “But advancements in roofing technology, including high-performance materials that aren’t plain white, offer more flexible options than ever before.”

A Cool Roof Policy With National Impact

While cities like New York and Chicago have implemented cool roof programs for over a decade, Atlanta’s proposed ordinance is one of the most comprehensive in the country — applying to all roof types, not just flat industrial ones.

“Atlanta is steadily emerging as one of the most climate-resilient cities in the U.S.,” said Stone, pointing to the city’s urban forest and growing network of floodable parks as complementary resilience strategies. “Adding a best-in-class cool roofing ordinance to that portfolio is a bold step forward.”

And it could spark innovation across the region.

“Georgia Tech is uniquely positioned to help advance climate-resilient design,” Kastner said. “From research on advanced coatings to urban planning tools that target the most heat-vulnerable areas, we’re bringing science and policy together to shape cooler, healthier cities.”

Before these futuristic aircraft can take off, Georgia Tech researchers say there’s serious work to do — in the air, on the ground, and in policy.

Why Now? The Technology Is Catching Up

“The same battery and automation technologies we’re using in electric ground vehicles are now being scaled for aircraft,” said Laurie Garrow, professor in the School of Civil and Environmental Engineering and co-director of Georgia Tech’s Center for Urban and Regional Air Mobility. “We’re also seeing improvements in distributed propulsion and composite materials that make these aircraft lighter, quieter, and more efficient.”

Garrow cautions that widespread commercial service is years away. “We may see high-profile demonstrations soon, maybe even at global events like the Olympics, but aviation certification is a rigorous process. It takes time to earn public trust.”

Safety, Regulation, and Public Acceptance

The promise of AAM depends on more than aircraft design — it also requires new safety frameworks and public confidence.

“We’ll need to define what I call ‘roads in the sky’ — safe corridors where these aircraft can operate alongside traditional air traffic,” Garrow said. “And we’ll need to ensure certification standards, air traffic control, and pilot training evolve alongside technology.” 

Understanding how these vehicles interact with complex urban environments is essential to safe operation. Marilyn Smith, David Sloan Lews Professor in the School of Aerospace Engineering and director of the Vertical Lift Research Center of Excellence, leads research on modeling and simulation to prepare aircraft for real-world conditions.

Her lab is developing real-time simulations that factor in turbulence, wind shear, and other transient effects. “These predictions are not trivial,” Smith said. “We need fast, physics-based models that can run in near-real time to inform both design and regulation. There are significant and abrupt variations in the atmosphere that must be accounted for, both for passenger vehicles and smaller delivery drones.”

Smith’s team is also integrating artificial intelligence to improve speed and accuracy in certification — but always under expert oversight. “AI can accelerate our work,” she said. “Without the knowledge of domain experts, machine learning can generate misleading results, and that’s unacceptable when safety is on the line.”

Infrastructure, Airspace, and the Urban Puzzle

Even the most advanced aircraft cannot operate without new infrastructure on the ground and in the sky. 

Vertiports are needed to allow aircraft to take off and land vertically. Also required are “charging systems and robust fire safety protocols for high-energy batteries,” Garrow said. “And perhaps most critically, we need ‘rules of the road in the sky’ to manage air traffic around existing airports.”

Atlanta could offer a unique advantage. “The runways at Hartsfield-Jackson run east to west, while most of the metro population centers are north and south,” Garrow noted. “That natural separation could make it easier to integrate vertical takeoff and landing operations.”

Alex Oettl, professor in the Scheller College of Business, cautions that AAM’s benefits could concentrate in major hubs without inclusive planning. “Improved connectivity will raise productivity in ‘superstar cities,’ but we’ll need new strategies if we want to ensure smaller communities aren’t left behind,” he said.

China’s Head Start and What It Means for the U.S.

Oettl notes that China has surged ahead in AAM thanks to coordinated government action, flexible regulations, and significant infrastructure investment.

“In contrast, the U.S. and Europe face more stringent certification requirements,” Oettl said. “That slows deployment but ideally ensures stronger safety standards. It’s a tradeoff between innovation speed and risk management.”

Cities and companies that move first into AAM could shape standards and attract investment — but they also shoulder more risk. “There’s a danger of technological lock-in or stranded assets if early systems don’t scale or demand falls short,” Oettl said. “We’ve seen parallels before, like the scooter boom that left cities with thousands of idle vehicles.”

Looking Ahead: The Urban Sky 

For now, AAM remains on the horizon — visible but not yet within reach. Coordinated efforts between government, industry, and academia will determine how quickly it moves from prototype to daily reality.

“Georgia has been proactive in attracting aviation manufacturing,” Garrow said. “Coupled with our state’s infrastructure and Georgia Tech’s research ecosystem, we’re well positioned to lead.”

She added, “In aviation, we like to say we crawl, we walk, we run. These technologies are coming, but safely integrating them into our skies will take time, teamwork, and trust.”

With a keen eye and a passion for geography, Radu Casapu, a graduate student in the School of City and Regional Planning, won the 2025 GeoGuessr World Championship in Copenhagen, Denmark.

PEMBROKE, GA — For more than two decades, Ray Butler has run Butler’s Tire & Lube in the heart of Pembroke. He’s seen the town evolve, shrink, and now, rapidly grow — all during the time of his life as a local here. 

“Science Square Labs marks a pivotal step forward for Georgia Tech and for Atlanta’s growing life sciences ecosystem. We’re not only accelerating our research and innovation — we’re building powerful momentum across the region,” said Ángel Cabrera, president of Georgia Tech. “Our labs moving to this space will attract top talent and drive medical innovation. The move sets the stage for transformative discoveries, and we hope others will join us to continue Atlanta’s evolution into a global hub for medical breakthroughs.” 

This move comes as Georgia Tech saw a 46% increase in research awards from 2018 to 2024, evidence of the Institute’s fast-growing impact. By adding these labs, Atlanta strengthens its position on the national stage for advanced tech and life sciences innovation.  

Why It Matters 

• Saving lives: From early cancer detection and more innovative immune therapies to healing damaged tissues and managing chronic diseases, the research that will be conducted at Science Square tackles health issues millions face.
• Fueling a tech hub: By combining research powerhouses like Georgia Tech and Emory with next-gen laboratory facilities, Atlanta is building the brainpower and resources to compete with national tech centers.
• Economic growth: Science Square is helping attract top researchers, startups, and funding — bringing jobs, investment, and opportunities to Georgia. Most recently, Duracell announced they are moving their research and development headquarters to Science Square. 

Research for Real Life 

Ph.D. student Phillip Si and Assistant Professor Peng Chen developed Latent-EnSF, a technique that improves how ML models assimilate data to make predictions.

In experiments predicting medium-range weather forecasting and shallow water wave propagation, Latent-EnSF demonstrated higher accuracy, faster convergence, and greater efficiency than existing methods for sparse data assimilation.

“We are currently involved in an NSF-funded project aimed at providing real-time information on extreme flooding events in Pinellas County, Florida,” said Si, who studies computational science and engineering (CSE). 

“We're actively working on integrating Latent-EnSF into the system, which will facilitate accurate and synchronized modeling of natural disasters. This initiative aims to enhance community preparedness and safety measures in response to flooding risks.” 

Latent-EnSF outperformed three comparable models in assimilation speed, accuracy, and efficiency in shallow water wave propagation experiments. These tests show models can make better and faster predictions of coastal flood waves, tides, and tsunamis. 

In experiments on medium-range weather forecasting, Latent-EnSF surpassed the same three control models in accuracy, convergence, and time. Additionally, this test demonstrated Latent-EnSF's scalability compared to other methods.

These promising results support using ML models to simulate climate, weather, and other complex systems.

Traditionally, such studies require employment of large, energy-intensive supercomputers. However, advances like Latent-EnSF are making smaller, more efficient ML models feasible for these purposes.

The Georgia Tech team mentioned this comparison in its paper. It takes hours for the European Center for Medium-Range Weather Forecasts computer to run its simulations. Conversely, the ML model FourCastNet calculated the same forecast in seconds.

“Resolution, complexity, and data-diversity will continue to increase into the future,” said Chen, an assistant professor in the School of CSE. 

“To keep pace with this trend, we believe that ML models and ML-based data assimilation methods will become indispensable for studying large-scale complex systems.”

Data assimilation is the process by which models continuously ingest new, real-world data to update predictions. This data is often sparse, meaning it is limited, incomplete, or unevenly distributed over time. 

Latent-EnSF builds on the Ensemble Filter Scores (EnSF) model developed by Florida State University and Oak Ridge National Laboratory researchers. 

EnSF’s strength is that it assimilates data with many features and unpredictable relationships between data points. However, integrating sparse data leads to lost information and knowledge gaps in the model. Also, such large models may stop learning entirely from small amounts of sparse data.

The Georgia Tech researchers employ two variational autoencoders (VAEs) in Latent-EnSF to help ML models integrate and use real-world data. The VAEs encode sparse data and predictive models together in the same space to assimilate data more accurately and efficiently.

Integrating models with new methods, like Latent-EnSF, accelerates data assimilation. Producing accurate predictions more quickly during real-world crises could save lives and property for communities.

[Related: University of South Florida Researchers Track Flooding in Coastal Communities During Hurricanes Helene and Milton]

To share Latent-EnSF to the broader research community, Chen and Si presented their paper at the SIAM Conference on Computational Science and Engineering (CSE25). The Society of Industrial and Applied Mathematics (SIAM) organized CSE25, held March 3-7 in Fort Worth, Texas.

Chen was one of ten School of CSE faculty members who presented research at CSE25, representing one-third of the School’s faculty body. Latent-EnSF was one of 15 papers by School of CSE authors and one of 23 Georgia Tech papers presented at the conference.

The pair will also present Latent-EnSF at the upcoming International Conference on Learning Representations (ICLR 2025). Occurring April 24-28 in Singapore, ICLR is one of the world’s most prestigious conferences dedicated to artificial intelligence research.

“We hope to bring attention to experts and domain scientists the exciting area of ML-based data assimilation by presenting our paper,” Chen said. “Our work offers a new solution to address some of the key shortcomings in the area for broader applications.”

As the Los Angeles fires quickly spread starting Jan. 7, with wind gusts approaching 100 mph, scientists observed a 110-fold rise in airborne lead levels. This spike had receded by Jan. 11.  

Researchers from the School of Computational Science and Engineering (CSE) created the Large Pre-Trained Time-Series Model (LPTM) framework. LPTM is a single foundational model that completes forecasting tasks across a broad range of domains. 

Along with performing as well or better than models purpose-built for their applications, LPTM requires 40% less data and 50% less training time than current baselines. In some cases, LPTM can be deployed without any training data.

The key to LPTM is that it is pre-trained on datasets from different industries like healthcare, transportation, and energy. The Georgia Tech group created an adaptive segmentation module to make effective use of these vastly different datasets.

The Georgia Tech researchers will present LPTM in Vancouver, British Columbia, Canada, at the 2024 Conference on Neural Information Processing Systems (NeurIPS 2024). NeurIPS is one of the world’s most prestigious conferences on artificial intelligence (AI) and ML research.

“The foundational model paradigm started with text and image, but people haven’t explored time-series tasks yet because those were considered too diverse across domains,” said B. Aditya Prakash, one of LPTM’s developers. 

“Our work is a pioneer in this new area of exploration where only few attempts have been made so far.”

[MICROSITE: Georgia Tech at NeurIPS 2024]

Foundational models are trained with data from different fields, making them powerful tools when assigned tasks. Foundational models drive GPT, DALL-E, and other popular generative AI platforms used today. LPTM is different though because it is geared toward time-series, not text and image generation.  

The Georgia Tech researchers trained LPTM on data ranging from epidemics, macroeconomics, power consumption, traffic and transportation, stock markets, and human motion and behavioral datasets.

After training, the group pitted LPTM against 17 other models to make forecasts as close to nine real-case benchmarks. LPTM performed the best on five datasets and placed second on the other four.

The nine benchmarks contained data from real-world collections. These included the spread of influenza in the U.S. and Japan, electricity, traffic, and taxi demand in New York, and financial markets.   

The competitor models were purpose-built for their fields. While each model performed well on one or two benchmarks closest to its designed purpose, the models ranked in the middle or bottom on others.

In another experiment, the Georgia Tech group tested LPTM against seven baseline models on the same nine benchmarks in zero-shot forecasting tasks. Zero-shot means the model is used out of the box and not given any specific guidance during training. LPTM outperformed every model across all benchmarks in this trial.

LPTM performed consistently as a top-runner on all nine benchmarks, demonstrating the model’s potential to achieve superior forecasting results across multiple applications with less and resources.

“Our model also goes beyond forecasting and helps accomplish other tasks,” said Prakash, an associate professor in the School of CSE. 

“Classification is a useful time-series task that allows us to understand the nature of the time-series and label whether that time-series is something we understand or is new.”

One reason traditional models are custom-built to their purpose is that fields differ in reporting frequency and trends. 

For example, epidemic data is often reported weekly and goes through seasonal peaks with occasional outbreaks. Economic data is captured quarterly and typically remains consistent and monotone over time. 

LPTM’s adaptive segmentation module allows it to overcome these timing differences across datasets. When LPTM receives a dataset, the module breaks data into segments of different sizes. Then, it scores all possible ways to segment data and chooses the easiest segment from which to learn useful patterns.

LPTM’s performance, enhanced through the innovation of adaptive segmentation, earned the model acceptance to NeurIPS 2024 for presentation. NeurIPS is one of three primary international conferences on high-impact research in AI and ML. NeurIPS 2024 occurs Dec. 10-15.

Ph.D. student Harshavardhan Kamarthi partnered with Prakash, his advisor, on LPTM. The duo are among the 162 Georgia Tech researchers presenting over 80 papers at the conference. 

Prakash is one of 46 Georgia Tech faculty with research accepted at NeurIPS 2024. Nine School of CSE faculty members, nearly one-third of the body, are authors or co-authors of 17 papers accepted at the conference. 

Along with sharing their research at NeurIPS 2024, Prakash and Kamarthi released an open-source library of foundational time-series modules that data scientists can use in their applications.

“Given the interest in AI from all walks of life, including business, social, and research and development sectors, a lot of work has been done and thousands of strong papers are submitted to the main AI conferences,” Prakash said. 

“Acceptance of our paper speaks to the quality of the work and its potential to advance foundational methodology, and we hope to share that with a larger audience.”

These are details autonomous flying vehicles would need to know to function safely. However, few aerial image datasets exist that can adequately train the computer vision algorithms that would pilot these vehicles.

That’s why Georgia Tech researchers created a new benchmark dataset of computer-generated aerial images.

Judy Hoffman, an assistant professor in Georgia Tech’s School of Interactive Computing, worked with students in her lab to create SKYSCENES. The dataset contains over 33,000 aerial images of cities curated from a computer simulation program.

Hoffman said sufficient training datasets could unlock the potential of autonomous flying vehicles. Constructing those datasets is a challenge the computer vision research community has been working for years to overcome.

“You can’t crowdsource it the same way you would standard internet images,” Hoffman said. “Trying to collect it manually would be very slow and expensive — akin to what the self-driving industry is doing driving around vehicles, but now you’re talking about drones flying around. 

“We must fix those problems to have models that work reliably and safely for flying vehicles.”

Many existing datasets aren’t annotated well enough for algorithms to distinguish objects in the image. For example, the algorithms may not recognize the surface of a building from the surface of a street.

Working with Hoffman, Ph.D. student Sahil Khose tried a new approach — constructing a synthetic image data set from a ground-view, open-source simulator known as CARLA.

CARLA was originally designed to provide ground-view simulation for self-driving vehicles. It creates an open-world virtual reality that allows users to drive around in computer-generated cities.

Khose and his collaborators adjusted CARLA’s interface to support aerial views that mimic views one might get from unmanned aerial vehicles (UAVs). 

What's the Forecast?

The team also created new virtual scenarios to mimic the real world by accounting for changes in weather, times of day, various altitudes, and population per city. The algorithms will struggle to recognize the objects in the frame consistently unless those details are incorporated into the training data.

“CARLA’s flexibility offers a wide range of environmental configurations, and we take several important considerations into account while curating SKYSCENES images from CARLA,” Khose said. “Those include strategies for obtaining diverse synthetic data, embedding real-world irregularities, avoiding correlated images, addressing skewed class representations, and reproducing precise viewpoints.”

SKYSCENES is not the largest dataset of aerial images to be released, but a paper co-authored by Khose shows that it performs better than existing models. 

Khose said models trained on this dataset exhibit strong generalization to real-world scenarios, and integration with real-world data enhances their performance. The dataset also controls variability, which is essential to perform various tasks.

“This dataset drives advancements in multi-view learning, domain adaptation, and multimodal approaches, with major implications for applications like urban planning, disaster response, and autonomous drone navigation,” Khose said. “We hope to bridge the gap for synthetic-to-real adaptation and generalization for aerial images.”

Seeing the Whole Picture

For algorithms, generalization is the ability to perform tasks based on new data that expands beyond the specific examples on which they were trained.

“If you have 200 images, and you train a model on those images, they’ll do well at recognizing what you want them to recognize in that closed-world initial setting,” Hoffman said. “But if we were to take aerial vehicles and fly them around cities at various times of the day or in other weather conditions, they would start to fail.”

That’s why Khose designed algorithms to enhance the quality of the curated images.

“These images are captured from 100 meters above ground, which means the objects appear small and are challenging to recognize,” he said. “We focused on developing algorithms specifically designed to address this.”

Those algorithms elevate the ability of ML models to recognize small objects, improving their performance in navigating new environments.

“Our annotations help the models capture a more comprehensive understanding of the entire scene — where the roads are, where the buildings are, and know they are buildings and not just an obstacle in the way,” Hoffman said. “It gives a richer set of information when planning a flight.

“To work safely, many autonomous flight plans might require a map given to them beforehand. If you have successful vision systems that understand exactly what the obstacles in the real world are, you could navigate in previously unseen environments.”

For more information about Georgia Tech Research at ECCV 2024, click here.

Led by a team of University of Alaska Fairbanks and Georgia Tech researchers that includes School of Earth and Atmospheric Sciences Professor Rodney Weber, the researchers' latest findings are published in Science Advances. 

In the study, the team leveraged state-of-the-art thermodynamic tools used in global air quality models, with an aim to better understand how reducing the amount of primary sulfate in the atmosphere might affect sub-zero air quality conditions.

The project stems from the 2022 Alaskan Layered Pollution and Chemical Analysis project, or ALPACA, an international project funded by the National Science Foundation, the National Oceanic and Atmospheric Administration and European sources. It is part of an international air quality effort called Pollution in the Arctic: Climate Environment and Societies.

Read the full story in the University of Alaska Fairbanks newsroom.