{"681385":{"#nid":"681385","#data":{"type":"event","title":"PhD Defense by Snigdaa Sethuram ","body":[{"value":"\u003Cp\u003ESchool of Physics Thesis Dissertation Defense\u003C\/p\u003E\u003Cp\u003ESnigdaa Sethuram\u0026nbsp;\u003Cbr\u003EAdvisor: \u0026nbsp;Dr. John Wise, School of Physics, Georgia Institute of Technology\u003C\/p\u003E\u003Cp\u003EMachine Learning Techniques to Accelerate Simulations, Modeling, and Analysis\u003Cbr\u003EFriday, March 28, 2025 \u0026nbsp;\u003Cbr\u003E2:00 p.m.\u0026nbsp;\u003Cbr\u003EGilbert Hillhouse Boggs Building, Room 1-44 (Visualization Laboratory)\u003Cbr\u003EZoom link\u003C\/p\u003E\u003Cp\u003ECommittee Members: \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u0026nbsp;\u003Cbr\u003EDr. Tamara Bogdanovic, School of Physics, Georgia Institute of Technology\u003Cbr\u003EDr. Gongjie Li, School of Physics, Georgia Institute of Technology\u003Cbr\u003EDr. Annalisa Bracco, School of Earth \u0026amp; Atmospheric Sciences, Georgia Institute of Technology\u003Cbr\u003EDr. Viviana Acquaviva, Department of Physics, CUNY NYC College of Technology\u003C\/p\u003E\u003Cp\u003EAbstract:\u003Cbr\u003EComputational methods in astrophysics are essential to better understanding our universe and validating theoretical models but achieving high-resolution simulations with complex physics remains computationally intensive. Machine learning (ML) methods have proven to be a valuable tool to mitigate these challenges and enable accelerated simulation runtime and analysis. In this work, data-driven approaches to traditional tasks are explored: (1) a neural network emulator that generates synthetic observations of simulated galaxies given global data, bypassing traditional radiative transfer, (2) a Bayesian framework employing Markov Chain Monte Carlo sampling to infer galaxy properties from JWST photometric observations, and (3) a convolutional recurrent network trained on spatiotemporal hydrodynamic data to emulate stellar feedback in cosmological simulations. These approaches integrate ML and statistical analysis methods with physical models to optimize parameter space exploration, reduce computational costs, and bridge simulations with observational data.\u003Cbr\u003E\u0026nbsp;\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003E\u003Cstrong\u003EMachine Learning Techniques to Accelerate Simulations, Modeling, and Analysis\u003C\/strong\u003E\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Machine Learning Techniques to Accelerate Simulations, Modeling, and Analysis"}],"uid":"27707","created_gmt":"2025-03-26 18:33:39","changed_gmt":"2025-03-26 18:34:11","author":"Tatianna Richardson","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2025-03-28T14:00:00-04:00","event_time_end":"2025-03-28T16:00:00-04:00","event_time_end_last":"2025-03-28T16:00:00-04:00","gmt_time_start":"2025-03-28 18:00:00","gmt_time_end":"2025-03-28 20:00:00","gmt_time_end_last":"2025-03-28 20:00:00","rrule":null,"timezone":"America\/New_York"},"location":"Gilbert Hillhouse Boggs Building, Room 1-44 (Visualization Laboratory) Zoom link","extras":[],"groups":[{"id":"221981","name":"Graduate Studies"}],"categories":[],"keywords":[{"id":"100811","name":"Phd Defense"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1788","name":"Other\/Miscellaneous"}],"invited_audience":[{"id":"78771","name":"Public"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}