{"689861":{"#nid":"689861","#data":{"type":"event","title":"MS Defense by Rameen Gauher","body":[{"value":"\u003Cdiv\u003ECandidate: Rameen Gauher\u003C\/div\u003E\u003Cdiv\u003EDegree: Master of Science, College of Computing\u003C\/div\u003E\u003Cdiv\u003EAdvisor: Dr. Josiah Hester\u003C\/div\u003E\u003Cdiv\u003E\u0026nbsp;\u003C\/div\u003E\u003Cdiv\u003ETitle: Physics-Informed Deep Learning Emulator for Predicting Hurricane-Driven Compound Flooding\u003C\/div\u003E\u003Cdiv\u003E\u0026nbsp;\u003C\/div\u003E\u003Cdiv\u003EDate: Tuesday, April 21, 2026\u003C\/div\u003E\u003Cdiv\u003ETime: 10:00 AM \u2013 11:00 AM\u003C\/div\u003E\u003Cdiv\u003E\u0026nbsp;\u003C\/div\u003E\u003Cdiv\u003EThesis Committee:\u003C\/div\u003E\u003Cdiv\u003E\u2022 Dr. Josiah Hester (Advisor) \u2013 College of Computing, Georgia Institute of Technology\u003C\/div\u003E\u003Cdiv\u003E\u2022 Dr. Ali Sarhadi \u2013 School of Earth and Atmospheric Sciences, Georgia Institute of Technology\u003C\/div\u003E\u003Cdiv\u003E\u2022 Dr. Peng Chen \u2013 School of Computational Science and Engineering, Georgia Institute of Technology\u003C\/div\u003E\u003Cdiv\u003E\u0026nbsp;\u003C\/div\u003E\u003Cdiv\u003EAbstract:\u003C\/div\u003E\u003Cdiv\u003EThis thesis presents a Transformer\u2013Fourier Neural Operator (Trans+FNO) architecture for predicting hurricane-driven compound flooding over the New York City metropolitan area. Compound flooding, the simultaneous interaction of storm surge and heavy rainfall, poses a growing threat to coastal communities under climate change. Physics-based hydrodynamic models can simulate compound flooding at high resolution but require hours of computation per event, making them impractical for ensemble-based probabilistic forecasting. Our deep learning emulator maps variable-length hurricane track sequences to three-channel spatially resolved flood depth fields at 1024\u00d71024 resolution, trained on 13,013 samples from a physics-based simulation framework spanning seven climate model realizations. The model achieves 97%+ wet\/dry classification accuracy and sub-0.1 m RMSE. We demonstrate ensemble-based flood uncertainty quantification using ECMWF forecasts and provide SHAP-based interpretability analysis revealing physically consistent feature importance hierarchies across compound, surge, and rainfall flooding.\u003C\/div\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EPhysics-Informed Deep Learning Emulator for Predicting Hurricane-Driven Compound Flooding\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":" Physics-Informed Deep Learning Emulator for Predicting Hurricane-Driven Compound Flooding"}],"uid":"27707","created_gmt":"2026-04-19 04:18:42","changed_gmt":"2026-04-19 04:19:30","author":"Tatianna Richardson","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2026-04-21T10:00:11-04:00","event_time_end":"2026-04-21T11:00:11-04:00","event_time_end_last":"2026-04-21T11:00:11-04:00","gmt_time_start":"2026-04-21 14:00:11","gmt_time_end":"2026-04-21 15:00:11","gmt_time_end_last":"2026-04-21 15:00:11","rrule":null,"timezone":"America\/New_York"},"location":"TBD","extras":[],"groups":[{"id":"221981","name":"Graduate Studies"}],"categories":[],"keywords":[{"id":"111531","name":"ms 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":""}}}