The deadline to submit a session, town hall, or pre-conference workshop proposal for AGU25 has passed. Please search for and review proposed sessions below. Please note this site is frozen as of 4/29/25 and will not reflect any changes to proposals made after this date.


Conveners will be contacted by the AGU25 Program Committee with any requests for mergers or edits to proposals. Conveners will be notified of the acceptance of their proposal in mid-June.


Abstract submissions will also open in mid-June and the deadline for abstract submissions is 30 July, 2025.


Please visit the AGU25 website for more information or please contact AGU with any questions.

Session Proposal: AI-Driven Innovations in Earth and Atmospheric Sciences (AGU25)

A021
AI-Driven Innovations in Earth and Atmospheric Sciences

Session ID#: 254648

Session Description:
Artificial Intelligence (AI), particularly machine learning and deep learning, is catalyzing transformative advances in Earth and Atmospheric Sciences. By harnessing vast datasets, AI offers innovative solutions that enhance our comprehension of complex processes. This session invites contributions exploring AI applications across atmospheric, terrestrial, riverine, oceanic, and Earth-related research domains. Topics may include: remote sensing, weather/air quality/sea-level forecasting, extreme events/natural hazards, super-resolution and downscaling, land use/land cover change, crop prediction, water quality/coastal water monitoring, and Earth system modeling. We also welcome strategies for integrating AI into education and research training, preparing students for data-intensive, interdisciplinary careers. Special emphasis will be placed on initiatives that expand access to AI tools and training, promote open science and responsible AI practices, and foster collaboration across research, education, and industry. By incorporating insights from diverse fields, we aim to broaden perspectives on AI-driven advancements in Earth and atmospheric sciences and their transformative impact on education.
Co-Sponsor(s):
  • ED - Education
  • GC - Global Environmental Change
  • NH - Natural Hazards
  • SY - Science and Society
Index Terms:

0555 Neural networks, fuzzy logic, machine learning [COMPUTATIONAL GEOPHYSICS]
1610 Atmosphere [GLOBAL CHANGE]
1622 Earth system modeling [GLOBAL CHANGE]
3315 Data assimilation [ATMOSPHERIC PROCESSES]
Primary Convener:  Jianfeng Li, Pacific Northwest National Laboratory, Richland, WA, United States
Conveners:  Samiah Moustafa, Bay Area Environmental Research Institute Moffett Field, Moffett Field, CA, United States, Dasa Gu, The Hong Kong University of Science and Technology, Division of Environment and Sustainability, Hong Kong, China, Ruben Delgado, Hampton University, Atmospheric and Planetary Sciences, Hampton, VA, United States, Guanyu Huang, Spelman College, Environmental and Health Sciences, Atlanta, United States, Yuzhong Zhang, Westlake University, Hangzhou, China and Aoxing Zhang, Southern University of Science and Technology, School of Environmental Science and Engineering, Shenzhen, China
Student/Early Career Convener:  Ziming Chen, Pacific Northwest National Laboratory, Richland, WA, United States
 
Long-term Spatial Estimates of Wet Deposition of Sulfate, Nitrate, and Ammonium over North America, Europe, and East Asia (1885814)
Mingyun Hu1, Xingcheng Lu2, Wanying Chen3 and Jimmy Chi-Hung Fung3, (1)Hong Kong University of Science and Technology, Mathematics, Hong Kong, Hong Kong, (2)Chinese University of Hong Kong, Department of Geography and Resource Management, Hong Kong, China, (3)Hong Kong University of Science and Technology, Hong Kong, Hong Kong
 
Machine Learning Enhances Projections of High-Latitude Land Warming (1888915)
Seoyeon Lee and Chang-Eui Park, KIST Korea Institute of Science and Technology, Center for Climate and Carbon Cycle Research, Seoul, South Korea
 
Exploring Steep Super-Resolution for Rapid Turbulent Flow Reconstruction (1903616)
Yeji Choi, DI Lab Inc., Seoul, South Korea, Sang-Hyun Lee, Kongju National University, Atmospheric Science, Gongju, South Korea and Sunju Lee, Kongju National University, Gongju, South Korea
 
Exploring the Spatiotemporal Variability of Leaf Area Index and Its Influence on Land Surface Temperature: A City-Scale Analysis in Hong Kong (1908387)
Xingcheng Lu, Chinese University of Hong Kong, Department of Geography and Resource Management, Hong Kong, China and Chaoran Zhang, The Chinese University of Hong Kong, Hong Kong, China
 
Spatial Filtering Fourier Neural Operator for Large-Eddy Prediction of Real Urban Turbulent Flows (1908419)
Hyeri Kim1, Sang-Hyun Lee1 and Yeji Choi2, (1)Kongju National University, Atmospheric Science, Gongju, South Korea, (2)DI Lab Inc., Seoul, South Korea
 
Emulating Smoke Transport Between Canada and NYC Using a Graph Neural Network (1912673)
Peyton Braun, Texas A&M University College Station, College Station, United States, Stuart M Evans, University at Buffalo, Department of Geography, Buffalo, NY, United States, Xudong Fan, University at Buffalo, Department of Civil, Structural, and Environmental Engineering, Buffalo, United States and Kang Sun, University at Buffalo, Department of Civil, Structural and Environmental Engineering, Buffalo, United States
 
AI-Enhanced Forward Modeling of Microwave Radiative Transfer (1915604)
Frederike Monte1, Steven Businger1, Paolo Antonelli2 and Katerina Giamalaki1, (1)University of Hawaii at Manoa, Atmospheric Sciences, Honolulu, United States, (2)AdaptiveMeteo, Rome, Italy
 
Geophysical Retrievals in an Artificial Intelligence (AI) Framework (1917051)
Virendra P Ghate1, Nesar Ramchandra2, Michael Buehlmann2, Azton Wells2 and Salman Habib2, (1)Argonne National Laboratory, Argonne, IL, United States, (2)Argonne National Laboratory, Argonne, United States
 
Enhancing Satellite Imagery Resolution for Coastal and Ocean Engineering Applications Using Sub-pixel Convolutional Neural Networks and PixelShuffle Techniques (1922377)
Aran Dezhban and Paul Mario Koola, Ocean Engineering Department, Texas A&M University, Galveston, United States
 
A Hypertemporal Geostationary Satellite-Based Cloud Mask Dataset for Semantic Segmentation (Invited) (1928531)
Kyle Kristian Kabasares1,2, Weile Wang3, Taejin Park4, Ian G Brosnan5, Pratima K C1 and Pratima Khatri-Chhetri, (1)Bay Area Environmental Research Institute, Moffett Field, United States, (2)NASA Ames Research Center, Earth Science Division, Moffett Field, United States, (3)NASA/AMES Research Center, Moffett Field, United States, (4)NASA Ames Research Center/Bay Area Environmental Research Institute, Moffett Field, United States, (5)NASA Ames Research Center, Earth Science Division, Moffett Field, CA, United States
 
Hierarchical Testing of a Hybrid Machine Learning-Physics Model (1934859)
L. Ruby Leung1, Ziming Chen1, Wenyu Zhou2, Jian Lu3, Sandro W. Lubis4, Ye Liu1, Chuan-Chieh Chang1, Bryce E Harrop5, Ya Wang6, Gan Zhang7 and Yun Qian1, (1)Pacific Northwest National Laboratory, Richland, WA, United States, (2)Pacific Northwest National Laboratory, Richland, United States, (3)Ocean University of China, Qingdao, China, (4)PNNL, Richland, United States, (5)Pacific Northwest National Laboratory, Atmospheric, Climate, and Earth Sciences Division, Richland, WA, United States, (6)Institute of Atmospheric Physics, Chinese Academy of Sciences, Beijing, China, (7)University of Illinois, Urbana, United States
 
Machine Learning Downscaling of Global AI Forecasts for Near-Surface Wind Prediction (1938163)
Mingshi Yang, University of Illinois at Urbana-Champaign, Department of Atmospheric Sciences, Urbana, United States
 
Advancing Urban Climate Science with Modeling, Sensing and AI/ML (Invited) (1942648)
Lei Zhao, University of Illinois at Urbana Champaign, Civil and Environmental Engineering, Urbana, IL, United States
 
Can a Single Sounding Predict the Weather? An AI Downscaling Framework for Local-Circulation-Dominated Flow over Complex Topography (1944471)
Fucent Hsuan Wei Hsu, Min-Ken Hsieh and Chien-ming Wu, National Taiwan University, Department of Atmospheric Sciences, Taipei, Taiwan
 
AI Innovation for NOAA Earth System Science (1950055)
Annarita Mariotti, NOAA, Climate program Office, Silver Spring, United States and Clara Deck, University Corporation for Atmospheric Research (UCAR), Cooperative Programs for the Advancement of Earth System Science (CPAESS), Silver Spring, United States
 
The Adaptability of Deep-Learned Observation Operators (1951742)
Kelsey Lieberman1, Matt Bender1, Mohammad Ridhwaan Alam2, Nick Krall1, Chris Miller3, Nick Silverman4, Noah Brenowitz5, Laura Slivinski6, Sergey Frolov6 and Joshua DaRosa1, (1)The MITRE Corporation, McLean, United States, (2)The MITRE Corporation, San Diego, United States, (3)MITRE Corporation, McLean, United States, (4)The MITRE Corporation, Missoula, United States, (5)NVIDIA Corporation, Santa Clara, CA, United States, (6)NOAA/PSL, Boulder, United States
 
When can we use explainable Artificial Intelligence tools to generate physical insight about the Earth system? (1956772)
Antonios Mamalakis, University of Virginia, Department of Environmental Sciences; School of Data Science, Charlottesville, United States, Will Chapman, NSF National Center for Atmospheric Research, Boulder, CO, United States and Dr. Kirsten J Mayer, PhD, University of Wisconsin Madison, Department of Atmospheric and Oceanic Sciences, Madison, WI, United States
 
UNet-based methods for identifying Chicago lake breeze fronts from NEXRAD (1960361)
Robert Clyde Jackson1, Seongha Park1, Bhupendra Raut2, Scott M Collis3, Troy Arcomano4,5, Joseph Robert O'Brien1, Matthew Tuftedal6, Maxwell Grover1, Paytsar Muradyan3, Elizabeth Wawrzyniak6, Rajesh Sankaran1, Nicola Ferrier7, Dario Dematties8, Gregory Anderson9, Sean Shahkarami8 and Yongho Kim6, (1)Argonne National Laboratory, Argonne, IL, United States, (2)Argonne National Laboratory, Lemont, United States, (3)Argonne National Laboratory, Lemont, IL, United States, (4)Texas A&M University, College Station, United States, (5)Allen AI Institute, Seattle, United States, (6)Argonne National Laboratory, Argonne, United States, (7)Argonne National Laboratory, Mathematics and Computer Science, Lemont, United States, (8)Northwestern University, Evanston, United States, (9)Northeastern Illinois University, Department of Physics, Chicago, United States
 
Retrieval of Cloud Properties for the Copernicus Atmospheric Missions Sentinel-4 and TROPOMI / Sentinel-5 Precursor using deep neural networks (1963337)
Fabian Romahn1, Diego G Loyola1, Ronny Lutz1, Víctor Molina García1,2, Adrian Doicu3 and Athina Argyrouli4, (1)German Aerospace Center (DLR), Remote Sensing Technology Institute (IMF), Oberpfaffenhofen, Germany, (2)Santa Barbara, CA, United States, (3)German Aerospace Center DLR Oberpfaffenhofen, Oberpfaffenhofen, Germany, (4)Technical University of Munich (TUM), School of Engineering and Design, Chair of Remote Sensing Technology, Munich, Germany
 
OceanAI: A Conversational Agent for Accurate, Transparent, Near-Real‑Time Oceanographic Insights (1969036)
Bowen Chen, North Carolina State University Raleigh, Raleigh, nc, UNITED STATES, Ruoying He, North Carolina State University, Marine, Earth, and Atmospheric Sciences, Raleigh, United States; Fathom Science LLC, Raleigh, United States, Paul Liu, North Carolina State University Raleigh, Marine, Earth and Atmospheric Science, Raleigh, United States, Dongkuan Xu, North Carolina State University Raleigh, Raleigh, United States, Greg Dusek, NOAA Camp Springs, Camp Springs, United States, Robert J Redmon, NOAA National Centers for Environmental Information, Boulder, United States and Patrick Hogan, NOAA/NESDIS/NCEI-MS, Stennis Space Center, United States
 
Creating and Assessing an Unconventional Global Database of Dust Storms Utilizing Generative AI (1974383)
Andrew T. Crooks1, Sage Keidel2 and Stuart M Evans1, (1)University at Buffalo, Department of Geography, Buffalo, NY, United States, (2)University at Albany, Department of Atmospheric and Environmental Sciences, Albany, United States
 
Promises and Limitations of AI Weather Models: From Democratizing Forecasting to Forecasting Gray Swans (Invited) (1976887)
Pedram Hassanzadeh, University of Chicago, Department of the Geophysical Sciences, Chicago, United States
 
Bridging Monitoring Gaps: Multi-Task Learning Enhances High-Resolution Surface-Level O3, NO2, and NO Estimation (1978749)
Zhongying Wang1, James Crooks2, Elizabeth Regan2 and Morteza Karimzadeh1, (1)University of Colorado Boulder, Department of Geography, Boulder, United States, (2)National Jewish Health, Denver, United States
 
Understanding Ice Crystal Habit Diversity with Self-Supervised Learning (1984538)
Joseph Ko1, Hariprasath Govindarajan2, Fredrik Lindsten2, Marcus van Lier Walqui3 and Kara Lamb4, (1)Columbia University, Climate School, New York, United States, (2)Linköping University, Computer and Information Science, Linköping, Sweden, (3)Columbia University, Center for Climate Systems Research, New York, United States, (4)Columbia University, Earth and Environmental Engineering, New York, United States
 
Evaluation of Spaceborne Lidar Estimates of Backscatter and Depolarization Ratio Using Machine Learning Denoising Methods (1984864)
Amanda Cresanti1, John E Yorks2, Patrick A Selmer3, Kenneth Edward Christian2, Natalia Roldan-Henao4, Natalie Midzak5 and Zhanqing Li6, (1)University of Maryland College Park, College Park, MD, United States, (2)NASA Goddard Space Flight Center, Greenbelt, United States, (3)SSAI/NASA GSFC, Greenbelt, United States, (4)University of Maryland College Park, College Park, United States, (5)NASA NPP, Greenbelt, United States, (6)University of Maryland, Department of Atmospheric and Oceanic Science, Earth System Science Interdisciplinary, College Park, United States
 
Enhancing Small Satellite Imagery with Hybrid Super-Resolution (1992905)
Vincenzo Della Corte, INAF, Oss. Astr. Capodimonte (OACN), Napoli, Italy, Camilla De Martino, Univ. Parthenope, Dept. Sciences and Technologies, Napoli, Italy, Laura Inno, Parthenope University of Naples, Naples, Italy, Fabio Cozzolino, INAF - OACN Astronomical Observatory of Capodimonte, Naples, Italy, Vania Da Deppo, CNR-IFN Padova, Padova, Italy, Sara Venafra, University of Basilicata, School of Engineering, Potenza, Italy, Giacomo Ruggiero, INAF, Oss.Astron. Capodimonte, Napoli, Italy, Paola Zuppella, CNR-IFN, Padova, Italy and Lama Moualla, CNR-IFN, PAdova, Italy
 
BenchFlux: Scalable AI Benchmarks for Terrestrial Carbon Fluxes to Advance Research, Education, and Resource Management (1997681)
Stefan Metzger1, Maoya Bassiouni2, Samuel Bower1, Ankur R Desai3, Matthew Fortier4, Sophie Hoffman5, Yanghui Kang6, Trevor Keenan2, Danielle Losos7, Alvaro Moreno8, Christopher Pal9, Sadegh Ranjbar, PhD Candidate10, Oliver Sonnentag11, Paul C Stoy12, Emma Izquierdo13 and Jingfeng Xiao14, (1)AtmoFacts, Longmont, United States, (2)University of California, Berkeley, Department of Environmental Science, Policy, and Management, Berkeley, United States, (3)University of Wisconsin Madison, Atmospheric and Oceanic Sciences, Madison, United States, (4)Mila - Quebec Artificial Intelligence Institute, Montreal, Canada, (5)University of Wisconsin Madison, Biological System Engineering, Madison, United States, (6)Virginia Tech, Department of Biological Systems Engineering, Blacksburg, Virginia, United States, (7)Yale University, New Haven, United States, (8)Image Processing Laboratory, Universitat de València, Paterna, Spain, (9)Ecole Polytechnique de Montreal, Computer Engineering and Software Engineering, Montreal, Canada, (10)University of Wisconsin Madison, Biological Systems Engineering, Madison, WI, United States, (11)University of Montreal, Département de Géographie, Montreal, QC, Canada, (12)University of Wisconsin-Madison, Madison, Biological Systems Engineering, Madison, United States, (13)BOKU University, Institute of Geomatics, Vienna, Austria, (14)University of New Hampshire, Institute for the Study of Earth, Oceans, and Space, Earth Systems Research Center, Durham, United States
 
ORBIT-2: Scaling Exascale Vision FoundationModels for Weather and Climate Downscaling (1847651)
Xiao Wang1, Dan Lu2, Prasanna Balaprakash1, Moetasim Ashfaq3, Dali Wang4, Peter E Thornton5, Ming Fan6, Jong Youl Choi2, Takuya Kurihana7, Isaac Lyngaas2, Hong-Jun Yoon8, Aristeidis Tsaris2, Mohamed Wahib9, Nasik Muhammad Nafi2, Ashwin Aji10, Maliha Hossain2 and Xi Xiao11, (1)Oak Ridge National Laboratory, Oak Ridge, TN, United States, (2)Oak Ridge National Laboratory, Oak Ridge, United States, (3)Oak Ridge National Laboratory, Computational Sciences and Engineering Divison, Oak Ridge, TN, United States, (4)Oak Ridge National Laboratory, Climate Change Science Institute and Environmental Sciences Division, Oak Ridge, TN, United States, (5)Oak Ridge National Laboratory, Environmental Sciences Division, Oak Ridge, United States, (6)Virginia Polytechnic Institute and State University, Blacksburg, United States, (7)University of Chicago, Computer Science, Chicago, United States, (8)Oak Ridge National Laboratory, Computational Sciences and Engineering Division, Oak Ridge, United States, (9)RIKEN Advanced Institute for Computational Sciences, Kobe, Japan, (10)Advanced Micro Devices, Fremont, United States, (11)University of Alabama at Birmingham, Birmingham, United States
 
Physics-Guided Discriminator Generative Models for Fast and Physically Consistent Reconstruction of Sparse Scatterometer Ocean Surface Winds (1854385)
Ran Bo1, Zeming Zhou1, Huadong Du2, Pinglv Yang1, Xiaofeng Zhao1, Qian Li1 and Zengliang Zang1, (1)National University of Defense Technology, College of Meteorology and Oceanography, Changsha, China, (2)National University of Defense Technology, College of Advanced Interdisciplinary Studies, Nanjing, China
 
Unexpectedly Strong Landscape Interconnections Captured by Earth Foundation AI for Land (Invited) (1861526)
Chaopeng Shen, Pennsylvania State University Main Campus, Department of Civil and Environmental Engineering, University Park, United States, Jiangtao Liu, Pennsylvania State University, Department of Civil and Environmental Engineering, University Park, United States, Nicholas Rigdeway Kraabel, Washington State University, School of Electrical Engineering & Computer Science, Pullman, United States, Chonggang Xu, Los Alamos National Lab, Los Alamos, United States and Marc McDill, Pennsylvania State University Main Campus, Department of Ecosystem Science and Management, University Park, United States
 
Deep Learning for Clouds, Cloud Shadow, and Plume Segmentation in Methane Satellite and Airborne Imaging Spectroscopy (1862562)
Maya Nasr1, Manuel Pérez-Carrasco2, Sébastien Roche3, Christopher Chan Miller3, Dr. Zhan Zhang, PhD1, Javier Roger4, Core Francisco Park5, Eleanor Walker6, Cecilia Garraffo7, Douglas Finkbeiner5, Daniel J. Varon8, Kang Sun7, Jonathan E Franklin5, Ritesh Gautam1, Steven C Wofsy5 and Manuel Pérez-Carrasco, (1)Environmental Defense Fund, New York, United States, (2)Center for Data and AI, Universidad de Concepción, Concepción, Chile, (3)Environmental Defense Fund, Harvard University, Cambridge, United States, (4)Research Institute of Water and Environmental Engineering (IIAMA), Universitat Politècnica de València, Valencia, Spain, (5)Harvard University, Cambridge, United States, (6)Stanford University, Earth Systems Science, Stanford, United States, (7)Harvard-Smithsonian Center for Astrophysics, Cambridge, United States, (8)Harvard University, School of Engineering and Applied Sciences, Cambridge, United States
See more of: Atmospheric Sciences
<< Previous Session Proposal | Next Session Proposal >>