GC015
Advancing Climate Science with Deep Learning
Session ID#: 248780
Session Description:
Cutting-edge deep learning methods are revolutionizing climate and Earth system science. Emerging techniques such as diffusion models, normalizing flows, variational autoencoders, long short-term memory networks, and vision transformers, are unlocking new possibilities for understanding and predicting complex environmental phenomena. Presentations will highlight applications of these methods to critical climate challenges, including modeling extreme floods, tracking wildfire progression, and detecting drought patterns with unprecedented precision. By leveraging the power of advanced neural network architectures and generative AI methods, researchers are pushing the boundaries of predictive accuracy, spatial resolution, and temporal insights in climate science. The session will foster interdisciplinary collaboration, showcasing how deep learning is transforming traditional approaches to data analysis and simulation. Attendees will gain insights into the latest advancements and learn how these tools can be applied to improve climate resilience and decision-making in the face of growing environmental challenges.
Co-Sponsor(s):
Index Terms:
0555 Neural networks, fuzzy logic, machine learning [COMPUTATIONAL GEOPHYSICS]
1622 Earth system modeling [GLOBAL CHANGE]
1942 Machine learning [INFORMATICS]
3305 Climate change and variability [ATMOSPHERIC PROCESSES]
Primary Convener: Donald D Lucas, Lawrence Livermore National Laboratory, Livermore, CA, United States
Conveners: Gemma Jayne Anderson, Lawrence Livermore National Laboratory, Livermore, CA, United States, Vipin Kumar, University of Minnesota Twin Cities, Department of Computer Science & Engineering, Minneapolis, United States and Duncan Watson-Parris, University of California San Diego, La Jolla, CA, United States
Generative Lagrangian Data Assimilation for Ocean Dynamics Under Extreme Sparsity. (1866082)
Niloofar Asefi, Organization Not Listed, Washington, DC, United States, Leonard Lupin-Jiminez, University of California, Santa Cruz, Applied Mathematics, Santa Cruz, United States, Tianning Wu, North Carolina State University, Dept. of Marine, Earth, and Atmospheric Sciences, Raleigh, United States, Ruoying He, North Carolina State University, Marine, Earth, and Atmospheric Sciences, Raleigh, United States and Ashesh Kumar Chattopadhyay, University of California Santa Cruz, Santa Cruz, United States
Surface temperature extremes produced by huge emulator-based ensembles of summer hindcasts (1881830)
William Drew Collins1, Mark Daniel Risser2, Ankur Mahesh3 and Joshua North1, (1)Lawrence Berkeley National Laboratory, Earth and Environmental Science, Berkeley, CA, United States, (2)Lawrence Berkeley National Laboratory, Earth and Environmental Sciences Area, Berkeley, CA, United States, (3)University of California Berkeley, Berkeley, United States
Generative Deep Learning to Correct Weather Models with Station Observations (1901801)
Donald D Lucas1, Gemma Jayne Anderson1, Charles Jones2 and Callum Thompson3, (1)Lawrence Livermore National Laboratory, Livermore, CA, United States, (2)University of California, Santa Barbara, Department of Geography, Santa Barbara, United States, (3)University of California, Santa Barbara, Santa Barbara, United States
Teaching AI weather models to forecast gray swan extreme events via rare-event sampling and active learning (Invited) (1927458)
Pedram Hassanzadeh, The University of Chicago, Department of the Geophysical Sciences, Chicago, United States, Amaury Lancelin, École Normale Supérieure, LMD, Paris, France, Alexander Wikner, University of Chicago, Chicago, United States, Dorian S Abbot, University of Chicago, Geophysical Sciences, Chicago, United States, Jonathan Weare, New York University, Courant Institute of Mathematical Sciences, New York, United States, Freddy Bouchet, LMD, IPSL, Paris, France, Laurent Dubus, RTE, Paris, France, Willow Stenglein, University of Texas at Austin, Austin, United States and Y Qiang Sun, UChicago, Chicago, United States
Data-Driven Modeling of AMOC Variability in CMIP6 Simulations (1931459)
Balu T Nadiga1, Guang Zhao2, Zhengyu Liu3, Luke P Van Roekel4, Wei Xu2 and Seungjun Lee2, (1)Los Alamos National Laboratory, Los Alamos, NM, United States, (2)Brookhaven National Laboratory, Upton, United States, (3)The Ohio State University, Department of Geography, Columbus, United States, (4)Los Alamos National Laboratory, Los Alamos, United States
AI-based climate model evaluation through the lens of pseudo-global warming storylines (1937243)
Shiheng Duan1, Jishi Zhang2, Celine Bonfils1, Giuliana Pallotta1 and Paul Ullrich2, (1)Lawrence Livermore National Laboratory, Livermore, CA, United States, (2)Lawrence Livermore National Laboratory, Livermore, United States
Generate the Forest before the Trees--A Hierarchical Diffusion model for Climate Downscaling (1946034)
Declan Curran1, Sanaa Hobeichi2, Hira Saleem1, Flora Salim3 and Hao Xue4, (1)University of New South Wales, Sydney, NSW, Australia, (2)University of New South Wales, Sydney, Australia, (3)University of New South Wales, Computer Science, Sydney, Australia, (4)UNSW, Sydney, Australia
WaveSim: A Multi-Scale Wavelet-Based Similarity Metric for Climate Field Comparison (1950455)
Dr. Gabriele Accarino, PhD, Columbia University, New York, United States, Viviana Acquaviva, CUNY New York City College of Technology, Brooklyn, United States, Sara Shamekh, New York University, Center for Atmosphere Ocean Science, Courant Institute of Mathematical Sciences, New York, United States and Duncan Watson-Parris, University of Oxford, Oxford, United Kingdom
Node-Adaptive Graph Neural Networks for Enhanced Prediction of Localized Wildfire Dynamics (1963197)
Junde Chen1, Dr. Wenzhao Li2, Rejoice Thomas1 and Hesham Mohamed El-Askary2, (1)Chapman University, Schmid College of Science and Technology, Orange, United States, (2)Chapman University, Schmid College of Science and Technology, Orange, CA, United States
Domain-Adaptive Geometry-Informed Neural Operators for Rapid Flood Forecasting (1964679)
Mehdi Taghizadeh1, Zanko Zandsalimi1, Mohammad Amin Nabian2, Jonathan L Goodall1 and Negin Alemazkoor1, (1)University of Virginia, Department of Civil and Environmental Engineering, Charlottesville, VA, United States, (2)NVIDIA, Santa Clara, United States
Discovery and Forecasting Critical Climate Thresholds for Early Warning Systems (1968106)
Jennifer A. Sleeman1, Dr. Genevieve Jay Brett, PhD2, Caroline Tang1, Jenelle Millison3, Adeline Hillier3, Alex Chen4, Jenny Boothby3, Mary Ruth Keller1, Anand Gnanadesikan5 and Caitlin Amos3, (1)Johns Hopkins University Applied Physics Laboratory, Laurel, MD, United States, (2)Woods Hole Oceanographic Institution, Cambridge, United States, (3)Johns Hopkins University Applied Physics Laboratory, Laurel, United States, (4)Johns Hopkins Applied Physics Laboratory, Laurel, United States, (5)Johns Hopkins University, Earth & Planetary Sciences, Baltimore, MD, United States
Simulating CERES Longwave Radiative Fluxes Using Machine Learning with AIRS and CrIS Hyperspectral Infrared Observations (1977107)
Robert C Wilson, NASA Jet Propulsion Laboratory, Pasadena, CA, United States, Maria Zita Hakuba, Jet Propulsion Laboratory, Caltech, Pasadena, United States, Joao Teixeira, Jet Propulsion Laboratory, California Institute of Technology, Pasadena, United States and Matthew D Lebsock, Jet Propulsion Laboratory, Pasadena, United States
Diffusion-based downscaling of precipitation extremes highlights potential impacts of future climate scenarios with and without stratospheric aerosol injection (1987964)
Cameron Dong1, Elizabeth Barnes1,2 and James Hurrell1, (1)Colorado State University, Atmospheric Science, Fort Collins, United States, (2)Boston University, Computing and Data Sciences, Earth and Environment, Boston, United States
Generation of High-Resolution Precipitation Data using Unsupervised Domain Adaptation Technique, a Deep Learning Based Approach (1989646)
Naman Rajouria, Indian Institiute of Science Education and Research Bhopal, Earth and Environmental Science, Bhopal, India, Tanishq Sharma, Indian Institute of Science Education and Research Bhopal, Data Science and Engineering, Bhopal, India, Sanjeev Jha, Indian Institute of Science Education and Research Bhopal, Earth and Environmental Sciences, Bhopal, India and Akshay Agarwal Dr., Indian Institiute of Science Education and Research Bhopal, Data Science and Engineering, Bhopal, India
AIMIP Phase 1: An intercomparison of AI climate models (1990353)
Brian M Henn, Oliver Watt-Meyer, Spencer Clark, Jeremy McGibbon, Troy Arcomano, Elynn Wu, James Duncan, W. Andre Perkins, Anna Kwa and Christopher Stephen Bretherton, Allen Institute for AI, Seattle, United States
Physically-Constrained Deep Generative Modeling (1992938)
Matthieu Blanke, New York University, New York, NY, United States, Yongquan Qu, Columbia University of New York, New York, United States, Sara Shamekh, New York University, Center for Atmosphere Ocean Science, Courant Institute of Mathematical Sciences, New York, United States and Pierre Gentine, Columbia University, Department of Earth and Environmental Engineering, New York, United States
