GC026
Deep Learning for Climate Science and Weather Prediction

Session ID#: 157912

Session Description:
Deep learning is transforming many scientific and engineering disciplines due to a convergence of large volumes of data, scalable algorithms, and new computer architectures. In the earth and space sciences, deep learning has been used to accelerate the identification of exoplanets, track cyclones and atmospheric rivers, and predict volcanic eruptions. With hundreds of petabytes of climate data on the horizon, climate science and weather prediction stand to benefit from deep learning algorithms that can detect complex, non-linear patterns in the climate system that are difficult, even impossible, for humans to identify and interpret. This session encourages contributions that apply data-driven and deep learning approaches to climate science and weather prediction. Submissions are welcome that use deep learning to improve our understanding of models and observations, and enhance the predictability of extreme events, including life-threatening hazards such as floods and wildfires.
Index Terms:

0555 Neural networks, fuzzy logic, machine learning [COMPUTATIONAL GEOPHYSICS]
1610 Atmosphere [GLOBAL CHANGE]
1626 Global climate models [GLOBAL CHANGE]
1942 Machine learning [INFORMATICS]

Primary Convener:  Donald D Lucas, Lawrence Livermore National Laboratory, Livermore, CA, United States
Conveners:  Brian L White, University of North Carolina at Chapel Hill, Chapel Hill, NC, United States, Vipin Kumar, University of Minnesota Twin Cities, Department of Computer Science/Engineering, Minneapolis, MN, United States and Gemma Jayne Anderson, Lawrence Livermore National Laboratory, Livermore, United States
 
Defying Chaos Theory: Using Machine Learning to Extend Earth System Prediction (Invited) (1051137)
Maria J Molina1,2, Jadwiga Richter3, Anne Sasha Glanville1, Katherine Dagon4, Judith Berner4, Aixue Hu5 and Gerald Meehl4, (1)National Center for Atmospheric Research, Boulder, United States, (2)University of Maryland College Park, College Park, United States, (3)National Center for Atmospheric Research, Climate and Global Dynamics Laboratory, Boulder, CO, United States, (4)National Center for Atmospheric Research, Boulder, CO, United States, (5)NCAR, Boulder, United States
 
How To Have Our Cake And Eat It Too: Combining Geophysical Models With Machine Learning (Invited) (1059226)
Christopher G Fletcher1, William McNally2, John Virgin1 and Fraser King1, (1)University of Waterloo, Waterloo, ON, Canada, (2)University of Waterloo, Systems design engineering, Waterloo, ON, Canada
 
A Physics-Informed Machine Learning Model for Medium-Range Probabilistic Weather Forecasts (1067949)
Monica Bobra, Steven Joel Brey, Luke Conibear, Allison Early Reed Harris and Ashley Elizabeth Payne, Tomorrow.io, Boston, United States
 
An Interpretable Deep Learning Model for ENSO Forecasts: Implications for understanding ENSO Dynamics (1072355)
Shineng Hu1, Haoyu Wang2 and X. Li2, (1)Duke University, Division of Earth and Climate Sciences, Nicholas School of the Environment, Durham, NC, United States, (2)CAS Key Laboratory of Ocean Circulation and Waves, Institute of Oceanology, Chinese Academy of Sciences and Center for Ocean Mega-Science, Chinese Academy of Sciences, Qingdao, China
 
ClimFormer: building an attention-based climate emulator (1077034)
Peetak Mitra1, Salva Ruhling Cachay2, Soo Kyung Kim2, Subhashis Hazarika2, Kalai Ramea3, Dipti Swapnil Hingmire4, Haruki Hirasawa5, Phil Rasch6 and Hansi Alice Singh7, (1)Organization Not Listed, Washington, DC, United States, (2)PARC, Palo Alto, United States, (3)PARC, Palo Alto, CA, United States, (4)Indian Institute of Tropical Meteorology, Pune, Pune, India, (5)University of Toronto, Toronto, ON, Canada, (6)Pacific Northwest National Laboratory, Richland, United States, (7)University of Victoria, Victoria, Canada
 
ZOOMING-IN ON ANTARCTIC SURFACE MELT USING DEEP LEARNING (1086445)
Zhongyang Hu1, Peter Kuipers Munneke1, Yao Sun2, Stef Lhermitte3, Brice Noel4, Melchior van Wessem1, Lichao Mou2,5 and Xiao Xiang Zhu2,5, (1)Institute for Marine and Atmospheric Research Utrecht, Utrecht, Netherlands, (2)Data Science in Earth Observation, Technical University of Munich, Munich, Germany, (3)Delft University of Technology, Geoscience and Remote Sensing, Delft, Netherlands, (4)Utrecht University, Institute for Marine and Atmospheric Research Utrecht, Utrecht, Netherlands, (5)German Aerospace Center DLR Oberpfaffenhofen, Oberpfaffenhofen, Germany
 
Combining machine learning and SMILEs to classify, better understand, and project changes in ENSO events (1094302)
Nicola Maher1,2, Thibault P Tabarin3 and Sebastian Milinski2,4, (1)University of Colorado at Boulder, CIRES/ATOC, Boulder, United States, (2)Max Planck Institute for Meteorology, Hamburg, Germany, (3)Freelancer, Boulder, United States, (4)National Center for Atmospheric Research, Boulder, United States
 
Reducing Biases and Improving Resolution of General Circulation Models with Statistically Consistent Machine Learning (1102744)
Antoine Blanchard1, Nishant Parashar1, Boyko Dodov1, Christian Lessig2 and Themistoklis Sapsis3, (1)Verisk Analytics, Boston, United States, (2)Otto-von-Guericke Universität, Magdeburg, Germany, (3)Massachusetts Institute of Technology, Department of Mechanical Engineering, Cambridge, MA, United States
 
A Development of High-Resolution Long-Term Meteorological Grid Data Using Deep Learning over South Korea (1103085)
Minjin Park and Kyuhyun Byun, Incheon National University, Environmental Engineering, Incheon, South Korea
 
BeigNET & ToboGAN v1.0 : a Convolutional Neural Network and a Generative Adversarial Network for Cloud Coverage Nowcasting (1105608)
Jacques de Chevron Villette1, Pierre Aillaud2, Olivier Liandrat2, Mathieu Turpin2, Sébastien Marchal3, Nicolas Sebastien2 and Nicolas Schmutz2, (1)Reuniwatt, Sainte Clothilde, Reunion, (2)Reuniwatt, Sainte-Clotilde, Reunion, (3)Réuniwatt, Saint Pierre (Reunion island), Reunion
 
Zero-Shot Super-Resolution of Regional-Scale Surface Heat Simulation Using Fourier Neural Operator (1124234)
Peishi Jiang1, Zhao Yang2, Jiali Wang3, Chenfu Huang4, Pengfei Xue5, TC Chakraborty6, Xingyuan Chen1 and Yun Qian7, (1)Pacific Northwest National Laboratory, Richland, WA, United States, (2)Pacific Northwest National Lab, Richland, United States, (3)Argonne National Laboratory, Argonne, United States, (4)Michigan Technological University, Houghton, United States, (5)Michigan Technological University, Department of Civil, Environmental and Geospatial Engineering, Houghton, MI, United States, (6)Yale University, New Haven, United States, (7)Pacific Northwest National Laboratory, Richland, United States
 
Enhancing Deep Learning Bias Correction of Climate Extremes with Uncertainty Quantification (1127916)
Yannic Lops1, Gemma Jayne Anderson2 and Indrasis Chakraborty2, (1)Lawrence Livermore National Laboratory, Livermore, CA, United States, (2)Lawrence Livermore National Laboratory, Livermore, United States
 
Why are the data-driven digital twins for Earth long-term unstable? (1137985)
Ashesh Kumar Chattopadhyay1, Pedram Hassanzadeh2 and Ebrahim Nabizadeh2, (1)Rice University, Houston, TX, United States, (2)Rice University, Houston, United States
 
Development of marine heatwave prediction CNN model based on dynamic mechanisms (1140307)
Seonju Lee, Myung-Sook Park and MinHo Kwon, KIOST Korea Institute of Ocean Science and Technology, Busan, South Korea
 
Non-Linear Dimensionality Reduction with a Variational Encoder Decoder to Understand Convective Processes in Climate Models (1142078)
Gunnar Behrens1,2, Tom Beucler3, Pierre Gentine4,5, Fernando Iglesias-Suarez1, Mike S Pritchard6 and Veronika Eyring1,7, (1)German Aerospace Center DLR Oberpfaffenhofen, Institute of Atmospheric Physics, Oberpfaffenhofen, Germany, (2)Columbia University, Earth and Environmental Engineering, New York City, United States, (3)University of Lausanne, Institute of Earth Surface Dynamics, Lausanne, Switzerland, (4)Columbia University, Department of Earth and Environmental Engineering, New York, NY, United States, (5)Columbia University, Earth Institute, New York, United States, (6)University California Irvine, Earth System Science, Irvine, United States, (7)University of Bremen, Institute of Environmental Physics, Bremen, Germany
 
Global-scale unsupervised cloud classification to construct a novel AI-driven Cloud Classification Atlas (AICCA) (1155129)
Takuya Kurihana, University of Chicago, Computer Science, Chicago, IL, United States, Elisabeth J Moyer, University of Chicago, Department of the Geophysical Sciences, Center for Robust Decision-making on Climate and Energy Policy, Chicago, IL, United States, Ziwei Wang, University of Chicago, Geophysical Sciences, Chicago, IL, United States, James A Franke, University Of Chicago, Department of the Geophysical Sciences, Center for Robust Decision-making on Climate and Energy Policy, Chicago, United States, Tatsu Monkman, University of Chicago, Geophysical Sciences, Chicago, United States, Jacob Kuntzleman, Michigan Technological University, Physics, Houghton, United States, Adam Chaikin-Lifshitz, Weizmann Institute of Science, Earth and Planetary Sciences, Rehovot, Israel and Ian Foster, University of Chicago, Computer Science, Chicago, United States
 
ClimateBench: A benchmark for data-driven climate projections (1155858)
Duncan Watson-Parris1, Yuhan Rao2, Dirk Olivié3, Oyvind Seland3, Peer Johannes Nowack4, Gustau Camps-Valls5, Philip Stier6, Shahine Bouabid7, Maura Claire Dewey8, Emilie Fons9, Jessenia Gonzalez10, Paula Harder11, Kai Jeggle9, Julien Lenhardt10, Peter Manshausen1, Maria Novitasari12, Lucile Ricard13 and Carla Roesch14, (1)University of Oxford, Oxford, United Kingdom, (2)North Carolina State University, North Carolina Institute for Climate Studies, Asheville, United States, (3)Norwegian Meteorological Institute, Oslo, Norway, (4)University of East Anglia, School of Environmental Sciences, Norwich, United Kingdom, (5)Image Processing Laboratory, Universitat de València, Paterna, Spain, (6)University of Oxford, Department of Physics, Oxford, United Kingdom, (7)University of Oxford, Department of Statistics, Oxford, United Kingdom, (8)Stockholm University, Stockholm, Sweden, (9)ETH Zurich, Institute of Atmospheric and Climate Science, Zurich, Switzerland, (10)Universität Leipzig, Institute for Meteorology, Leipzig, Germany, (11)Fraunhofer Institute, Kaiserslautern, Germany, (12)University College London, Department of Electronic and Electrical Engineering, London, United Kingdom, (13)Ecole Polytechnique Fédérale de Lausanne, School of Architecture, Civil & Environmental Engineering, Lausanne, Switzerland, (14)University of Edinburgh, School of Geosciences, Edinburgh, United Kingdom
 
Multidimensional Approach for Temperature Forecasts in the US using Deep Learning (1159451)
Jahangir Ali, University of Arkansas, Fayetteville, AR, United States and Linyin Cheng, University of Arkansas at Fayetteville, Geosciences, Fayetteville, AR, United States
 
AtmoRep: Representation Learning for Spatio-Temporal Data in the Earth Sciences (1161894)
Christian Lessig, Otto-von-Guericke Universität, Magdeburg, Germany, Maike Sonnewald, Princeton University, Princeton, NJ, United States, Ilaria Luise, CERN, Geneve, Switzerland, Aneesh Subramanian, University of Colorado at Boulder, Department of Atmospheric and Oceanic Sciences, Boulder, United States and Martin Schultz, Foschungszentrum Juelich, Juelich, Germany
 
Physics-Constrained Deep Learning of Aerosol Microphysics (1165785)
Paula Harder1, Duncan Watson-Parris2, Philip Stier3, Dominik Strassel4, Nicolas R Gauger5 and Janis Keuper4, (1)Fraunhofer Institute, Kaiserslautern, Germany, (2)University of Oxford, Oxford, United Kingdom, (3)University of Oxford, Department of Physics, Oxford, United Kingdom, (4)Fraunhofer ITWM, Kaiserslautern, Germany, (5)University of Kaiserslautern, Kaiserslautern, Germany
 
Quantifying changes in global snowpack at high spatial resolutions under future warming scenarios via deep-learning models (1167762)
Andrew Bennett, University of Arizona, Department of Hydrology & Atmospheric Sciences, Tucson, AZ, United States and Oriana Chegwidden, CarbonPlan, San Francisco, United States
 
Empirical Mode Decomposition and Deep Long Short-Term Memory Neural Network Approach for Predicting Monsoon over Indian Homogenous Regions (1168390)
Yajnaseni Dash, Indian Institute of Technology Delhi, New Delhi, India and Saroj K. Mishra, Indian Institute of Technology Delhi, Centre for Atmospheric Sciences, New Delhi, India
 
Probabilistic Machine Learning of the Natural Variability of Climate (1181124)
Balu Nadiga, Los Alamos National Laboratory, Los Alamos, NM, United States
 
The Fire Index Risk Optimizer (FIRO) (1183906)
Campbell Watson, IBM Research USA, Yorktown Heights, NY, United States, Gabrielle Nyirjesy, Columbia University, New York, United States, Bianca Zadrozny, IBM Research, Rio de Janeiro, Brazil, Juan Nathaniel, Columbia University, Department of Earth and Environmental Engineering, New York, United States and Eduardo Rodrigues, IBM Research Brasil, Sao Paolo, Brazil
 
Towards Digital Twins for NVIDIA’s Earth-2 Initiative: Pushing the Limits of Deep Auto-regressive Fourier Neural Operator and Transformer models for Earth System Emulation (1187037)
Karthik Kashinath1, Mike S Pritchard1, Anima Anandkumar1, Jaideep Pathak1, Morteza Mardani1, Thorsten Kurth2, David Hall3, Peter Messmer1, Stan Posey1, Shashank Subramanian4, Peter Harrington4 and NVIDIA Earth-2 and collaborators, (1)NVIDIA Corporation, Santa Clara, United States, (2)NVIDIA Corporation, Zurich, Switzerland, (3)NVIDIA Corporation, Lafayette, United States, (4)Lawrence Berkeley National Laboratory, NERSC, Berkeley, United States
 
Deep Learning Methods for Storm Surge Forecasting (1188935)
Marie Li, Princeton University, Princeton, NJ, United States and Kyle T Mandli, Columbia University of New York, Applied Physics and Applied Mathematics, New York, NY, United States
 
Using Uncertainty-enhanced Deep Learning to Predict the Intensification of Tropical Depressions to Tropical Storms (1191264)
Ryan Lagerquist, Cooperative Institute for Research in the Atmosphere, Fort Collins, CO, United States and Jebb Stewart, NOAA Global Systems Laboratory, Boulder, United States
 
Machine Learning Methods may Reduce Uncertainty in Earth System Model Projections: A Case Study of Ocean Heat Uptake and AMOC Collapse (1194848)
Hansi Alice Singh1, Kalai Ramea2 and Dipti Hingmire1, (1)University of Victoria, School of Earth and Ocean Sciences, Victoria, BC, Canada, (2)PARC, Palo Alto, CA, United States
 
Transfer Learning on Convolutional Neural Network for Predicting the Northern Hemispheric Extreme Heatwaves (1194933)
Yuke Zhang1, Anh Nhat Nhu2, Valentina Castaneda Amaya3, Wencong Xie2 and Lei Wang4, (1)Purdue University, Mathematics / Computer Science, West Lafayette, United States, (2)Purdue University, West Lafayette, United States, (3)Purdue University, Department of Earth, Atmospheric, and Planetary Sciences, West Lafayette, United States, (4)Purdue University, Department of Earth, Atmospheric, and Planetary Sciences, West Lafayette, IN, United States
See more of: Global Environmental Change
<< Previous Session Proposal | Next Session Proposal >>