GC014
Climate Science in the Age of Deep Learning and Machine Learning
Session ID#: 75997
Session Description:
Deep learning is transforming many scientific and engineering disciplines: a result of a convergence of large volumes of data, scalable algorithms and new computer architectures. In many areas of earth and space sciences, deep learning has accelerated advancements in identifying galactic structures, improving the representation of atmospheric turbulence, predicting volcanic eruptions, and many more. With hundreds of petabytes of climate data on the horizon, climate science stands to benefit from deep learning approaches that can aid in analyzing non-linear, complex patterns in the climate system that can be difficult, even impossible, for humans to identify and interpret. We seek contributions that apply deep learning or machine learning to climate models and observations to make forecasts; improve our understanding of various aspects of the climate system; or to improve upon state of the art techniques or results, including hybrid learning approaches.
Co-Organized:
Index Terms:
0555 Neural networks, fuzzy logic, machine learning [COMPUTATIONAL GEOPHYSICS]
1626 Global climate models [GLOBAL CHANGE]
1942 Machine learning [INFORMATICS]
Primary Convener: Donald D Lucas, Lawrence Livermore National Laboratory, Livermore, CA, United States
Conveners: Steve M Easterbrook, University of Toronto, Toronto, ON, Canada, Gemma Jayne Anderson, Lawrence Livermore National Laboratory, Livermore, CA, United States and Vipin Kumar, University of Minnesota Twin Cities, Minneapolis, MN, United States
Primary Liaison: Donald D Lucas, LLNL, Livermore, CA, United States
Arctic sea ice forecasts at weather time-scales with Convolutional Long-Short Term Memory Networks (503342)
Yang Liu1,2, Jisk Attema1 and Wilco Hazeleger3, (1)Netherlands eScience Center, Amsterdam, Netherlands, (2)Wageningen University and Research Center, Meteorology and Air Quality Group, Wageningen, Netherlands, (3)Utrecht University, Utrecht, Netherlands
Inter-seasonal snowpack prediction with deep convolutional neural networks (543603)
Andre Goncalves, Lawrence Livermore National Laboratory, Computer Engineering Directorate, Livermore, CA, United States, Gemma Jayne Anderson, Lawrence Livermore National Laboratory, Livermore, CA, United States, Donald D Lucas, LLNL, Livermore, CA, United States and Jiwoo Lee, Lawence Livermore National Laboratory, Livermore, CA, United States
Combining Crowd-sourcing and Deep Learning to Understand Meso-scale Organization of Shallow Convection (554079)
Stephan Rasp1, Hauke Schulz2, Bjorn B Stevens2 and Sandrine Bony3, (1)Ludwig Maximilians University of Munich, Munich, Germany, (2)Max Planck Institute for Meteorology, Hamburg, Germany, (3)Laboratoire de Météorologie Dynamique, Paris, France
Calibrate-Emulate-Sample for Climate Models (Invited) (570074)
Tapio Schneider1, Emmet Cleary2, Alfredo Garbuno-Inigo2 and Andrew Stuart3, (1)California Institute of Technology, Environmental Science and Engineering, Pasadena, CA, United States, (2)California Institute of Technology, Pasadena, United States, (3)California Institute of Technology, Pasadena, CA, United States
Intensity Estimation of Tropical Cyclone Satellite Images Using Random Walk with Restart (609521)
Yu-Ju Lee, University of Colorado Boulder, Department of Computer Science, Boulder, CO, United States, Wenwei Liao, National Oceanic and Atmospheric Administration, Earth System Research Laboratory - Global Systems Division, Boulder, CO, United States and Kuan-Neng Chen, National Chiao Tung Univeristy, Department of Electronics Engineering, Hsinchu City, Taiwan
Physics-informed Recurrent Neural Network Surrogates for E3SM Land Model (610083)
Vishagan Ratnaswamy1, Cosmin Safta1, Khachik Sargsyan2 and Daniel M Ricciuto3, (1)Sandia National Laboratories, Livermore, CA, United States, (2)Sandia National Laboratories, Albuquerque, NM, United States, (3)Oak Ridge National Laboratory, Environmental Sciences Division and Climate Change Science Institute, Oak Ridge, TN, United States
Forcasting el Nino with Convolutional Recurrent Networks (613992)
Maximilian cody Evans1, Garima Jain1, Ankur Mahesh2, Carlos F. Gaitan Ospina3, Matias Castillo4, Brent Lunghino5, Aranildo Lima6, Jarrett Hunt4, Patrick T Brown7, Saahil Agrawal8 and Himanshu Gupta9, (1)ClimateAi, San Francisco, United States, (2)Lawrence Berkeley National Laboratory, Berkeley, CA, United States, (3)University of Oklahoma Norman Campus, South Central Climate Science Center, Norman, OK, United States, (4)Stanford University, Palo Alto, United States, (5)USGS, Pacific Coastal and Marine Science Center, Baltimore, MD, United States, (6)ClimateAI, Vancouver, Canada, (7)Duke University, Durham, NC, United States, (8)Stanford University, Management Science and Engineering, Stanford, United States, (9)ClimateAi, San Fransico, United States
Climate change + AI: Tackling climate change with machine learning (620574)
Kelly Kochanski, University of Colorado - Boulder, Geological Sciences, Boulder, CO, United States, David Rolnick, University of Pennsylvania, Philadelphia, PA, United States, Priya Donti, Carnegie Mellon University, Pittsburgh, United States, Lynn Kaack, ETH Zurich, Zurich, Switzerland and Scientific authors of 'Tackling climate change with machine learning'
ClimateNet: Bringing the power of Deep Learning to weather and climate sciences via open datasets and architectures (624661)
Karthik Kashinath1, Mayur Mudigonda2, Ankur Mahesh1, Jiayi Chen3, Kevin Yang3, Annette Greiner4 and Mr Prabhat1, (1)Lawrence Berkeley National Laboratory, Berkeley, CA, United States, (2)University of California Berkeley, Berkeley, CA, United States, (3)University of California Berkeley, Computer Science, Berkeley, United States, (4)Lawrence Berkeley National Laboratory, NERSC, Berkeley, United States
Benchmarking Quantitative Precipitation Forecast Using a Composite of Numerical Modeling and Deep Neural Networks (629761)
Baoxiang Pan, Lawrence Livermore National Laboratory, Livermore, CA, United States, Kuo-lin Hsu, University of California Irvine, Irvine, CA, United States, Amir AghaKouchak, University of California, Irvine, Civil and Environmental Engineering, Irvine, CA, United States and Soroosh Sorooshian, Univ California Irvine, Irvine, CA, United States
Deep Learning for Extreme Weather Detection (629790)
Mr Prabhat1, Karthik Kashinath2, Michael F Wehner2 and William Drew Collins3, (1)University of California Berkeley, Berkeley, CA, United States, (2)Lawrence Berkeley National Laboratory, Berkeley, CA, United States, (3)Berkeley Lab and UC Berkeley, Berkeley, CA, United States
