A091
Machine Learning for Climate Modeling
Session ID#: 78836
Session Description:
Machine learning (ML) can be used to leverage information from both observations and high-resolution models to improve our ability to simulate the past variability and future evolution of the weather and climate. For example, ML can be used to learn sub-grid-scale parameterizations from high-resolution simulations, replace entire components of climate models, or infer unobserved features from limited observations. Compared to more traditional applications of ML (e.g. computer vision), these applications present several unique challenges owing to the multi-scale, multi-physics, and chaotic nature of the Earth’s atmosphere and ocean. For example, prognostic applications such as sub-grid-scale parameterizations should remain numerically stable in time, computationally efficient, and respect conservation laws. This session focuses on 1) applications such as parameterization, automated model tuning, and data assimilation and inference, which promise to improve traditional physics-based prediction systems; or 2) completely data-driven approaches to weather or climate modeling.
Co-Organized:
Co-Sponsor(s):
Index Terms:
1942 Machine learning [INFORMATICS]
3305 Climate change and variability [ATMOSPHERIC PROCESSES]
3337 Global climate models [ATMOSPHERIC PROCESSES]
3365 Subgrid-scale (SGS) parameterization [ATMOSPHERIC PROCESSES]
Primary Convener: Noah Brenowitz, University of Washington, Atmospheric Sciences, Seattle, WA, United States
Conveners: Laure Zanna, University of Oxford, Dept. of Physics, Oxford, United Kingdom and V. Balaji, Princeton University, Princeton, NJ, United States
Primary Liaison: Noah Brenowitz, University of Washington, Atmospheric Sciences, Seattle, WA, United States
Unsupervised Learning Reveals Geography of Global Ocean Dynamical Regions (Invited) (487056)
Maike Sonnewald, Harvard University, Earth and Planetary Sciences, Cambridge, MA, United States, Carl Wunsch, Harvard University, Cambridge, MA, United States and Patrick Heimbach, Massachusetts Institute of Technology, Cambridge, MA, United States
Towards data-driven approaches for simulating rainfall in climate models (491829)
Ramalingam Saravanan1, Junho Yang2, Mikyoung Jun2, Courtney Schumacher3, Jiayi Wang2 and Raymond Ka Wai Wong2, (1)Texas A&M University College Station, College Station, TX, United States, (2)Texas A&M University College Station, Statistics, College Station, United States, (3)Texas A&M Univ, College Station, TX, United States
Artificial Intelligence Based Cloud Distributor (AI-CD): Probing Low Cloud Distribution with Generative Adversarial Neural Networks (507077)
Tianle Yuan1, Hua Song2, David Hall3, Victor Schmidt4, Kris Sankaran4 and Yoshua Bengio5, (1)NASA Goddard Space Flight Center, Greenbelt, MD, United States, (2)University of Maryland Baltimore County, Baltimore, MD, United States, (3)NVIDIA, Lafayette, CO, United States, (4)MILA, Montreal, QC, Canada, (5)MILA / University of Montreal, Montreal, Canada
Reconstruction of Sub-grid-scale Buoyancy Fluxes from Large-Scale ocean Variables (512211)
Anna Sommer, LSCE/CEA, Gif-Sur-Yvette Cedex, France, V. Balaji, Princeton University, Princeton, NJ, United States, Julie Deshayes, Universite Pierre et Marie Curie, LOCEAN, Paris, France, Julien Lesommer, Institut des Géosciences de l'Environnement, CNRS/Univ. Grenoble Alpes/G-INP/IRD, Grenoble, France and Aurélie Albert, Institut des Géosciences de l'Environnement/CNRS/Univ. Grenoble Alpes, Grenoble, France
Deep learning for subgrid-scale turbulence modeling in large-eddy simulations of the atmospheric boundary layer (512420)
Yu Cheng1, Marco Giometto2, Pit Kauffmann3, Ling Lin3, Chen Cao3, Cody Zupnick3, Harold Li1, Qi Li4, Ryan Abernathey5 and Pierre Gentine1, (1)Department of Earth and Environmental Engineering, Columbia University, New York, NY, United States, (2)Department of Civil Engineering and Engineering Mechanics, Columbia University, New York, NY, United States, (3)Columbia University, Capstone Project at Data Science Institute, New York, NY, United States, (4)Cornell University, School of Civil and Environmental Engineering, Ithaca, NY, United States, (5)Department of Earth and Environmental Sciences, Columbia University, Palisades, NY, United States
Tropical Pacific SST prediction with implications for ENSO (529060)
Julian David Rojo Hernandez, Universidad Nacional de Colombia, Bogota, Colombia, Upmanu Lall, Columbia University, New York, NY, United States and Oscar J Mesa, Univ Nacional de Colombia, Medellin, Colombia
Inferring Causation in the Double ITCZ problem in E3SM (544285)
Tao Zhang1, Wuyin Lin1, Minghua Zhang2, Yi Qin3, Hailong Liu4 and Andrew M Vogelmann1, (1)Brookhaven National Laboratory, Upton, NY, United States, (2)SUNY Stony Brook, Stony Brook, NY, United States, (3)Center for Earth System Science, Tsinghua University, Beijing, China, (4)IAP, CAS, Beijing, China
Deep learning forecasts of gridded 500-hPa geopotential heights on short-range to seasonal time scales (553330)
Jonathan Weyn, Austin, TX, United States, Dale R Durran, University of Washington Seattle Campus, Atmospheric Sciences, Seattle, WA, United States and Rich Caruana, Microsoft Research, Redmond, WA, United States
A Generalized Machine Learning Classifier for Spatiotemporal Analysis of Coral Reefs in the Red Sea (560217)
Justin Gapper1, Hesham Mohamed El-Askary2, Erik Linstead3 and Thomas Piechota3, (1)Chapman University, Orange, CA, United States, (2)Chapman Univ, Orange, CA, United States, (3)Chapman University, Schmid College of Science and Technology, Orange, CA, United States
Exploring Uncertainty in Model Representation of Atmospheric Convection through Universal Structural Parameterisation (573190)
Francis H Lambert1, Peter Graham Challenor1, Richard Keane2, Mark Webb3, Doug J McNeall4 and Hannah Mary Christensen5, (1)University of Exeter, Exeter, EX4, United Kingdom, (2)Met Office Hadley center for Climate Change, Exeter, United Kingdom, (3)UK MetOffice, Exeter, United Kingdom, (4)Met Office Hadley Centre, Exeter, United Kingdom, (5)University of Oxford, Atmospheric, Oceanic and Planetary Physics, Oxford, United Kingdom
Towards sub-grid scale parameterizations using a super-resolution generative adversarial network (583528)
Eden Ka Long Au1, Karthik Kashinath2, Adrian Albert2, Mr Prabhat2 and Simon FB Tett3, (1)University of Edinburgh, School of GeoSciences, Edinburgh, EH9, United Kingdom, (2)Lawrence Berkeley National Laboratory, Berkeley, CA, United States, (3)University of Edinburgh, School of GeoSciences, Edinburgh, United Kingdom
A Quantum Mechanical Approach for Data Assimilation in Climate Dynamics (600101)
Dimitrios Giannakis1, Joanna Slawinska2 and Abbas Ourmazd2, (1)New York University, Courant Institute of Mathematical Sciences, New York, NY, United States, (2)University of Wisconsin-Milwaukee, Department of Physics, Milwaukee, WI, United States
Climate Model Intercomparison with Multivariate Information Theoretic Measures (610699)
J. Emmanuel Johnson, University of Valencia, Image Processing Laboratory (IPL), Valencia, Spain, Valero Laparra, University of Valencia, Valencia, Spain, Peer Johannes Nowack, University of Cambridge, Cambridge, United Kingdom, Jakob Runge, German Aerospace Center, Jena, Germany, Veronika Eyring, German Aerospace Center (DLR), Oberpfaffenhofen, Germany and Gustau Camps-Valls, Universitat de València, Image Processing Laboratory (IPL), Burjassot, Spain
