A068
Machine Learning for Weather and Climate Modeling IV Posters

Wednesday, 9 December 2020: 04:00-20:59
Poster
Primary Convener:  Noah Brenowitz, Vulcan, Climate Modeling, Seattle, WA, United States
Conveners:  Christopher Stephen Bretherton, University of Washington Seattle Campus, Seattle, WA, United States, Laure Zanna, University of Oxford, Dept. of Physics, Oxford, United Kingdom and Maike Sonnewald, Princeton University, Princeton, NJ, United States
Primary Liaison:  Noah Brenowitz, Vulcan, Climate Modeling, Seattle, WA, United States
Chairs:  Laure Zanna, University of Oxford, Dept of Physics, Oxford, United Kingdom and Christopher Stephen Bretherton, University of Washington Seattle Campus, Seattle, WA, United States
OSPA Liaison:  Maike Sonnewald, Harvard University, Earth and Planetary Sciences, Cambridge, MA, United States
 
A Machine learning assisted Cloud Population Model as a Parameterization of Cumulus Convection (670988)
Samson M Hagos1, Jingyi Chen2, Koichi Sakaguchi3, Katelyn A Barber2, Zhe Feng2, Heng Xiao4 and Robert Plant5, (1)Pacific Northwest National Laboratory, Atmospheric Sciences & Global Change Division, Richland, WA, United States, (2)Pacific Northwest National Laboratory, Richland, WA, United States, (3)PNNL / Climate Physics, Richland, WA, United States, (4)Pacific Northwest Natl Lab, Richland, WA, United States, (5)University of Reading, Reading, United Kingdom
 
A new data-driven method to diagnose ocean eddy transport coefficients (743053)
Mu Xu and Ryan Abernathey, Lamont -Doherty Earth Observatory, Palisades, NY, United States
 
An Evaluation of Coupled Machine Learning Emulators for Physical Parameterizations in the Community Atmosphere Model (753802)
Garrett Limon, University of Michigan Ann Arbor, Ann Arbor, MI, United States and Christiane Jablonowski, University of Michigan, Ann Arbor, MI, United States
 
Assessing the potential of deep neural networks for emulating cloud superparameterization in climate models under real geography boundary conditions (750261)
Griffin Mooers1, Mike S Pritchard1, Tom Beucler1,2, Jordan Ott3, Galen Yacalis4, Pierre Baldi3 and Pierre Gentine2, (1)University of California Irvine, Earth System Science, Irvine, CA, United States, (2)Columbia University, Earth and Environmental Engineering, New York, NY, United States, (3)University of California Irvine, Information and Computer Sciences, Irvine, CA, United States, (4)Jupiter Intelligence, San Mateo, CA, United States
 
Climate-Invariant Nets: Using Physical Rescalings to Help Neural Networks Generalize to Out-of-Sample Climates (738580)
Tom Beucler1, Mike S Pritchard2, Liran Peng1, Stephan Rasp3, Pierre Gentine4 and Ankitesh Gupta5, (1)University of California Irvine, Earth System Science, Irvine, CA, United States, (2)University California Irvine, Department of Earth System Science, Irvine, CA, United States, (3)Technical University of Munich, Munich, Germany, (4)Columbia University, Earth and Environmental Engineering, New York, NY, United States, (5)University of California, Irvine, Earth System Science, Irvine, CA, United States
 
Correcting weather models by learning nudging tendencies from hindcast simulations (711951)
Oliver Watt-Meyer1, Noah Brenowitz1, Christopher Stephen Bretherton1,2, Spencer Clark1, Brian M Henn1, Anna Kwa1, Jeremy McGibbon1, Andre Perkins1 and Lucas Harris3, (1)Vulcan, Inc., Climate Modeling, Seattle, WA, United States, (2)University of Washington Seattle Campus, Seattle, WA, United States, (3)NOAA/Geophysical Fluid Dynamics Laboratory, Princeton, NJ, United States
 
Data-driven Super-prameterization in Climate Modeling with Recurrent Neural Networks and Transfer-Learning (694780)
Ashesh Kumar Chattopadhyay1, Adam Subel2 and Pedram Hassanzadeh1, (1)Rice University, Houston, TX, United States, (2)Rice University, Mechanical Engineering, Hosuton, TX, United States
 
Emulator-accelerated perturbed parameter ensembles: methods for addressing observational biases, parametric errors, and structural errors in GCMs (727361)
Marcus van Lier-Walqui, Columbia University, Center for Climate Systems Research, New York, NY, United States, Hugh Morrison, NCAR, MMM Laboratory, Boulder, CO, United States and Gregory Elsaesser, Columbia University/NASA GISS, Dept. of Applied Physics and Applied Mathematics, New York, NY, United States
 
Hyperparameter Optimization and a Deep Learning Bridge to Fortran (770012)
Jordan Ott1, Mike S Pritchard2, Natalie Best3, Erik Linstead4, Milan Curcic5 and Pierre Baldi1, (1)University of California Irvine, Information and Computer Sciences, Irvine, CA, United States, (2)University California Irvine, Department of Earth System Science, Irvine, CA, United States, (3)Chapman University, Fowler School of Engineering, Orange, United States, (4)Chapman University, Schmid College of Science and Technology, Orange, CA, United States, (5)University of Miami/RSMAS, Miami, FL, United States
 
Machine Learning for emulating Physical Parameterization of Planetary Boundary Layer Height (745297)
Phuong Nguyen1, Rahul Gite2, Ankita Rathod2, Zhifeng Yang3 and Milton Halem1, (1)University of Maryland Baltimore County, Computer Science, Baltimore, MD, United States, (2)University of Maryland Baltimore County, Computer Science and Electrical Engineering, Baltimore, MD, United States, (3)University of Maryland Baltimore County, Physics Department, Baltimore, MD, United States
 
Machine Learning Parameterization of Mature Tropical Cyclone Boundary Layer (716409)
Leyi Wang and Zhe-Min Tan, Nanjing University, Nanjing, China
 
Physically Regularized Machine Learning Emulators of Aerosol Activation (693878)
Sam James Silva1, Po-Lun Ma1, Joseph Clinton Hardin1, Daniel A Rothenberg2 and Kyle Pressel1, (1)Pacific Northwest National Laboratory, Richland, WA, United States, (2)Massachusetts Institute of Technology, Earth, Atmospheric, and Planetary Sciences, Cambridge, MA, United States
 
Towards a deep learned subgrid-scale surrogate model for stratified turbulence from high-resolution simulation data (750796)
Muralikrishnan Gopalakrishnan Meena, Oak Ridge National Laboratory, Oak Ridge, TN, United States and Matthew R Norman, Oak Ridge National Lab, Oak Ridge, TN, United States
 
Uncertainty-Aware Physics-Informed Neural Networks for Parametrizations in Ocean Modeling (679017)
Björn Lütjens1, Mark Veillette2 and Dava Newman1, (1)Massachusetts Institute of Technology, Department of Aeronautics and Astronautics, Cambridge, MA, United States, (2)MIT Lincoln Laboratory, Lexington, MA, United States
See more of: Atmospheric Sciences
<< Previous Session Proposal | Next Session Proposal >>