Session: Machine Learning Techniques for Atmospheric and Oceanic Prediction Models (99th American Meteorological Society Annual Meeting)

Wednesday, 9 January 2019: 8:30 AM-10:00 AM

North 124B (Phoenix Convention Center - West and North Buildings)

Hosts: (Joint between the 18th Conference on Artificial and Computational Intelligence and its Applications to the Environmental Sciences; and the 17th Symposium on the Coastal Environment )

Cochairs:

Christiane Jablonowski, University of Michigan, Climate and Space Science and Enigneering, Ann Arbor, MI; Amy McGovern, University of Oklahoma, School of Computer Science, Norman, OK and Alan Blumberg, Stevens Institute of Technology, Davidson Laboratory, Hoboken, NJ

The session focuses on machine learning techniques for future-generation weather, climate, and ocean models, which includes machine learning testbeds with idealized modeling frameworks such as aquaplanets, shallow-water models, single-column models, or even more conceptual models. Potential topics might explore whether machine learning techniques can be used to estimate uncertain parameters or closure assumptions in subgrid-scale physical parameterizations, or even replace complex physical parameterization packages such as cloud or turbulence schemes. Of particular interest are physics-informed machine learning concepts.

Papers:

8:30 AM

J1.1

Testing the Potential of Machine Learning for Weather Prediction

Peter Dueben, ECMWF, Reading, United Kingdom; and P. Bauer

Recorded Presentation

8:45 AM

J1.2

Evaluating Generative Adversarial Network Stochastic Parameterizations of the Lorenz '96 Model at Weather and Climate Time Scales

David John Gagne II, NCAR, Boulder, CO; and H. Christensen, A. Subramanian, and A. H. Monahan

9:00 AM

J1.3