Primary Convener:
Zeyu Xue, Pacific Northwest National Laboratory

Convener:
Wenli Zhao, Columbia University
Shiheng Duan, Lawrence Livermore National Laboratory
Ye Liu, Pacific Northwest National Laboratory
Yusuke Hiraga, Tohoku University

Chair:
Wenli Zhao, Columbia University
Shiheng Duan, Lawrence Livermore National Laboratory
Ye Liu, Pacific Northwest National Laboratory
Yusuke Hiraga, Tohoku University

Extreme events often result in severe losses in human society and environment. Accurate simulation and prediction of extreme events have been relied highly on the physical models, whereas the computational cost and parameterization deficits have limited the ability of current physical models. Recently, the rapid advancement in machine learning has offered promising solutions to these challenges, though issues related to lack of physical constraints, representational fidelity, and interpretability remain unresolved. Hybrid models appear to be the answer in the new era, promoting the simulation, prediction, and projection in extreme events and consequent impacts. This session invites researchers from both the physical modeling and machine learning communities and aims to build the bridge between two areas.

Index Terms
3355 Regional modeling
1622 Earth system modeling
1627 Coupled models of the climate system
1817 Extreme events

Suggested Itineraries:
Disasters‚ Calamities and Extreme Events
Climate Change and Global Policy
Machine Learning and AI

Co-Organized Sessions:
Atmospheric Sciences

Neighborhoods:
3. Earth Covering