Stable Simulation of the Community Atmosphere Model Using Machine‐Learning Physical Parameterization Trained With Experience Replay

Abstract In recent years, machine learning (ML) models have been used to improve physical parameterizations of general circulation models (GCMs). A significant challenge of integrating ML models into GCMs is the online instability when they are coupled for long‐term simulation. We present a new stra...

Full description

Saved in:
Bibliographic Details
Main Authors: Jianda Chen, Minghua Zhang, Tao Zhang, Wuyin Lin, Wei Xue
Format: Article
Language:English
Published: American Geophysical Union (AGU) 2025-06-01
Series:Journal of Advances in Modeling Earth Systems
Subjects:
Online Access:https://doi.org/10.1029/2024MS004722
Tags: Add Tag
No Tags, Be the first to tag this record!