Skip to yearly menu bar Skip to main content


Poster
in
Workshop: NeurIPS 2023 Workshop on Tackling Climate Change with Machine Learning: Blending New and Existing Knowledge Systems

ACE: A fast, skillful learned global atmospheric model for climate prediction

Oliver Watt-Meyer · Gideon Dresdner · Jeremy McGibbon · Spencer K. Clark · James Duncan · Brian Henn · Matthew Peters · Noah Brenowitz · Karthik Kashinath · Mike Pritchard · Boris Bonev · Christopher S. Bretherton


Abstract:

Existing ML-based atmospheric models are not suitable for climate prediction, which requires long-term stability and physical consistency. We present ACE (AI Climate Emulator), a 200M-parameter, autoregressive machine learning emulator of an existing comprehensive 100-km resolution global atmospheric model. The formulation of ACE allows evaluation of physical laws such as the conservation of mass and moisture. The emulator is stable for 10 years, nearly conserves column moisture without explicit constraints and faithfully reproduces the reference model's climate, outperforming a challenging baseline on over 80% of tracked variables. ACE requires nearly 100x less wall clock time and is 100x more energy efficient than the reference model using typically available resources.

Chat is not available.