ACE: A fast, skillful learned global atmospheric model for climate prediction
This work addresses the need for fast and stable climate prediction models, representing a significant advance over existing ML-based atmospheric models.
The authors tackled the problem of creating a machine learning-based atmospheric model suitable for climate prediction by developing ACE, a 200M-parameter emulator that is stable for 100 years, outperforms a baseline on over 90% of tracked variables, and is 100x faster and more energy-efficient than the reference model.
Existing ML-based atmospheric models are not suitable for climate prediction, which requires long-term stability and physical consistency. We present ACE (AI2 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 100 years, nearly conserves column moisture without explicit constraints and faithfully reproduces the reference model's climate, outperforming a challenging baseline on over 90% 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. Without fine-tuning, ACE can stably generalize to a previously unseen historical sea surface temperature dataset.