Climate-Invariant Machine Learning
This addresses the challenge of improving climate model projections for researchers and policymakers, though it is incremental as it builds on existing ML and physical modeling approaches.
The paper tackles the problem of poor generalization of machine learning models in climate projections by proposing a 'climate-invariant' ML framework that incorporates physical knowledge, showing it maintains high accuracy across diverse climate conditions in three atmospheric models.
Projecting climate change is a generalization problem: we extrapolate the recent past using physical models across past, present, and future climates. Current climate models require representations of processes that occur at scales smaller than model grid size, which have been the main source of model projection uncertainty. Recent machine learning (ML) algorithms hold promise to improve such process representations, but tend to extrapolate poorly to climate regimes they were not trained on. To get the best of the physical and statistical worlds, we propose a new framework - termed "climate-invariant" ML - incorporating knowledge of climate processes into ML algorithms, and show that it can maintain high offline accuracy across a wide range of climate conditions and configurations in three distinct atmospheric models. Our results suggest that explicitly incorporating physical knowledge into data-driven models of Earth system processes can improve their consistency, data efficiency, and generalizability across climate regimes.