Machine learning for climate physics and simulations

TL;DR

This paper explores how machine learning techniques can advance climate physics understanding and simulations, emphasizing the importance of physics-informed models especially in data-scarce, long-term climate prediction scenarios.

Contribution

It highlights the dual roles of ML in climate physics and simulations, stressing the need for interdisciplinary collaboration to develop reliable, interpretable models for climate science.

Findings

ML models excel with abundant data, but physics knowledge is crucial for small-data regimes.

Physics-informed ML enhances interpretability and generalization in climate modeling.

Collaboration across disciplines is essential for reliable climate ML applications.

Abstract

We discuss the emerging advances and opportunities at the intersection of machine learning (ML) and climate physics, highlighting the use of ML techniques, including supervised, unsupervised, and equation discovery, to accelerate climate knowledge discoveries and simulations. We delineate two distinct yet complementary aspects: (1) ML for climate physics and (2) ML for climate simulations. While physics-free ML-based models, such as ML-based weather forecasting, have demonstrated success when data is abundant and stationary, the physics knowledge and interpretability of ML models become crucial in the small-data/non-stationary regime to ensure generalizability. Given the absence of observations, the long-term future climate falls into the small-data regime. Therefore, ML for climate physics holds a critical role in addressing the challenges of ML for climate simulations. We emphasize the need for collaboration among climate physics, ML theory, and numerical analysis to achieve reliable ML-based models for climate applications.