Towards Physically Consistent Deep Learning For Climate Model Parameterizations

Abstract

Climate models play a critical role in understanding and projecting climate change. Due to their complexity, their horizontal resolution of about 40-100 km remains too coarse to resolve processes such as clouds and convection, which need to be approximated via parameterizations. These parameterizations are a major source of systematic errors and large uncertainties in climate projections. Deep learning (DL)-based parameterizations, trained on data from computationally expensive short, high-resolution simulations, have shown great promise for improving climate models in that regard. However, their lack of interpretability and tendency to learn spurious non-physical correlations result in reduced trust in the climate simulation. We propose an efficient supervised learning framework for DL-based parameterizations that leads to physically consistent models with improved interpretability and negligible computational overhead compared to standard supervised training. First, key features determining the target physical processes are uncovered. Subsequently, the neural network is fine-tuned using only those relevant features. We show empirically that our method robustly identifies a small subset of the inputs as actual physical drivers, therefore removing spurious non-physical relationships. This results in by design physically consistent and interpretable neural networks while maintaining the predictive performance of unconstrained black-box DL-based parameterizations.

Accepted at ICMLA 2024

References in corpus (7)

• Interpreting and Stabilizing Machine-learning Parametrizations of Convection
• Deep Learning Based Cloud Cover Parameterization for ICON
• Learning physics-constrained subgrid-scale closures in the small-data regime for stable and accurate LES
• Causally-informed deep learning to improve climate models and projections
• Non-local parameterization of atmospheric subgrid processes with neural networks
• Generative data-driven approaches for stochastic subgrid parameterizations in an idealized ocean model
• Non-Linear Dimensionality Reduction with a Variational Encoder Decoder to Understand Convective Processes in Climate Models