Interpretable Machine Learning for Weather and Climate Prediction: A Survey

TL;DR

This survey reviews current interpretable machine learning methods applied to weather and climate prediction, emphasizing techniques that enhance model transparency and understanding of meteorological insights.

Contribution

It categorizes and summarizes existing interpretability approaches in meteorological ML, highlighting challenges and future research directions.

Findings

Post-hoc interpretability techniques explain pre-trained models.

Inherently interpretable models include tree ensembles and explainable neural networks.

Identifies challenges in aligning ML interpretability with physical climate principles.

Abstract

Advanced machine learning models have recently achieved high predictive accuracy for weather and climate prediction. However, these complex models often lack inherent transparency and interpretability, acting as "black boxes" that impede user trust and hinder further model improvements. As such, interpretable machine learning techniques have become crucial in enhancing the credibility and utility of weather and climate modeling. In this survey, we review current interpretable machine learning approaches applied to meteorological predictions. We categorize methods into two major paradigms: 1) Post-hoc interpretability techniques that explain pre-trained models, such as perturbation-based, game theory based, and gradient-based attribution methods. 2) Designing inherently interpretable models from scratch using architectures like tree ensembles and explainable neural networks. We summarize how each technique provides insights into the predictions, uncovering novel meteorological relationships captured by machine learning. Lastly, we discuss research challenges around achieving deeper mechanistic interpretations aligned with physical principles, developing standardized evaluation benchmarks, integrating interpretability into iterative model development workflows, and providing explainability for large foundation models.