Advancing climate model interpretability: Feature attribution for Arctic melt anomalies
Tolulope Ale, Nicole-Jeanne Schlegel, Vandana P. Janeja
TL;DR
This work addresses the interpretability of Arctic melt anomalies by comparing ERA5 snowmelt and GEMB melt models and applying a CLV-based unsupervised anomaly detector with counterfactual feature attribution to Greenland. The approach reveals instance-level drivers of anomalies and demonstrates distinct physics captured by each model, with ERA5 emphasizing temperature- and radiation-driven features and GEMB highlighting cryospheric processes. Ground-truth validation shows GEMB better aligns with MEaSUREs melt, while both models exhibit an increasing trend in anomaly frequency over the past decades. The framework enhances climate-model interpretability, supports model-intercomparison efforts, and offers a pathway toward physics-informed model selection for polar climate projections.
Abstract
The focus of our work is improving the interpretability of anomalies in climate models and advancing our understanding of Arctic melt dynamics. The Arctic and Antarctic ice sheets are experiencing rapid surface melting and increased freshwater runoff, contributing significantly to global sea level rise. Understanding the mechanisms driving snowmelt in these regions is crucial. ERA5, a widely used reanalysis dataset in polar climate studies, offers extensive climate variables and global data assimilation. However, its snowmelt model employs an energy imbalance approach that may oversimplify the complexity of surface melt. In contrast, the Glacier Energy and Mass Balance (GEMB) model incorporates additional physical processes, such as snow accumulation, firn densification, and meltwater percolation/refreezing, providing a more detailed representation of surface melt dynamics. In this research, we focus on analyzing surface snowmelt dynamics of the Greenland Ice Sheet using feature attribution for anomalous melt events in ERA5 and GEMB models. We present a novel unsupervised attribution method leveraging counterfactual explanation method to analyze detected anomalies in ERA5 and GEMB. Our anomaly detection results are validated using MEaSUREs ground-truth data, and the attributions are evaluated against established feature ranking methods, including XGBoost, Shapley values, and Random Forest. Our attribution framework identifies the physics behind each model and the climate features driving melt anomalies. These findings demonstrate the utility of our attribution method in enhancing the interpretability of anomalies in climate models and advancing our understanding of Arctic melt dynamics.