Using Explainability to Inform Statistical Downscaling Based on Deep Learning Beyond Standard Validation Approaches
This work addresses the need for better evaluation methods in climate science, particularly for downscaling applications, but it is incremental as it builds on existing approaches.
The authors tackled the challenge of evaluating deep learning models for climate downscaling under changing conditions by integrating explainable AI techniques, demonstrating their utility in diagnosing model behavior and enhancing evaluation frameworks.
Deep learning (DL) has emerged as a promising tool to downscale climate projections at regional-to-local scales from large-scale atmospheric fields following the perfect-prognosis (PP) approach. Given their complexity, it is crucial to properly evaluate these methods, especially when applied to changing climatic conditions where the ability to extrapolate/generalise is key. In this work, we intercompare several DL models extracted from the literature for the same challenging use-case (downscaling temperature in the CORDEX North America domain) and expand standard evaluation methods building on eXplainable artifical intelligence (XAI) techniques. We show how these techniques can be used to unravel the internal behaviour of these models, providing new evaluation dimensions and aiding in their diagnostic and design. These results show the usefulness of incorporating XAI techniques into statistical downscaling evaluation frameworks, especially when working with large regions and/or under climate change conditions.