XAI4Extremes: An interpretable machine learning framework for understanding extreme-weather precursors under climate change
This work addresses the challenge of understanding extreme-weather precursors for climate scientists and policymakers, but it is incremental as it applies existing interpretability methods to a new domain.
The paper tackled the problem of identifying precursors to extreme weather events under climate change by using post-hoc interpretability methods to create relevance maps from deep learning models, and found that these models can identify patterns that enrich understanding of precursors, with experiments focused on Indochina heatwaves.
Extreme weather events are increasing in frequency and intensity due to climate change. This, in turn, is exacting a significant toll in communities worldwide. While prediction skills are increasing with advances in numerical weather prediction and artificial intelligence tools, extreme weather still present challenges. More specifically, identifying the precursors of such extreme weather events and how these precursors may evolve under climate change remain unclear. In this paper, we propose to use post-hoc interpretability methods to construct relevance weather maps that show the key extreme-weather precursors identified by deep learning models. We then compare this machine view with existing domain knowledge to understand whether deep learning models identified patterns in data that may enrich our understanding of extreme-weather precursors. We finally bin these relevant maps into different multi-year time periods to understand the role that climate change is having on these precursors. The experiments are carried out on Indochina heatwaves, but the methodology can be readily extended to other extreme weather events worldwide.