Quantus x Climate - Applying Explainable AI Evaluation in Climate Science

Explainable artificial intelligence (XAI) methods shed light on the predictions of deep neural networks (DNNs). In the climate context, XAI has been applied to improve and validate deep learning (DL) methods while providing researchers with new insight into physical processes. However, the evaluation, validation and selection of XAI methods are challenging due to often lacking ground truth explanations. In this tutorial, we introduce the XAI evaluation package Quantus to the climate community to facilitate well-founded XAI research in climate science. Based on an example research case, we discuss the explanation properties that can be evaluated such as robustness, faithfulness, complexity, localization and randomization. By demonstrating how metrics differ in their scoring and interpretation, we guide the participants towards a practical understanding of XAI evaluation. Moreover, we teach the participants to compare and select an appropriate XAI method by performing a comprehensive XAI evaluation.
Speaker: Philine Lou Bommer ((UMI Lab, Faculty IV, TU Berlin & Data Science in Bioeconomy, ATB Potsdam)
To ask your questions for the Q&A session, Slido link: app.sli.do/eve...

[@khaledissa5539]

Is it possible to add me to your community ,