Researchers introduce ADAGE framework to evaluate alignment between deep learning model explanations and established remote sensing knowledge in satellite-based flood mapping.

A study presents the ADAGE (Alignment between Domain Knowledge And GeoAI Explanation Evaluation) framework, which uses Channel-Group SHAP (a method for estimating feature contributions) to assess how well deep learning model explanations align with domain knowledge in remote sensing for flood mapping tasks.

The framework enables quantitative measurement of alignment between model explanations and reference explanations derived from domain knowledge, and helps domain experts identify misaligned explanations through alignment scores.

The research addresses the challenge that deep learning models used in satellite-based flood monitoring have opaque decision-making processes, which has been a barrier to their integration into critical scientific and operational workflows.