Explainable artificial intelligence (XAI) for scaling: An application for deducing hydrologic connectivity at watershed scale
This work addresses the challenge of cross-scale aggregation in hydrology for researchers, offering a framework to enhance process understanding, though it is incremental by integrating XAI with existing hydrologic knowledge.
The study tackled the problem of scaling hydrologic responses by applying explainable AI (XAI) to interpret deep learning models, using hydrologic connectivity as a demonstration; results showed that XAI-based classification effectively identified functional differences in watershed sub-regions and provided a quantitative indicator for connectivity development.
Explainable artificial intelligence (XAI) methods have been applied to interpret deep learning model results. However, applications that integrate XAI with established hydrologic knowledge for process understanding remain limited. Here we show that XAI method, applied at point-scale, could be used for cross-scale aggregation of hydrologic responses, a fundamental question in scaling problems, using hydrologic connectivity as a demonstration. Soil moisture and its movement generated by physically based hydrologic model were used to train a long short-term memory (LSTM) network, whose impacts of inputs were evaluated by XAI methods. Our results suggest that XAI-based classification can effectively identify the differences in the functional roles of various sub-regions at watershed scale. The aggregated XAI results could be considered as an explicit and quantitative indicator of hydrologic connectivity development, offering insights to hydrological organization. This framework could be used to facilitate aggregation of other geophysical responses to advance process understandings.