A Review on Interpretable and Explainable Artificial Intelligence in Hydroclimatic Applications

Abstract (from Water): This review focuses on the use of Interpretable Artificial Intelligence (IAI) and eXplainable Artificial Intelligence (XAI) models for data imputations and numerical or categorical hydroclimatic predictions from nonlinearly combined multidimensional predictors. The AI models considered in this paper involve Extreme Gradient Boosting, Light Gradient Boosting, Categorical Boosting, Extremely Randomized Trees, and Random Forest. These AI models can transform into XAI models when they are coupled with the explanatory methods such as the Shapley additive explanations and local interpretable model-agnostic explanations. The review highlights that the IAI models are capable of unveiling the rationale...

Categories: Publication; Types: Citation

Explainable AI reveals new hydroclimatic insights for ecosystem-centric groundwater management

Trustworthy projections of hydrological droughts are pivotal for identifying the key hydroclimatic factors that affect future groundwater level (GWL) fluctuations in drought-prone karstic aquifers that provide water for human consumption and sustainable ecosystems. Herein, we introduce an explainable artificial intelligence (XAI) framework integrated with scenario-based downscaled climate projections from global circulation models. We use the integrated framework to investigate nonlinear hydroclimatic dependencies and interactions behind future hydrological droughts in the Edwards Aquifer Region, an ecologically fragile groundwater-dependent semi-arid region in southern United States. We project GWLs under different...

Categories: Publication; Types: Citation