Can eXplainable AI Offer a New Perspective for Groundwater Recharge Estimation?-Global-Scale Modeling Using Neural Network

Due to the difficulties in estimating groundwater recharge and cross-boundary nature of many aquifers, estimating groundwater recharge at large scale has been called upon. Process-based models as well as data-driven models have been established to meet this need. Meanwhile, with the advent of explainable artificial intelligence (XAI) methods, data-driven machine learning models can take advantage of enhanced explainability while keeping the strength of high flexibility. In this study, an ensemble neural network model was built to check the suitability of the model to predict groundwater recharge and the possibility to gain new insights from large data set. Recent large inputs of groundwater recharge data and additional input for the Arabian Peninsula collated in this study were fed to the model with multiple predictors related to climatology considering seasonality, soil and plant characteristics, topography, and hydrogeology. The model showed higher performance (adjusted R2: 0.702, RMSE: 193.35 mm yr-1) than a recent global process-based model in predicting groundwater recharge. Using XAI methods as individual conditional expectations and Shapley Additive Explanation interaction values, the model behavior was analyzed and possible linear and non-linear relationships between the predictors and the groundwater recharge rate were found. Long-term averaged precipitation and enhanced vegetation index showed non-linear relationships with groundwater recharge rate, while slope, compound topographic index, and water table depth showed low importance to the model results. Most model behaviors followed the domain knowledge, while multi-correlation between predictors and data skewness hindered the model from learning. Estimating groundwater recharge rates at a large scale has been an important task among hydrologists. Both process-based models and data-driven models have been used for this purpose. Despite their high flexibility and high performance, there has been criticism over data-driven models, especially machine-learning models, that the result of the models are difficult to explain. However, new analysis tools called explainable artificial intelligence (XAI) can help explain the model results. In this study, a machine-learning model (ensemble neural network model) has been built at global scale to check if the model can estimate groundwater recharge rates and to check if the model's behavior explained by XAI can give new insights into the processes. Our model shows higher performance compared to a recent global process-based model. XAI tools are used to explain how the model predicted the groundwater recharge rates. Long-term averaged precipitation and enhanced vegetation index show high sensitivity and high importance in predicting groundwater recharge rates, while topographical factors related to slope, curvature, and depth to the groundwater aquifer show low sensitivity and importance. Estimating groundwater recharge rates at global scale using an ensemble neural network model with 5541 observations and 20 predictors XAI can quantify the sensitivity and importance of each predictor, showing non-linearities with long-term precipitation and vegetation index Predictions show higher accuracy than the current process-based model, with most behaviors measured by XAI aligning with domain knowledge