Support vector machine and data assimilation framework for Groundwater Level Forecasting using GRACE satellite data

Abstract

Groundwater (GW) is a vital resource for human consumption, agriculture, environmental sustainability, and socio-economic development in different parts of the world. Besides, GW plays a crucial role in minimizing the impacts during extreme drought events. However, there is a fast decline in groundwater resources due to increased sectoral water demand compounded by reduced rainfall and rising temperature. Therefore, it is essential to develop appropriate tools to study spatio-temporal dynamics and predict groundwater levels to improve water resource management, especially during drought events. In this study, we applied machine learning algorithms based on support vector machines (SVMs), combined with data assimilation (DA) technique to predict the change in groundwater levels (CGWLs) at 1 to 3-month time scales for 46 GW wells located at the northeast United States. The in-situ climate variables and the Gravity Recovery and Climate Experiment (GRACE) mission-informed groundwater anomalies data (GWA) are used to develop the models. The results suggest that SVMs (SVM-DA) models forced with limited climate variables (i.e., precipitation, solar radiation, air temperature, infrared surface temperature) can forecast the CGWLs up to 3-month lead times at most of the locations. The addition of GRACE data as a forcing variable can improve the performance of SVMs at most of the stations, where a strong relationship exists between the CGWLs and the GWA. The SVM-DA model comparatively performed better than SVMs at most of the stations.