Data‐Driven Estimation of Groundwater Level Time‐Series at Unmonitored Sites Using Comparative Regional Analysis

Abstract

A new method is presented to efficiently estimate daily groundwater level time series at unmonitored sites by linking groundwater dynamics to local hydrogeological system controls. The proposed approach is based on the concept of comparative regional analysis, an approach widely used in surface water hydrology, but uncommon in hydrogeology. Using physiographic and climatic site descriptors, the method utilizes regression analysis to estimate cumulative frequency distributions of groundwater levels (groundwater head duration curves, HDC) at unmonitored locations. The HDC is then used to construct a groundwater hydrograph using time series from distance‐weighted neighboring monitored (donor) locations. For estimating times series at unmonitored sites, in essence, spatio‐temporal interpolation, stepwise multiple linear regression (MLR), extreme gradient boosting (XGB), and nearest neighbors are compared. The methods were applied to 10‐year daily groundwater level time series at 157 sites in unconfined alluvial aquifers in Southern Germany. Models of HDCs were physically plausible and showed that physiographic and climatic controls on groundwater level fluctuations are nonlinear and dynamic, varying in significance from “wet” to “dry” aquifer conditions. XGB yielded a significantly higher predictive skill than nearest neighbor and MLR. However, donor site selection is of key importance. The study presents a novel approach for regionalization and infilling of groundwater level time series that also aids conceptual understanding of controls on groundwater dynamics, both central tasks for water resources managers.

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

“…There have been substantial advances of machine learning (ML) in the data science field. For predicting groundwater levels that can be observed relatively easily, ML models have been used successfully at regional scales (Haaf et al., 2023; Wunsch et al., 2022). For the European continent, there is even a groundwater recharge map based on ML, which uses national survey data as training data (Martinsen et al., 2022).…”