Using Long Short-Term Memory networks to connect water table depth anomalies to precipitation anomalies over Europe

This study utilized spatiotemporally continuous precipitation anomaly (pr_a) and water table depth anomaly (wtd_a) from integrated hydrologic simulation results (i.e., the TSMP-G2A data set) over Europe in combination with Long Short-Term Memory (LSTM) networks to capture the time-varying and time-lagged relationship between pr_a and wtd_a in order to obtain reliable models to estimate wtd_a at the individual pixel level. The data files provide the TSMP-G2A pr_a, the TSMP-G2A wtd_a, and the LSTM wtd_a data from 1996 to 2016, with a spatial resolution of 0.11 degree.