Towards a global spatial machine learning model for seasonal groundwater level predictions in Germany

Abstract. Reliable predictions of groundwater levels are crucial for sustainable groundwater resource management, which needs to balance diverse water needs and to address potential ecological consequences of groundwater depletion. Machine learning (ML) approaches for time series forecasting have shown promising accuracy for groundwater level prediction and, furthermore, offer scalability advantages over traditional numerical methods when sufficient data are available. Global ML architectures enable predictions across numerous monitoring wells concurrently using a single model, allowing predictions over a broad range of hydrogeological and meteorological conditions and simplifying model management. In this contribution, groundwater levels for 5288 monitoring wells across Germany were forecasted up to 12 weeks using two state-of-the-art ML approaches, the Temporal Fusion Transformer (TFT) and the Neural Hierarchical Forecasting for Time Series (N-HiTS) algorithm. The models were provided with historical groundwater levels, meteorological features, and a wide range of static features describing hydrogeological and soil properties at the monitoring sites. To determine the conditions under which the model achieves good performance and whether it aligns with hydrogeological system understanding, the model's performance was evaluated spatially and correlations with both static input features and time series features from hydrograph data were examined. The N-HiTS model outperformed the TFT model, achieving a median Nash–Sutcliffe efficiency (NSE) of 0.5 for the 12-week prediction over all 5288 monitoring wells. Performance varied widely: 25 % of wells achieved an NSE >0.68, while 15 % had an NSE <0 with the best N-HiTS model. A tendency for better predictions in areas with high data density was observed. Moreover, the models achieved higher performance in lowland areas with distinct seasonal groundwater dynamics, in monitoring wells located in porous aquifers, and at sites with moderate permeabilities, which aligns with theoretical expectations. Overall, the findings highlight that global ML models can facilitate accurate seasonal groundwater predictions over large, hydrogeological diverse areas, potentially informing future groundwater management practices at a national scale.