Revisiting European groundwater variation and its response to human interventions and extreme events with GRACE/-FO data (GREA-EU)

• Applicant: Dr. Fupeng Li
• Subject Area: Geodesy, Photogrammetry, Remote Sensing, Geoinformatics, Cartography ; Hydrogeology, Hydrology, Limnology, Urban Water Management, Water Chemistry, Integrated Water Resources Management
• Term: since 2026
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 585099946

Groundwater, the world’s largest unfrozen freshwater reserve, is essential for water supply, ecosystem sustainability, and agricultural, industrial, and domestic activities. It also buffers land surface temperatures during droughts and heatwaves, influencing climate variability. However, groundwater is difficult to observe directly, and both satellite-based observations (e.g., GRACE) and in-situ measurements have limitations, restricting our understanding of groundwater responses to human activities and extreme events. This project proposes a novel artificial intelligence (AI)–based framework to integrate GRACE-derived products, in-situ groundwater observations, model outputs, and climate forcing data to reconstruct a robust, high-resolution groundwater storage dataset. Focusing on Europe, we will use long short-term memory (LSTM) neural networks to establish empirical relationships in well-instrumented regions and extend them to poorly monitored areas, producing a comprehensive groundwater storage network at 0.25° × 0.25° resolution. By selectively including and excluding GRACE data in the reconstruction, we will quantify human-induced groundwater variations and assess groundwater responses to interventions such as irrigation and dam construction. The reconstructed dataset will also be evaluated against documented drought and heatwave events to improve understanding of groundwater’s role in buffering climate extremes.

• DFG Programme: Research Grants