SHALCC

The SHALCC project tackles the critical challenge of modeling managing shallow aquifers’ water resources variability under climate change. These vital yet vulnerable resources are highly sensitive to climate variability and anthropogenic pressures. Unlike deeper confined aquifers, shallow aquifers are more exposed to surface processes, supporting river base flows, ecosystems, and human water supply, but are prone to overexploitation due to lower operational costs. The project aims to address two key challenges: developing hydrological simulations and projections for shallow aquifers under climate scenarios in both gauged and ungauged areas and creating hybrid modeling tools combining physics-based (PB) methods with deep learning (DL). These tools will simulate hydrological dynamics with accuracy and efficiency while ensuring physical consistency and broad applicability. The study focuses on regions with shallow aquifers over crystalline bedrock, including Normandy, Pays de la Loire, and Provence-Alpes-Côte d’Azur. These areas, with groundwater flows confined to shallow weathered and fractured zones (10–100 meters), exhibit diverse geological and climatic conditions. Flow patterns, driven by hillslope processes and linked to meteorological conditions, are highly variable. Climate change, with more intense and prolonged droughts, coupled with internal climate variability, exacerbates stress on these aquifers, highlighting the need for reliable modeling tools for poorly gauged or ungauged basins. The hybrid modeling approach integrates deep learning with physical constraints derived from process-based models, ensuring interpretability and applicability. Validated across contrasting Atlantic and Mediterranean climates, these models will improve predictions in diverse settings. Expected outcomes include scalable, user-friendly forecasting tools for groundwater management, accurate long-term simulations to assess aquifer vulnerability, and advancements in hydrology by integrating AI and physics-based methods. The project will support regional climate initiatives (SAGE, SDAGE, GIEC forecasts), aid local water planning (PTGE, water authorities), and enhance the national “AquiFR” aquifer modeling platform. Ultimately, SHALCC aims to advance hydrology by combining process-driven and data-driven modeling. By leveraging interpretable AI tools alongside process knowledge, the project seeks to improve understanding of water resource variability and provide innovative solutions for managing groundwater amidst climate change impacts.