Artificial intelligence for a sustainable groundwater management

In recent years, parts of Germany have experienced groundwater shortages due to warmer and drier summers and lower annual rainfall. Climate projections until the year 2100 show that the trend towards drier and warmer summers will continue. With a presumed increase in water demand, groundwater levels will further decline and there is an imminent risk of groundwater salinisation due to the upwelling of deep saline waters or seawater intrusion near the coast.

In the recently started research project "KIMoDIs" (AI-based monitoring, data management and information system for coupled forecasting and early warning of low groundwater levels and salinisation), BGR is working with eight project partners to develop a data-driven and user-specific early warning and decision support tool for an optimised groundwater management. It is intended to ensure a long-term and sustainable use of the available groundwater resources. For this purpose, all available management data of the water suppliers and of the classic groundwater monitoring are combined with remote sensing-based real-time analyses of irrigated agriculture.

Artificial intelligence (AI) methods are used for the coupled prediction of groundwater levels and salinisation, for optimising the monitoring network and for early warning of critical conditions with regard to drinking water supply and groundwater-dependent ecosystems. AI methods offer significant benefits compared to established methods, as they are able to extract complex relationships from existing data and transfer them both spatially and temporally. The approach is being developed for a supra-regional study area (the state of Brandenburg) and will be transferred exemplarily to two further pilot regions. In this way, the project is contributing to the fulfilment of the goals of the National Water Strategy.

Group photo of the participants at the kick-off event of the KIMoDIs research project at the BGR branch office in Berlin-Spandau Source: BGR