Nitrate Monitoring 4.0 - Intelligent Systems for Sustainable Reduction of Nitrate in Groundwater (NiMo 4.0)
Federal Ministry for the Environment, Nature Conservation and Nuclear Safety (BMU)
Funding code: 67KI2048C
Disy Informationssysteme GmbH (Disy)
DVGW-Technologiezentrum Wasser (TZW)
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung (IOSB)
The distribution of nitrate in groundwater is the result of a complex interplay of many influencing factors, including not only the input, which is determined by land use, but also meteorological factors (precipitation, evaporation), chemical-physical properties of the groundwater-covering layers and transport and reaction processes in the groundwater itself. The nitrate distribution in groundwater therefore represents a highly complex, spatially and temporally highly variable pattern, which shows a pronounced hydro-geochemical differentiation regionally and especially vertically. Although the input, transport and dispersion of nitrate in groundwater follow largely known chemical-physical processes, modelling with analytical or numerical models at a reasonable spatial resolution has been difficult so far. AI applications, in particular neural networks belonging to the field of machine learning or deep learning methods, as they are often used in other disciplines for pattern recognition, offer here a clear added value compared to the established methods. As a data-based model, they are able to extract and transfer complex relationships from a large amount of data.
The overall aim of the project is to improve the spatial and temporal prediction of nitrate in groundwater and to develop intelligent decision support systems based on this, which, for example, contribute to the optimisation of groundwater protection programmes through scenario calculations and thus to efficient and sustainable nitrate reduction. The considered approaches and methods will be developed, demonstrated and validated on the basis of real data from two pilot regions of water management importance, with sufficiently large hydrogeological variability, in order to be able to make statements on the general validity and transferability of the developed solutions. Furthermore, the spatial prediction in combination with modern methods of geostatistics and operational research also allows recommendations for the optimisation of the monitoring network.
|Promotion:||Federal Ministry for the Environment, Nature Conservation and Nuclear Safety (BMU)|
|Support programme:||AI Lighthouses for Environment, Climate, Nature and Resources|
|conveyor line:||Application orientation and foundation|