BGR Bundesanstalt für Geowissenschaften und Rohstoffe

GRUVO - Groundwater levels and forecasts for Germany

Country / Region: Germany

Status of project: April 25, 2024

Background:
The web-based application GRUVO uses a machine learning approach to provide a standardised and regularly updated view of past, present and future groundwater levels throughout Germany. Forecast periods range from short-term (up to 3 months) to medium-term (10 years) and long-term (up to 2100) in order to objectively assess the development of groundwater levels against the background of climate change, taking into account the scenarios of the Intergovernmental Panel on Climate Change (IPCC). In addition to groundwater data from the monitoring networks of the relevant state authorities, the information base also includes weather and climate forecasts and climate projections from the German Weather Service (DWD).

Homepage of the GRUVO application "Groundwater levels and forecasts for Germany"Homepage of the GRUVO application

The groundwater level, also known as the water table, provides a direct and easily determined method for an initial assessment of the availability of the groundwater resource. Knowledge of past, present and future groundwater levels provides decision-makers and practitioners in the water sector with important information on long-term trends and changes in groundwater availability. This can help to anticipate potential problems and develop appropriate strategies for managing groundwater resources for drinking water supply and agricultural irrigation. Groundwater level forecasts can also raise public awareness of potential water shortage situations due to low groundwater levels and overflow situations due to high groundwater levels.

Methodology:
The application is based on the concept of reference monitoring sites. All available monitoring sites are reduced to a manageable number of reference monitoring sites. Each reference monitoring site is assigned a number of cluster monitoring sites, which are relatively reliably represented by the respective reference monitoring site. With limited technical feasibility, this allows a largely area-wide forecast. Only a limited number of monitoring sites can be equipped with data loggers with remote data transmission, and the computational effort for the monthly update remains manageable. In GRUVO, current measurements are displayed at around 120 reference monitoring sites, which are then transferred to a total of around 4,200 monitoring sites so that short-term forecasts can be calculated in a further step. The medium-term and long-term forecasts are displayed at 60 and 118 reference monitoring sites respectively.

Algorithms based on the Artificial Neural Network (ANN) method were developed and used for this purpose. The main objective was to replace traditional physical-numerical models with machine learning to predict groundwater levels nationwide using available data. This can compensate for missing or incomplete field data, such as geometries and physical properties of the subsurface. This was possible by reducing the problem to a simple input-output relationship. The previously complex and expensive data collection to characterise the subsurface is no longer necessary. A detailed description of the methodology used can be found at https://gruvo.bgr.de/website/methodology.

Main features:

  • Presentation of current groundwater levels in five status classes (from very low to very high), based on the reference period 1991-2020
  • Monthly overview of groundwater levels at national, major hydrogeological district and hydrogeological region level
  • Predicted groundwater levels for the next three months, ten years and up to 2100
  • Visualisation of model and prediction quality

Outlook:
Further development of the application is planned. The number of reference and cluster monitoring sites will be increased, the quality of forecasts will be continuously improved, groundwater information will be transferred from the monitoring site to the surface and the forecast will be extended to include spring discharges.


View of the GRUVO map application. On the left, the forecast selection menu and legend window; on the right, the info window with hydrograph plots and model and forecast quality indicatorsView of the GRUVO map application. On the left, the forecast selection menu and legend window; on the right, the info window with hydrograph plots and model and forecast quality indicators Source: BGR


Application: GRUVO - Groundwater levels and forecast for Germany


Literature:

Technical report

  • WUNSCH, A. & LIESCH, T. (2020): Entwicklung und Anwendung von Algorithmen zur Berechnung von Grundwasserständen an Referenzmessstellen auf Basis der Methode Künstlicher Neuronaler Netze. - Abschlussbericht Projektphase I, 183 S., 61 Abb., 11 Tab., 13 Anh.; KIT, Karlsruhe. doi: 10.5445/IR/1000136522

Papers

  • WUNSCH, A., LIESCH, T. & BRODA, S. (2022b): Deep learning shows declining groundwater levels in Germany until 2100 due to climate change. - Nat Commun 13, 1221. doi: 10.1038/s41467-022-28770-2
  • WUNSCH, A., LIESCH, T. & BRODA, S. (2022a): Feature-based Groundwater Hydrograph Clustering Using Unsupervised Self-Organizing Map-Ensembles. - Water Resour. Manage., 36(1): 39-54. doi: 10.1007/s11269-021-03006-y
  • WUNSCH, A., LIESCH, T. & BRODA, S. (2021): Groundwater level forecasting with artificial neural networks: a comparison of long short-term memory (LSTM), convolutional neural networks (CNNs), and non-linear autoregressive networks with exogenous input (NARX). - Hydrol. Earth Syst. Sci. 25: 1671-1687. doi: 10.5194/hess-25-1671-2021
  • WUNSCH, A., LIESCH, T. & BRODA, S. (2021): Feature-basiertes Clustering von Umweltzeitreihen mit Self-Organizing-Map-Ensembles. - In: REUSSNER, R.H., KOZIOLEK, A. & HEINRICH, R. (Hrsg.): Informatik 2020. Gesellschaft für Informatik, Bonn. (S. 1035-1041). doi: 10.18420/inf2020_98
  • WUNSCH, A., LIESCH, T. & BRODA, S. (2018): Forecasting Groundwater Levels using nonlinear Autoregressive Networks with exogenous Input (NARX). - J. Hydrol. 567: 743-758. doi: 10.1016/j.jhydrol.2018.01.045

Presentations

  • BRODA, S., WUNSCH, A. & LIESCH, T. (2018): Wochen-, Monats-und Jahreszeitenvorhersage von Grundwasserständen mit künstlichen neuronalen Netzen. - 26. Tagung der Fachsektion Hydrogeologie e. V. in der DGGV e. V., Ruhr-Universität Bochum.
  • BRODA, S., WUNSCH, A., LIESCH, T., GOLDSCHEIDER, N. & REICHLING, J. (2017): Weekly, monthly and seasonal Forecasting of Groundwater Levels using Artificial Neural Networks. - 44th IAH Congress, Dubrovnik, Croatia.
  • NÖLSCHER, M., HEBER, M., CLOS, P., ZAEPKE, M., STOLZ, W. & BRODA, S. (2024): Aktueller Zustand und Vorhersage der Grundwasserstände – eine neue bundesweite Fachanwendung. - 29. Tagung der Fachsektion Hydrogeologie e. V. in der DGGV e. V., RWTH Aachen University.
  • WUNSCH, A., LIESCH, T. & BRODA, S. (2021): Using Convolutional Neural Networks to evaluate Long-Term Groundwater Trends in Germany. - 48th IAH Congress, Brussels, Belgium.
  • WUNSCH, A., LIESCH, T. & BRODA, S. (2020): Groundwater Level Forecasting with Artificial Neural Networks: A Comparison of LSTM, CNN and NARX. - AGU Fall Meeting, San Francisco, CA, USA.
  • WUNSCH, A., LIESCH, T. & BRODA, S. (2019): Uncover Similarities of Groundwater Dynamics with Machine Learning based Hydrograph Clustering. - AGU Fall Meeting, San Francisco, CA, USA.

Partner:

  • State Geological Surveys (SGD)
  • State Environmental Agencies and Water Management Authorities

Contact:

    
Dr. Stefan Broda
Phone: +49-(0)30-36993-250
Fax: +49-(0)511-643-531250

This Page: