Neural network predictions of drawdown from groundwater abstraction in the Egebjerg catchment, Denmark

Mathias Busk Dahl; Troels Norvin Vilhelmsen; Trine Enemark; Thomas Mejer Hansen

doi:10.34194/geusb.v53.8357

Authors

Mathias Busk Dahl Department of Geoscience, Aarhus University, Aarhus, Denmark; NIRAS, Aarhus, Denmark https://orcid.org/0000-0003-4816-0241
Troels Norvin Vilhelmsen NIRAS, Aarhus, Denmark https://orcid.org/0000-0002-6399-8563
Trine Enemark Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark https://orcid.org/0000-0002-3881-2739
Thomas Mejer Hansen Department of Geosciences and Natural Resource Management, University of Copenhagen, Copenhagen, Denmark https://orcid.org/0000-0003-4529-0112

DOI:

https://doi.org/10.34194/geusb.v53.8357

Keywords:

Decision support, Groundwater modelling, Machine learning, Probabilistic neural network, Resource management

Abstract

Results from numerical simulations play a vital role in the decision process of everyday groundwater management. However, these simulations can be time-consuming for large-scale investigations, and it can be necessary to apply approximate methods instead. This study investigates the abilities of a neural network to replicate simulated drawdown from groundwater abstraction in a numerical groundwater model of the Egebjerg catchment, Denmark. We follow a generalised methodology that uses the information within the deterministic numerical model to create a training set for the neural network to learn from and extend the method to work in a 3D Danish groundwater model case. We compare the abilities of the trained neural network with the results of conventional computations in terms of speed and accuracy and argue that this approach has the potential to improve decision support for decision-makers within groundwater management.

Downloads

Download data is not yet available.

References

Abadi, M. et al. 2016: Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467. https://doi.org/10.48550/arXiv.1603.04467

Belitz, K. & Stackelberg, P.E. 2021: Evaluation of six methods for correcting bias in estimates from ensemble tree machine learning regression models. Environmental Modelling & Software 139, 105006. https://doi.org/10.1016/j.envsoft.2021.105006

Dahl, M.B., Vilhelmsen, T.N., Bach, T. & Hansen, T.M. 2023: Hydraulic head change predictions in groundwater models using a probabilistic neural network. Frontiers in Water 5. https://doi.org/10.3389/frwa.2023.1028922

Dillon, J.V. et al. 2017: Tensorflow distributions. arXiv preprint arXiv:1711.10604. https://doi.org/10.48550/arXiv.1711.10604

Enemark, T., Andersen, L.T., Høyer, A.-S., Jensen, K.H., Kidmose, J., Sandersen, P.B.E. & Sonnenborg, T.O. 2022: The influence of layer and voxel geological modelling strategy on groundwater modelling results. Hydrogeology Journal 30(2), 617–635. https://doi.org/10.1007/s10040-021-02442-9

Furtney, J. 2021: Scikit-fmm: The fast marching method for Python. https://github.com/scikit-fmm/scikit-fmm (accessed June 2023).

Gardner, M.W. & Dorling, S.R. 1998: Artificial neural networks (the multilayer perceptron) – A review of applications in the atmospheric sciences. Atmospheric Environment 32, 2627–2636. https://doi.org/10.1016/S1352-2310(97)00447-0

Gorelick, S.M. 1983: A review of distributed parameter groundwater management modeling methods. Water Resources Research 19, 305–319. https://doi.org/10.1029/WR019i002p00305

Green, T.R., Taniguchi, M., Kooi, H., Gurdak, J.J., Allen, D.M., Hiscock, K.M., Treidel, H. & Aureli, A. 2011: Beneath the surface of global change: Impacts of climate change on groundwater. Journal of Hydrology 405(3), 532–560. https://doi.org/10.1016/j.jhydrol.2011.05.002

Hadded, R., Nouiri, I., Alshihabi, O., Mamann, J., Huber, M., Laghouane, A., Yahiaoui, H. & Tarhouni, J. 2013: A decision support system to manage the groundwater of the Zeuss Koutine Aquifer using the WEAP-MODFLOW framework. Water Resources Management 27, 1981–2000. https://doi.org/10.1007/s11269-013-0266-7

Harbaugh, A.W. 2005: MODFLOW-2005, The U.S. Geological Survey modular ground-water model — the ground-water flow process: U.S. Geological Survey Techniques and Methods 6-A16. USGS. https://doi.org/10.3133/tm6A16

Hendrycks, D. & Gimpel, K. 2016: Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415. https://doi.org/10.48550/arXiv.1606.08415

Kingma, D.P. & Ba, J. 2014: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980. https://doi.org/10.48550/arXiv.1412.6980

Johnson, J.M. & Khoshgoftaar, T.M. 2019: Survey on deep learning with class imbalance. Journal of Big Data 6(1), 27. https://doi.org/10.1186/s40537-019-0192-5

Kingma, D.P. & Ba, J. 2014: Adam: A method for stochastic optimization. arXiv Preprint arXiv:1412.6980.

Langevin, C.D., Hughes, J.D., Banta, E.R., Niswonger, R.G., Panday, S. & Provost, A.M. 2017: Documentation for the MODFLOW 6 Groundwater Flow Model. Report. U.S. Geological Survey Techniques and Methods 6-A55. http://pubs.er.usgs.gov/publication/tm6A55 (accessed June 2023).

Langevin, C., Hughes, J., Banta, E., Provost, A., Niswonger, R. & Panday, S. 2019: MODFLOW 6 Modular Hydrologic Model Version 6.1.0. U.S. Geological Survey Software. https://doi.org/10.5066/F76Q1VQV

Pisinaras, V., Petalas, C., Tsihrintzis, V.A. & Zagana, E. 2007: A groundwater flow model for water resources management in the Ismarida plain, North Greece. Environmental Modeling & Assessment 12(2), 75–89. https://doi.org/10.1007/s10666-006-9040-z

Thibaut, R., Laloy, E. & Hermans, T. 2021: A new framework for experimental design using Bayesian Evidential Learning: The case of well-head protection area. Journal of Hydrology 603, 126903. https://doi.org/10.1016/j.jhydrol.2021.126903