Neural network predictions of drawdown from groundwater abstraction in the Egebjerg catchment, Denmark
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Neural network predictions of drawdown from groundwater abstraction in the Egebjerg catchment, Denmark. / Dahl, Mathias Busk; Vilhelmsen, Troels Norvin; Enemark, Trine; Hansen, Thomas Mejer.
In: GEUS Bulletin, Vol. 53, 8357, 2023.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Neural network predictions of drawdown from groundwater abstraction in the Egebjerg catchment, Denmark
AU - Dahl, Mathias Busk
AU - Vilhelmsen, Troels Norvin
AU - Enemark, Trine
AU - Hansen, Thomas Mejer
N1 - Publisher Copyright: © 2023, GEUS - Geological Survey of Denmark and Greenland. All rights reserved.
PY - 2023
Y1 - 2023
N2 - Results from numerical simulations play a vital role in the decision process of everyday groundwa-ter 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.
AB - Results from numerical simulations play a vital role in the decision process of everyday groundwa-ter 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.
KW - decision support
KW - groundwater modelling
KW - machine learning
KW - probabilistic neural network
KW - resource management
U2 - 10.34194/geusb.v53.8357
DO - 10.34194/geusb.v53.8357
M3 - Journal article
AN - SCOPUS:85176910935
VL - 53
JO - GEUS Bulletin
JF - GEUS Bulletin
SN - 2597-2162
M1 - 8357
ER -
ID: 376451847