RT Journal Article
T1 Comparison of artificial neural networks and reservoir models for simulating karst spring discharge on five test sites in the Alpine and Mediterranean regions.
A1 Cinkus, Guillaume
A1 Wunsch, Andreas
A1 Mazzilli, Naomí
A1 Liesch, Tanja
A1 Chen, Zhao
A1 Ravbar, Nataša
A1 Doummar, Joanna
A1 Fernández-Ortega, Jaime
A1 Barberá-Fornell, Juan Antonio
A1 Andreo-Navarro, Bartolomé
A1 Goldscheider, Nico
A1 Jourde, Hervé
K1 Acuíferos
K1 Redes neuronales (Informática)
K1 Mediterráneo (Región)
K1 Minerales carbonatados
AB Hydrological models are widely used to characterize, understand and manage hydrosystems. Lumped parameter models are of particular interest in karst environments given the complexity and heterogeneity of these systems. There is a multitude of lumped parameter modelling approaches, which can make it difficult for a manager or researcher to choose. We therefore conducted a comparison of two lumped parameter modelling approaches: artificial neural networks (ANNs) and reservoir models. We investigate five karst systems in the Mediterranean and Alpine regions with different characteristics in terms of climatic conditions, hydrogeological properties and data availability. We compare the results of ANN and reservoir modelling approaches using several performance criteria over different hydrological periods. The results show that both ANNs and reservoir models can accurately simulate karst spring discharge but also that they have different advantages and drawbacks: (i) ANN models are very flexible regarding the format and amount of input data, (ii) reservoir models can provide good results even with a few years of relevant discharge in the calibration period and (iii) ANN models seem robust for reproducing high-flow conditions, while reservoir models are superior in reproducing low-flow conditions. However, both modelling approaches struggle to reproduce extreme events (droughts, floods), which is a known problem in hydrological modelling. For research purposes, ANN models have been shown to be useful for identifying recharge areas and delineating catchments, based on insights into the input data. Reservoir models are adapted to understand the hydrological functioning of a system by studying model structure and parameters.
PB Copernicus Publications (European Geosciences Union)
YR 2023
FD 2023-05-23
LK https://hdl.handle.net/10630/30134
UL https://hdl.handle.net/10630/30134
LA eng
NO Guillaume Cinkus, Andreas Wunsch, Naomi Mazzilli, Tanja Liesch, Zhao Chen, Nataša Ravbar, Joanna Doummar, Jaime Fernández-Ortega, Juan Antonio Barberá, Bartolomé Andreo, Nico Goldscheider y Hervé Jourde (2023): Comparison of artificial neural networks and reservoir models for simulating karst spring discharge on five test sites in the Alpine and Mediterranean regions. Hydrology and Earth System Sciences, 27: 1961-1985.
NO This research has been supported by the French Ministry of Higher Education and Research for the thesis scholarship of Guillaume Cinkus and the European Commission for its support through the Partnership for Research and Innovation in the Mediterranean Area (PRIMA) programme under Horizon 2020 (KARMA project, grant agreement no. 01DH19022A). The data collection and instrumentation on the Qachqouch catchment were funded by USAID and the National Academy of Science (Peer Science; 705 project award: 102881; Cycle 3) and the KARMA project (L-CNRS in the framework of the PRIMA programme; award no. 103895; project no. 25713). We thank the Slovenian Research Agency for financial support within the project “Infiltration processes in forested karst aquifers under changing environment” (no. J2-1743) and the Karst Research Programme (no. P6-0119). We further thank the National Agency of Research of the Spanish Ministry of Science, 710 Innovation and Universities for the funding of the KARMA project (PCI2019-103675) and the Autonomous Government of Andalusia (Spain) for the funding of Research Group RNM-308.
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 21 ene 2026