02 Nov 2022
02 Nov 2022
Status: this preprint is currently under review for the journal HESS.

Comparison of artificial neural networks and reservoir models for simulating karst spring discharge on five test sites in the Alpine and Mediterranean regions

Guillaume Cinkus1, Andreas Wunsch2, Naomi Mazzilli3, Tanja Liesch2, Zhao Chen4, Nataša Ravbar5, Joanna Doummar6, Jaime Fernández-Ortega7, Juan Antonio Barberá7, Bartolomé Andreo7, Nico Goldscheider2, and Hervé Jourde1 Guillaume Cinkus et al.
  • 1HydroSciences Montpellier (HSM), Univ. Montpellier, CNRS, IRD, 34090 Montpellier, France
  • 2Karlsruhe Institute of Technology (KIT), Institute of Applied Geosciences, Kaiserstr. 12, 76131 Karlsruhe, Germany
  • 3UMR 1114 EMMAH (AU-INRAE), Université d’Avignon, 84000 Avignon, France
  • 4Institute of Groundwater Management, Technical University of Dresden, 01062 Dresden, Germany
  • 5ZRC SAZU, Karst Research Institute, Titov trg 2, 6230 Postojna, Slovenia
  • 6Department of Geology, American University of Beirut, PO Box 11 - 0236/26, Beirut, Lebanon
  • 7Department of Geology and Centre of Hydrogeology, University of Málaga (CEHIUMA), 29071 Málaga, Spain

Abstract. Hydrological models are widely used to characterise, understand and manage hydrosystems. Data-driven models are of particular interest in karst environments given the complexity and heterogeneity of these systems. There is a multitude of data-driven modelling approaches, which can make it difficult for a manager or researcher to choose. We therefore conducted a comparison of two data-driven modelling approaches: artificial neural networks (ANN) 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 ANN 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 short calibration periods, and (iii) ANN models seem robust for reproducing high-flow conditions while reservoir models are superior for 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 shown to be useful to identify recharge areas and delineate catchment, 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.

Guillaume Cinkus et al.

Status: open (until 02 Mar 2023)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on hess-2022-365', Anonymous Referee #1, 24 Nov 2022 reply

Guillaume Cinkus et al.

Guillaume Cinkus et al.


Total article views: 526 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
374 137 15 526 5 5
  • HTML: 374
  • PDF: 137
  • XML: 15
  • Total: 526
  • BibTeX: 5
  • EndNote: 5
Views and downloads (calculated since 02 Nov 2022)
Cumulative views and downloads (calculated since 02 Nov 2022)

Viewed (geographical distribution)

Total article views: 505 (including HTML, PDF, and XML) Thereof 505 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 06 Feb 2023
Short summary
Numerous modelling approaches can be used for studying karst water resources, which can make it difficult for a stakeholder or researcher to choose the appropriate method. We conduct a comparison of two widely used karst modelling approaches: artificial neural networks (ANN) and reservoir models. Results show that ANN models are very flexible and seem great for reproducing high flows. Reservoir models can work with relatively short time series and seem to accurately reproduce low flows.