Articles | Volume 26, issue 9
https://doi.org/10.5194/hess-26-2405-2022
https://doi.org/10.5194/hess-26-2405-2022
Research article
 | 
09 May 2022
Research article |  | 09 May 2022

Karst spring discharge modeling based on deep learning using spatially distributed input data

Andreas Wunsch, Tanja Liesch, Guillaume Cinkus, Nataša Ravbar, Zhao Chen, Naomi Mazzilli, Hervé Jourde, and Nico Goldscheider

Data sets

Archive of Hydrological Data ARSO - Slovenian Environment Agency http://vode.arso.gov.si/hidarhiv/

Archive of Meteorological Data ARSO - Slovenian Environment Agency http://www.meteo.si

Time Series of Type Hydrology-Hydrogeology in Le Lez (Méditerranée) Basin - MEDYCYSS Observatory - KARST Observatory Network - OZCAR Critical Zone Network Research Infrastructure SNO KARST https://doi.org/10.15148/CFD01A5B-B7FD-41AA-8884-84DBDDAC767E

E-OBS daily gridded meteorological data for Europe from 1950 to present derived from in-situ observations Copernicus Climate Change Service https://doi.org/10.24381/CDS.151D3EC6

ERA5-Land hourly data from 2001 to present J. Muñoz Sabater https://doi.org/10.24381/CDS.E2161BAC,

Model code and software

AndreasWunsch/CNN_KarstSpringModeling: v0.1 (v0.1) A. Wunsch https://doi.org/10.5281/zenodo.5184692

Pandas-Dev/Pandas: Pandas 1.0.3 The pandas development team https://doi.org/10.5281/zenodo.3509134

Download
Short summary
Modeling complex karst water resources is difficult enough, but often there are no or too few climate stations available within or close to the catchment to deliver input data for modeling purposes. We apply image recognition algorithms to time-distributed, spatially gridded meteorological data to simulate karst spring discharge. Our models can also learn the approximate catchment location of a spring independently.