Articles | Volume 29, issue 19
https://doi.org/10.5194/hess-29-5005-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/hess-29-5005-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
08 Oct 2025
Research article |
| 08 Oct 2025
| 08 Oct 2025
How well do process-based and data-driven hydrological models learn from limited discharge data?
Maria Staudinger
CORRESPONDING AUTHOR
Department of Geography, University of Zurich, Winterthurerstrasse 190, 8057 Zurich, Switzerland
Anna Herzog
Department of Hydrology and Climatology, Institute of Environmental Science and Geography, University of Potsdam, Potsdam, Germany
Ralf Loritz
Institute of Water and Environment, Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany
Tobias Houska
Department of Landscape Ecology and Resources Management, University of Gießen, Gießen, Germany
Sandra Pool
Department Water Resources and Drinking Water, Eawag – Swiss Federal Institute of Aquatic Science and Technology, Dübendorf, Switzerland
Diana Spieler
Department of Hydrosciences, Institute of Hydrology and Meteorology, TUD Dresden University of Technology, Dresden, Germany
now at: Schulich School of Engineering, University of Calgary, Calgary, Canada
Paul D. Wagner
Department of Hydrology and Water Resources Management, Institute for Natural Resource Conservation, Kiel University, Kiel, Germany
Juliane Mai
Earth and Environmental Science, University of Waterloo, Waterloo, Ontario, Canada
Jens Kiesel
Department of Hydrology and Water Resources Management, Institute for Natural Resource Conservation, Kiel University, Kiel, Germany
Stone Environmental, 535 Stone Cutters Way, 05602 Montpelier, VT, USA
Stephan Thober
Computational Hydrosystems, Helmholtz Centre for Environmental Research – UFZ, Leipzig, Germany
Björn Guse
Department of Hydrology and Water Resources Management, Institute for Natural Resource Conservation, Kiel University, Kiel, Germany
German Research Centre for Geosciences, Section Hydrology, Potsdam, Germany
Uwe Ehret
Institute of Water and Environment, Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany
Viewed
Total article views: 7,537 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 14 Mar 2025)
| HTML | XML | Total | Supplement | BibTeX | EndNote | |
|---|---|---|---|---|---|---|
| 5,806 | 1,511 | 220 | 7,537 | 398 | 192 | 237 |
- HTML: 5,806
- PDF: 1,511
- XML: 220
- Total: 7,537
- Supplement: 398
- BibTeX: 192
- EndNote: 237
Total article views: 3,404 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 08 Oct 2025)
| HTML | XML | Total | Supplement | BibTeX | EndNote | |
|---|---|---|---|---|---|---|
| 2,913 | 380 | 111 | 3,404 | 106 | 82 | 86 |
- HTML: 2,913
- PDF: 380
- XML: 111
- Total: 3,404
- Supplement: 106
- BibTeX: 82
- EndNote: 86
Total article views: 4,133 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 14 Mar 2025)
| HTML | XML | Total | Supplement | BibTeX | EndNote | |
|---|---|---|---|---|---|---|
| 2,893 | 1,131 | 109 | 4,133 | 292 | 110 | 151 |
- HTML: 2,893
- PDF: 1,131
- XML: 109
- Total: 4,133
- Supplement: 292
- BibTeX: 110
- EndNote: 151
Viewed (geographical distribution)
Total article views: 7,537 (including HTML, PDF, and XML)
Thereof 7,374 with geography defined
and 163 with unknown origin.
Total article views: 3,404 (including HTML, PDF, and XML)
Thereof 3,273 with geography defined
and 131 with unknown origin.
Total article views: 4,133 (including HTML, PDF, and XML)
Thereof 4,101 with geography defined
and 32 with unknown origin.
| Country | # | Views | % |
|---|
| Country | # | Views | % |
|---|
| Country | # | Views | % |
|---|
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
Cited
8 citations as recorded by crossref.
- Distinct relationships between multidimensional urban green space characteristics and urban heat island effect across local climate zones Q. Cai et al. https://doi.org/10.1016/j.eiar.2026.108636
- When physics gets in the way: an entropy-based evaluation of conceptual constraints in hybrid hydrological models M. Álvarez Chaves et al. https://doi.org/10.5194/hess-30-629-2026
- A non-equilibrium thermodynamics framework for daily simulation of coupled water and heat transport in variably saturated and frozen soils I. Borzì https://doi.org/10.1016/j.advwatres.2026.105257
- A Hybrid Rank-Preserving and Evolutionary Algorithm for Multisite Daily Streamflow Simulation S. Pitulić et al. https://doi.org/10.3390/a19070541
- A dynamic-gated Mixture-of-Experts framework improves and interprets daily streamflow simulation W. Yuan et al. https://doi.org/10.1038/s43247-026-03799-z
- Deriving groundwater storage anomalies based on GRACE data and drought prediction using deep learning Y. Tian et al. https://doi.org/10.7717/peerj-cs.3459
- Blending-ensemble LSTM-SVR Modeling for Streamflow Prediction with Limited Data Series Based on Tree-structured Parzen Estimator Bayesian Optimization J. Zhang et al. https://doi.org/10.1007/s11269-026-04619-x
- Deep Learning-Based Monthly Runoff Simulation in Changing Environments: Enhancing Accuracy by Reducing Data Redundancy S. Liu et al. https://doi.org/10.1007/s11269-026-04680-6
8 citations as recorded by crossref.
- Distinct relationships between multidimensional urban green space characteristics and urban heat island effect across local climate zones Q. Cai et al. https://doi.org/10.1016/j.eiar.2026.108636
- When physics gets in the way: an entropy-based evaluation of conceptual constraints in hybrid hydrological models M. Álvarez Chaves et al. https://doi.org/10.5194/hess-30-629-2026
- A non-equilibrium thermodynamics framework for daily simulation of coupled water and heat transport in variably saturated and frozen soils I. Borzì https://doi.org/10.1016/j.advwatres.2026.105257
- A Hybrid Rank-Preserving and Evolutionary Algorithm for Multisite Daily Streamflow Simulation S. Pitulić et al. https://doi.org/10.3390/a19070541
- A dynamic-gated Mixture-of-Experts framework improves and interprets daily streamflow simulation W. Yuan et al. https://doi.org/10.1038/s43247-026-03799-z
- Deriving groundwater storage anomalies based on GRACE data and drought prediction using deep learning Y. Tian et al. https://doi.org/10.7717/peerj-cs.3459
- Blending-ensemble LSTM-SVR Modeling for Streamflow Prediction with Limited Data Series Based on Tree-structured Parzen Estimator Bayesian Optimization J. Zhang et al. https://doi.org/10.1007/s11269-026-04619-x
- Deep Learning-Based Monthly Runoff Simulation in Changing Environments: Enhancing Accuracy by Reducing Data Redundancy S. Liu et al. https://doi.org/10.1007/s11269-026-04680-6
Saved (final revised paper)
Latest update: 20 Sep 2026
Short summary
Three process-based and four data-driven hydrological models are compared using different training data. We found that process-based models perform better with small datasets but stop learning soon, while data-driven models learn longer. The study highlights the importance of memory in data and the impact of different data sampling methods on model performance. The direct comparison of these models is novel and provides a clear understanding of their performance under various data conditions.
Three process-based and four data-driven hydrological models are compared using different...
