Articles | Volume 29, issue 5
https://doi.org/10.5194/hess-29-1277-2025
© 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-29-1277-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
11 Mar 2025
Research article |
| 11 Mar 2025
| 11 Mar 2025
Analyzing the generalization capabilities of a hybrid hydrological model for extrapolation to extreme events
Eduardo Acuña Espinoza
CORRESPONDING AUTHOR
Institute of Water and Environment, Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany
Ralf Loritz
Institute of Water and Environment, Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany
Frederik Kratzert
Google Research, Vienna, Austria
Daniel Klotz
Google Research, Vienna, Austria
Helmholtz Centre for Environmental Research (UFZ), Leipzig, Germany
Martin Gauch
Google Research, Zurich, Switzerland
Manuel Álvarez Chaves
Stuttgart Center for Simulation Science, Statistical Model-Data Integration, University of Stuttgart, Stuttgart, Germany
Uwe Ehret
Institute of Water and Environment, Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany
Viewed
Total article views: 8,546 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 30 Jul 2024)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 5,731 | 1,678 | 1,137 | 8,546 | 180 | 250 |
- HTML: 5,731
- PDF: 1,678
- XML: 1,137
- Total: 8,546
- BibTeX: 180
- EndNote: 250
Total article views: 3,395 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 11 Mar 2025)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 2,827 | 483 | 85 | 3,395 | 97 | 109 |
- HTML: 2,827
- PDF: 483
- XML: 85
- Total: 3,395
- BibTeX: 97
- EndNote: 109
Total article views: 5,151 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 30 Jul 2024)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 2,904 | 1,195 | 1,052 | 5,151 | 83 | 141 |
- HTML: 2,904
- PDF: 1,195
- XML: 1,052
- Total: 5,151
- BibTeX: 83
- EndNote: 141
Viewed (geographical distribution)
Total article views: 8,546 (including HTML, PDF, and XML)
Thereof 8,454 with geography defined
and 92 with unknown origin.
Total article views: 3,395 (including HTML, PDF, and XML)
Thereof 3,312 with geography defined
and 83 with unknown origin.
Total article views: 5,151 (including HTML, PDF, and XML)
Thereof 5,142 with geography defined
and 9 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
19 citations as recorded by crossref.
- BiasCast: learning and adjusting real time biases from meteorological forecasts to enhance runoff predictions O. Konold et al. https://doi.org/10.5194/hess-30-5067-2026
- Riverine heatwaves are an emergent climate change risk A. van Hamel et al. https://doi.org/10.1038/s44221-025-00541-5
- A hybrid method coupling physical process-driven model with generative deep learning for probabilistic flood forecasting X. Yang et al. https://doi.org/10.1016/j.jhydrol.2026.135319
- Process-Driven Cross-Factor Integration of SWAT and Interpretable Machine Learning for Enhancing Riverine Total Nitrogen Prediction X. Xi et al. https://doi.org/10.1021/acsestwater.5c01391
- A physics-informed geospatial machine-learning downscaling framework for improving extreme rainfall K. He et al. https://doi.org/10.1016/j.geosus.2026.100513
- River temperature response to atmospheric heatwaves is modulated by discharge and meltwater A. van Hamel et al. https://doi.org/10.1038/s43247-026-03269-6
- Hybrid models generalize better to warmer climate conditions than process-based and purely data-driven models J. Bohl et al. https://doi.org/10.5194/hess-30-4667-2026
- A comparative study of deep learning and process-based models for hourly flood simulation under a unified input and optimization framework S. Gao et al. https://doi.org/10.1016/j.envsoft.2026.107101
- A physically guided and interpretable SWAT-BiLSTM framework with Bayesian optimization for bias correction in daily streamflow forecasting L. Jin et al. https://doi.org/10.1016/j.jconhyd.2026.104952
- Spatially resolved rainfall streamflow modeling in central Europe M. Vischer et al. https://doi.org/10.5194/hess-29-5233-2025
- How well do hydrological models simulate streamflow extremes and drought-to-flood transitions? E. Muñoz-Castro et al. https://doi.org/10.5194/hess-30-825-2026
- Unveiling the limits of deep learning models in hydrological extrapolation tasks S. Baste et al. https://doi.org/10.5194/hess-29-5871-2025
- Development and implementation of a passive surveillance system for Aedes albopictus in Emilia-Romagna, Italy M. Blaha et al. https://doi.org/10.1016/j.ecoinf.2026.103718
- Never Train a Deep Learning Model on a Single Well? Revisiting Training Strategies for Groundwater Level Prediction M. Ohmer & T. Liesch https://doi.org/10.5194/hess-30-2373-2026
- A variational approach at uncertainty estimation in data-driven rainfall-runoff modeling M. Álvarez Chaves et al. https://doi.org/10.1088/3049-4753/ae89ba
- Integrating deep learning and multi-objective optimization for floodwater utilization: a coordinated surface water-groundwater regulation framework for groundwater recovery L. Zhang et al. https://doi.org/10.1016/j.jhydrol.2025.134749
- Fast urban flood modeling informing response decisions: Model development and future perspectives T. Duan et al. https://doi.org/10.1016/j.aei.2025.104152
- Uncertainty in estimating the relative change of design floods under climate change: a stylized experiment with process-based, deep learning, and hybrid models S. Poudel et al. https://doi.org/10.1016/j.jhydrol.2025.134427
- Benchmark-guided insights into hybrid process-based-deep learning models for continental-scale streamflow prediction across the United States D. Sourya et al. https://doi.org/10.1016/j.ejrh.2026.103636
19 citations as recorded by crossref.
- BiasCast: learning and adjusting real time biases from meteorological forecasts to enhance runoff predictions O. Konold et al. https://doi.org/10.5194/hess-30-5067-2026
- Riverine heatwaves are an emergent climate change risk A. van Hamel et al. https://doi.org/10.1038/s44221-025-00541-5
- A hybrid method coupling physical process-driven model with generative deep learning for probabilistic flood forecasting X. Yang et al. https://doi.org/10.1016/j.jhydrol.2026.135319
- Process-Driven Cross-Factor Integration of SWAT and Interpretable Machine Learning for Enhancing Riverine Total Nitrogen Prediction X. Xi et al. https://doi.org/10.1021/acsestwater.5c01391
- A physics-informed geospatial machine-learning downscaling framework for improving extreme rainfall K. He et al. https://doi.org/10.1016/j.geosus.2026.100513
- River temperature response to atmospheric heatwaves is modulated by discharge and meltwater A. van Hamel et al. https://doi.org/10.1038/s43247-026-03269-6
- Hybrid models generalize better to warmer climate conditions than process-based and purely data-driven models J. Bohl et al. https://doi.org/10.5194/hess-30-4667-2026
- A comparative study of deep learning and process-based models for hourly flood simulation under a unified input and optimization framework S. Gao et al. https://doi.org/10.1016/j.envsoft.2026.107101
- A physically guided and interpretable SWAT-BiLSTM framework with Bayesian optimization for bias correction in daily streamflow forecasting L. Jin et al. https://doi.org/10.1016/j.jconhyd.2026.104952
- Spatially resolved rainfall streamflow modeling in central Europe M. Vischer et al. https://doi.org/10.5194/hess-29-5233-2025
- How well do hydrological models simulate streamflow extremes and drought-to-flood transitions? E. Muñoz-Castro et al. https://doi.org/10.5194/hess-30-825-2026
- Unveiling the limits of deep learning models in hydrological extrapolation tasks S. Baste et al. https://doi.org/10.5194/hess-29-5871-2025
- Development and implementation of a passive surveillance system for Aedes albopictus in Emilia-Romagna, Italy M. Blaha et al. https://doi.org/10.1016/j.ecoinf.2026.103718
- Never Train a Deep Learning Model on a Single Well? Revisiting Training Strategies for Groundwater Level Prediction M. Ohmer & T. Liesch https://doi.org/10.5194/hess-30-2373-2026
- A variational approach at uncertainty estimation in data-driven rainfall-runoff modeling M. Álvarez Chaves et al. https://doi.org/10.1088/3049-4753/ae89ba
- Integrating deep learning and multi-objective optimization for floodwater utilization: a coordinated surface water-groundwater regulation framework for groundwater recovery L. Zhang et al. https://doi.org/10.1016/j.jhydrol.2025.134749
- Fast urban flood modeling informing response decisions: Model development and future perspectives T. Duan et al. https://doi.org/10.1016/j.aei.2025.104152
- Uncertainty in estimating the relative change of design floods under climate change: a stylized experiment with process-based, deep learning, and hybrid models S. Poudel et al. https://doi.org/10.1016/j.jhydrol.2025.134427
- Benchmark-guided insights into hybrid process-based-deep learning models for continental-scale streamflow prediction across the United States D. Sourya et al. https://doi.org/10.1016/j.ejrh.2026.103636
Saved (final revised paper)
Latest update: 16 Aug 2026
Short summary
Data-driven techniques have shown the potential to outperform process-based models in rainfall–runoff simulations. Hybrid models, combining both approaches, aim to enhance accuracy and maintain interpretability. Expanding the set of test cases to evaluate hybrid models under different conditions, we test their generalization capabilities for extreme hydrological events.
Data-driven techniques have shown the potential to outperform process-based models in...
