Articles | Volume 25, issue 1
https://doi.org/10.5194/nhess-25-335-2025
© 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/nhess-25-335-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
23 Jan 2025
Research article |
| 23 Jan 2025
| 23 Jan 2025
Multi-scale hydraulic graph neural networks for flood modelling
Roberto Bentivoglio
CORRESPONDING AUTHOR
Department of Water Management, Faculty of Civil Engineering and Geosciences, Delft University of Technology, Delft, the Netherlands
Elvin Isufi
Department of Intelligent Systems, Faculty of Electrical Engineering, Mathematics and Computer Science, Delft University of Technology, Delft, the Netherlands
Sebastiaan Nicolas Jonkman
Department of Hydraulic Engineering, Faculty of Civil Engineering and Geosciences, Delft University of Technology, Delft, the Netherlands
Riccardo Taormina
Department of Water Management, Faculty of Civil Engineering and Geosciences, Delft University of Technology, Delft, the Netherlands
Viewed
Total article views: 13,181 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 20 Sep 2024)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 8,134 | 3,258 | 1,789 | 13,181 | 287 | 499 |
- HTML: 8,134
- PDF: 3,258
- XML: 1,789
- Total: 13,181
- BibTeX: 287
- EndNote: 499
Total article views: 6,895 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 23 Jan 2025)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 5,245 | 1,508 | 142 | 6,895 | 150 | 288 |
- HTML: 5,245
- PDF: 1,508
- XML: 142
- Total: 6,895
- BibTeX: 150
- EndNote: 288
Total article views: 6,286 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 20 Sep 2024)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 2,889 | 1,750 | 1,647 | 6,286 | 137 | 211 |
- HTML: 2,889
- PDF: 1,750
- XML: 1,647
- Total: 6,286
- BibTeX: 137
- EndNote: 211
Viewed (geographical distribution)
Total article views: 13,181 (including HTML, PDF, and XML)
Thereof 12,744 with geography defined
and 437 with unknown origin.
Total article views: 6,895 (including HTML, PDF, and XML)
Thereof 6,489 with geography defined
and 406 with unknown origin.
Total article views: 6,286 (including HTML, PDF, and XML)
Thereof 6,255 with geography defined
and 31 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
21 citations as recorded by crossref.
- Structural investigation of regime-dependent surrogate representations under controlled hydrodynamic conditions: A Mixture-of-Experts approach J. Zevallos et al. https://doi.org/10.1016/j.envsoft.2026.107135
- Probabilistic flood hazard mapping for dike-breach floods via graph neural networks R. Bentivoglio et al. https://doi.org/10.5194/nhess-26-2089-2026
- Response-pattern-aware graph neural network for rapid compound rainfall-tide urban drainage prediction P. Sun et al. https://doi.org/10.1016/j.jhydrol.2026.136418
- Optimization of water-saving irrigation decision using dynamic spatiotemporal graph neural networks Y. Fang et al. https://doi.org/10.1038/s41598-026-54923-0
- Spatiotemporal Graph Learning on Urban Environments H. Li et al. https://doi.org/10.1021/acs.est.5c12640
- Forecasting of flash flood disasters in small and medium catchments using an improved SVSMR + LSTM model Z. Xu et al. https://doi.org/10.1080/19942060.2026.2678105
- GTNet: A Graph–Transformer Neural Network for Robust Ecological Health Monitoring in Smart Cities M. Aldossary https://doi.org/10.3390/math14010064
- Dual-Attention ResUNet With Masked Focal-Tversky Loss for Robust SAR-Based Flood Mapping A. Das et al. https://doi.org/10.1109/ACCESS.2025.3637023
- An explainable physics-aware deep learning framework with improved spatiotemporal dependence matrices and signal decomposition for multi-station uncertainty daily runoff simulation W. Wu et al. https://doi.org/10.1016/j.jhydrol.2026.135625
- Deep learning techniques for extreme rainfall prediction: a review of state-of-the-art B. Mukhalela et al. https://doi.org/10.3389/frai.2026.1908848
- Predicting flood energy reduction in vegetated open channel: Comparative assessment of hybrid artificial intelligence techniques A. Rezzoug et al. https://doi.org/10.1016/j.engappai.2025.111756
- Generalist–specialist transfer learning for cross-city spatial generalization in pluvial flood prediction Z. Li et al. https://doi.org/10.1016/j.watres.2026.126650
- Levee-breach inundation forecasting with deep-learning and hydrodynamic models: the 2020 Panaro river case study S. Dazzi et al. https://doi.org/10.1080/28375807.2026.2724268
- Convolutional neural network model for rapid prediction of urban flash flood water depth and velocity maps M. Asif et al. https://doi.org/10.1016/j.jhydrol.2026.135601
- A Hydraulically Informed ANN Surrogate Framework for Nonlinear Open-Channel Flow Analysis A. Tawfik & M. Elgamal https://doi.org/10.3390/w18172101
- Integrating XGBoost and SHAP to uncover feature contributions for river network selection across different patterns H. Yu et al. https://doi.org/10.1016/j.jag.2026.105120
- FloodSformer: A transformer-based data-driven model for predicting the 2-D dynamics of fluvial floods M. Pianforini et al. https://doi.org/10.1016/j.envsoft.2025.106599
- A Physical-Enhanced Spatio-Temporal Graph Convolutional Network for River Flow Prediction R. Huang et al. https://doi.org/10.3390/app15169054
- Multi-scale hydraulic graph neural networks for flood modelling R. Bentivoglio et al. https://doi.org/10.5194/nhess-25-335-2025
- Intelligent Synchronization of Machine Learning Models Using Graph Neural Networks: Application to Flood Prediction B. Temelkovski et al. https://doi.org/10.3390/fi18090474
- Mobility vulnerability index for community vulnerability assessment in disaster response J. Patel et al. https://doi.org/10.1038/s44304-026-00212-9
21 citations as recorded by crossref.
- Structural investigation of regime-dependent surrogate representations under controlled hydrodynamic conditions: A Mixture-of-Experts approach J. Zevallos et al. https://doi.org/10.1016/j.envsoft.2026.107135
- Probabilistic flood hazard mapping for dike-breach floods via graph neural networks R. Bentivoglio et al. https://doi.org/10.5194/nhess-26-2089-2026
- Response-pattern-aware graph neural network for rapid compound rainfall-tide urban drainage prediction P. Sun et al. https://doi.org/10.1016/j.jhydrol.2026.136418
- Optimization of water-saving irrigation decision using dynamic spatiotemporal graph neural networks Y. Fang et al. https://doi.org/10.1038/s41598-026-54923-0
- Spatiotemporal Graph Learning on Urban Environments H. Li et al. https://doi.org/10.1021/acs.est.5c12640
- Forecasting of flash flood disasters in small and medium catchments using an improved SVSMR + LSTM model Z. Xu et al. https://doi.org/10.1080/19942060.2026.2678105
- GTNet: A Graph–Transformer Neural Network for Robust Ecological Health Monitoring in Smart Cities M. Aldossary https://doi.org/10.3390/math14010064
- Dual-Attention ResUNet With Masked Focal-Tversky Loss for Robust SAR-Based Flood Mapping A. Das et al. https://doi.org/10.1109/ACCESS.2025.3637023
- An explainable physics-aware deep learning framework with improved spatiotemporal dependence matrices and signal decomposition for multi-station uncertainty daily runoff simulation W. Wu et al. https://doi.org/10.1016/j.jhydrol.2026.135625
- Deep learning techniques for extreme rainfall prediction: a review of state-of-the-art B. Mukhalela et al. https://doi.org/10.3389/frai.2026.1908848
- Predicting flood energy reduction in vegetated open channel: Comparative assessment of hybrid artificial intelligence techniques A. Rezzoug et al. https://doi.org/10.1016/j.engappai.2025.111756
- Generalist–specialist transfer learning for cross-city spatial generalization in pluvial flood prediction Z. Li et al. https://doi.org/10.1016/j.watres.2026.126650
- Levee-breach inundation forecasting with deep-learning and hydrodynamic models: the 2020 Panaro river case study S. Dazzi et al. https://doi.org/10.1080/28375807.2026.2724268
- Convolutional neural network model for rapid prediction of urban flash flood water depth and velocity maps M. Asif et al. https://doi.org/10.1016/j.jhydrol.2026.135601
- A Hydraulically Informed ANN Surrogate Framework for Nonlinear Open-Channel Flow Analysis A. Tawfik & M. Elgamal https://doi.org/10.3390/w18172101
- Integrating XGBoost and SHAP to uncover feature contributions for river network selection across different patterns H. Yu et al. https://doi.org/10.1016/j.jag.2026.105120
- FloodSformer: A transformer-based data-driven model for predicting the 2-D dynamics of fluvial floods M. Pianforini et al. https://doi.org/10.1016/j.envsoft.2025.106599
- A Physical-Enhanced Spatio-Temporal Graph Convolutional Network for River Flow Prediction R. Huang et al. https://doi.org/10.3390/app15169054
- Multi-scale hydraulic graph neural networks for flood modelling R. Bentivoglio et al. https://doi.org/10.5194/nhess-25-335-2025
- Intelligent Synchronization of Machine Learning Models Using Graph Neural Networks: Application to Flood Prediction B. Temelkovski et al. https://doi.org/10.3390/fi18090474
- Mobility vulnerability index for community vulnerability assessment in disaster response J. Patel et al. https://doi.org/10.1038/s44304-026-00212-9
Saved (final revised paper)
Latest update: 20 Sep 2026
Short summary
Deep learning methods are increasingly used as surrogates for spatio-temporal flood models but struggle with generalization and speed. Here, we propose a multi-resolution approach using graph neural networks that predicts dike breach floods across different meshes, topographies, and boundary conditions with high accuracy and up to 1000× speed-ups. The model also generalizes to larger more complex case studies with just one additional simulation for fine-tuning.
Deep learning methods are increasingly used as surrogates for spatio-temporal flood models but...
Altmetrics
Final-revised paper
Preprint