Articles | Volume 27, issue 23
https://doi.org/10.5194/hess-27-4227-2023
© Author(s) 2023. 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-27-4227-2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
30 Nov 2023
Research article |
| 30 Nov 2023
| 30 Nov 2023
Rapid spatio-temporal flood modelling via hydraulics-based graph neural networks
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: 6,258 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 22 Mar 2023)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 4,714 | 1,455 | 89 | 6,258 | 100 | 97 |
- HTML: 4,714
- PDF: 1,455
- XML: 89
- Total: 6,258
- BibTeX: 100
- EndNote: 97
Total article views: 4,436 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 30 Nov 2023)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 3,582 | 790 | 64 | 4,436 | 72 | 81 |
- HTML: 3,582
- PDF: 790
- XML: 64
- Total: 4,436
- BibTeX: 72
- EndNote: 81
Total article views: 1,822 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 22 Mar 2023)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 1,132 | 665 | 25 | 1,822 | 28 | 16 |
- HTML: 1,132
- PDF: 665
- XML: 25
- Total: 1,822
- BibTeX: 28
- EndNote: 16
Viewed (geographical distribution)
Total article views: 6,258 (including HTML, PDF, and XML)
Thereof 6,047 with geography defined
and 211 with unknown origin.
Total article views: 4,436 (including HTML, PDF, and XML)
Thereof 4,310 with geography defined
and 126 with unknown origin.
Total article views: 1,822 (including HTML, PDF, and XML)
Thereof 1,737 with geography defined
and 85 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
24 citations as recorded by crossref.
- Real-Time Urban Flood Depth Mapping: Convolutional Neural Networks for Pluvial and Fluvial Flood Emulation M. El baida et al. 10.1007/s11269-024-03886-w
- Multifidelity graph neural networks for efficient and accurate mesh‐based partial differential equations surrogate modeling M. Taghizadeh et al. 10.1111/mice.13312
- Drowning overconfidence with uncertainty: mitigating deep learning overconfidence in flood depth super-resolution through maximum entropy regularization M. El baida et al. 10.1007/s00477-025-02917-1
- A Systematic Literature Review on Classification Machine Learning for Urban Flood Hazard Mapping M. El baida et al. 10.1007/s11269-024-03940-7
- Artificial intelligence for flood risk management: A comprehensive state-of-the-art review and future directions Z. Liu et al. 10.1016/j.ijdrr.2024.105110
- On the accuracy requirement of surrogate models for adequate global sensitivity analysis of urban low-impact development model K. Yi et al. 10.1016/j.jhydrol.2025.133102
- SwinFlood: A hybrid CNN-Swin Transformer model for rapid spatiotemporal flood simulation W. Song et al. 10.1016/j.jhydrol.2025.133280
- Multi-scale hydraulic graph neural networks for flood modelling R. Bentivoglio et al. 10.5194/nhess-25-335-2025
- A priori physical information to aid generalization capabilities of neural networks for hydraulic modeling G. Guglielmo et al. 10.3389/fcpxs.2024.1508091
- Automatic analysis method for topological relationship between river network and hydrological stations Y. Wang et al. 10.1016/j.envsoft.2025.106558
- A conceptual model to quantify probabilistic dike breach outflow L. Besseling et al. 10.1007/s11069-025-07500-z
- Predicting Flood Inundation after a Dike Breach Using a Long Short-Term Memory (LSTM) Neural Network L. Besseling et al. 10.3390/hydrology11090152
- FloodSformer: A transformer-based data-driven model for predicting the 2-D dynamics of fluvial floods M. Pianforini et al. 10.1016/j.envsoft.2025.106599
- Generation and selection of training events for surrogate flood inundation models N. Fraehr et al. 10.1016/j.jenvman.2024.123570
- Smart Hydrology: The Role of Artificial Intelligence in Sustainable Soil and Water Resource Management P. Kharat et al. 10.18311/jmmf/2025/48871
- U-RNN high-resolution spatiotemporal nowcasting of urban flooding X. Cao et al. 10.1016/j.jhydrol.2025.133117
- Assessment of surrogate models for flood inundation: The physics-guided LSG model vs. state-of-the-art machine learning models N. Fraehr et al. 10.1016/j.watres.2024.121202
- Real-time flood maps forecasting for dam-break scenarios with a transformer-based deep learning model M. Pianforini et al. 10.1016/j.jhydrol.2024.131169
- Transferable and data efficient metamodeling of storm water system nodal depths using auto-regressive graph neural networks A. Garzón et al. 10.1016/j.watres.2024.122396
- Interpretable physics‐informed graph neural networks for flood forecasting M. Taghizadeh et al. 10.1111/mice.13484
- Rapid spatio-temporal flood modelling via hydraulics-based graph neural networks R. Bentivoglio et al. 10.5194/hess-27-4227-2023
- Real time probabilistic inundation forecasts using a LSTM neural network F. Hop et al. 10.1016/j.jhydrol.2024.131082
- Spatial-temporal graph neural networks for groundwater data M. Taccari et al. 10.1038/s41598-024-75385-2
- LSTM-based autoencoder models for real-time quality control of wastewater treatment sensor data S. Seshan et al. 10.2166/hydro.2024.167
20 citations as recorded by crossref.
- Real-Time Urban Flood Depth Mapping: Convolutional Neural Networks for Pluvial and Fluvial Flood Emulation M. El baida et al. 10.1007/s11269-024-03886-w
- Multifidelity graph neural networks for efficient and accurate mesh‐based partial differential equations surrogate modeling M. Taghizadeh et al. 10.1111/mice.13312
- Drowning overconfidence with uncertainty: mitigating deep learning overconfidence in flood depth super-resolution through maximum entropy regularization M. El baida et al. 10.1007/s00477-025-02917-1
- A Systematic Literature Review on Classification Machine Learning for Urban Flood Hazard Mapping M. El baida et al. 10.1007/s11269-024-03940-7
- Artificial intelligence for flood risk management: A comprehensive state-of-the-art review and future directions Z. Liu et al. 10.1016/j.ijdrr.2024.105110
- On the accuracy requirement of surrogate models for adequate global sensitivity analysis of urban low-impact development model K. Yi et al. 10.1016/j.jhydrol.2025.133102
- SwinFlood: A hybrid CNN-Swin Transformer model for rapid spatiotemporal flood simulation W. Song et al. 10.1016/j.jhydrol.2025.133280
- Multi-scale hydraulic graph neural networks for flood modelling R. Bentivoglio et al. 10.5194/nhess-25-335-2025
- A priori physical information to aid generalization capabilities of neural networks for hydraulic modeling G. Guglielmo et al. 10.3389/fcpxs.2024.1508091
- Automatic analysis method for topological relationship between river network and hydrological stations Y. Wang et al. 10.1016/j.envsoft.2025.106558
- A conceptual model to quantify probabilistic dike breach outflow L. Besseling et al. 10.1007/s11069-025-07500-z
- Predicting Flood Inundation after a Dike Breach Using a Long Short-Term Memory (LSTM) Neural Network L. Besseling et al. 10.3390/hydrology11090152
- FloodSformer: A transformer-based data-driven model for predicting the 2-D dynamics of fluvial floods M. Pianforini et al. 10.1016/j.envsoft.2025.106599
- Generation and selection of training events for surrogate flood inundation models N. Fraehr et al. 10.1016/j.jenvman.2024.123570
- Smart Hydrology: The Role of Artificial Intelligence in Sustainable Soil and Water Resource Management P. Kharat et al. 10.18311/jmmf/2025/48871
- U-RNN high-resolution spatiotemporal nowcasting of urban flooding X. Cao et al. 10.1016/j.jhydrol.2025.133117
- Assessment of surrogate models for flood inundation: The physics-guided LSG model vs. state-of-the-art machine learning models N. Fraehr et al. 10.1016/j.watres.2024.121202
- Real-time flood maps forecasting for dam-break scenarios with a transformer-based deep learning model M. Pianforini et al. 10.1016/j.jhydrol.2024.131169
- Transferable and data efficient metamodeling of storm water system nodal depths using auto-regressive graph neural networks A. Garzón et al. 10.1016/j.watres.2024.122396
- Interpretable physics‐informed graph neural networks for flood forecasting M. Taghizadeh et al. 10.1111/mice.13484
4 citations as recorded by crossref.
- Rapid spatio-temporal flood modelling via hydraulics-based graph neural networks R. Bentivoglio et al. 10.5194/hess-27-4227-2023
- Real time probabilistic inundation forecasts using a LSTM neural network F. Hop et al. 10.1016/j.jhydrol.2024.131082
- Spatial-temporal graph neural networks for groundwater data M. Taccari et al. 10.1038/s41598-024-75385-2
- LSTM-based autoencoder models for real-time quality control of wastewater treatment sensor data S. Seshan et al. 10.2166/hydro.2024.167
Latest update: 30 Aug 2025
Short summary
To overcome the computational cost of numerical models, we propose a deep-learning approach inspired by hydraulic models that can simulate the spatio-temporal evolution of floods. We show that the model can rapidly predict dike breach floods over different topographies and breach locations, with limited use of ground-truth data.
To overcome the computational cost of numerical models, we propose a deep-learning approach...
