A Deep U-Net Framework for Flood Hazard Mapping Using Hydraulic Simulations of the Wupper Catchment
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910158749171712 |
|---|---|
| author | Lammers, Christian Arévalo, Fernando Märker-Neuhaus, Leonie Heinenberg, Daniel Förster, Christian Spies, Karl-Heinz |
| author_facet | Lammers, Christian Arévalo, Fernando Märker-Neuhaus, Leonie Heinenberg, Daniel Förster, Christian Spies, Karl-Heinz |
| contents | The increasing frequency and severity of global flood events highlights the need for the development of rapid and reliable flood prediction tools. This process traditionally relies on computationally expensive hydraulic simulations. This research presents a prediction tool by developing a deep-learning based surrogate model to accurately and efficiently predict the maximum water level across a grid. This was achieved by conducting a series of experiments to optimize a U-Net architecture, patch generation, and data handling for approximating a hydraulic model. This research demonstrates that a deep learning surrogate model can serve as a computationally efficient alternative to traditional hydraulic simulations. The framework was tested using hydraulic simulations of the Wupper catchment in the North-Rhein Westphalia region (Germany), obtaining comparable results. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_21028 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Deep U-Net Framework for Flood Hazard Mapping Using Hydraulic Simulations of the Wupper Catchment Lammers, Christian Arévalo, Fernando Märker-Neuhaus, Leonie Heinenberg, Daniel Förster, Christian Spies, Karl-Heinz Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition The increasing frequency and severity of global flood events highlights the need for the development of rapid and reliable flood prediction tools. This process traditionally relies on computationally expensive hydraulic simulations. This research presents a prediction tool by developing a deep-learning based surrogate model to accurately and efficiently predict the maximum water level across a grid. This was achieved by conducting a series of experiments to optimize a U-Net architecture, patch generation, and data handling for approximating a hydraulic model. This research demonstrates that a deep learning surrogate model can serve as a computationally efficient alternative to traditional hydraulic simulations. The framework was tested using hydraulic simulations of the Wupper catchment in the North-Rhein Westphalia region (Germany), obtaining comparable results. |
| title | A Deep U-Net Framework for Flood Hazard Mapping Using Hydraulic Simulations of the Wupper Catchment |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.21028 |