Preprints
https://doi.org/10.5194/hess-2024-63
https://doi.org/10.5194/hess-2024-63
15 Mar 2024
 | 15 Mar 2024
Status: a revised version of this preprint is currently under review for the journal HESS.

Enhancing generalizability of data-driven urban flood models by incorporating contextual information

Tabea Cache, Milton Salvador Gomez, Tom Beucler, Jovan Blagojevic, João Paulo Leitao, and Nadav Peleg

Abstract. Fast urban pluvial flood models are necessary for a range of applications, such as near real-time flood nowcasting or processing large rainfall ensembles for uncertainty analysis. Data-driven models can help overcome the long computational time of traditional flood simulation models, and the state-of-the-art models have shown promising accuracy. Yet the lack of generalizability of urban pluvial flood data-driven models to both terrain and rainfall events still limits their application. These models usually adopt a patch-based framework to overcome multiple bottlenecks, such as data availability and computational and memory constraints. However, this approach does not incorporate contextual information of the terrain surrounding the small image patch (typically 256 m x 256 m). We propose a new deep-learning model that maintains the high-resolution information of the local patch and incorporates a larger context to increase the visual field of the model with the aim of enhancing the generalizability of urban pluvial flood data-driven models. We trained and tested the model in the city of Zurich (Switzerland), at a spatial resolution of 1 m, for 1-hour rainfall events at 5 min temporal resolution. We demonstrate that our model can faithfully represent flood depths for a wide range of rainfall events, with peak rainfall intensities ranging from 42.5 mm h-1 to 161.4 mm h-1. Then, we assessed the model’s terrain generalizability in distinct urban settings, namely Luzern (Switzerland) and Singapore. The model accurately identifies locations of water accumulation, which constitutes an improvement compared to other deep-learning models. Using transfer learning, the model was successfully retrained in the new cities, requiring only a single rainfall event to adapt the model to new terrains while preserving adaptability across diverse rainfall conditions. Our results indicate that by incorporating contextual terrain information into the local patches, our proposed model effectively generates high-resolution urban pluvial flood maps, demonstrating applicability across varied terrains and rainfall events.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Tabea Cache, Milton Salvador Gomez, Tom Beucler, Jovan Blagojevic, João Paulo Leitao, and Nadav Peleg

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on hess-2024-63', Anonymous Referee #1, 19 Mar 2024
    • AC1: 'Reply on RC1', Tabea Cache, 21 Mar 2024
  • RC2: 'Comment on hess-2024-63', Anonymous Referee #2, 11 May 2024
    • AC2: 'Reply on RC2', Tabea Cache, 14 May 2024
Tabea Cache, Milton Salvador Gomez, Tom Beucler, Jovan Blagojevic, João Paulo Leitao, and Nadav Peleg
Tabea Cache, Milton Salvador Gomez, Tom Beucler, Jovan Blagojevic, João Paulo Leitao, and Nadav Peleg

Viewed

Total article views: 612 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
445 133 34 612 55 26 23
  • HTML: 445
  • PDF: 133
  • XML: 34
  • Total: 612
  • Supplement: 55
  • BibTeX: 26
  • EndNote: 23
Views and downloads (calculated since 15 Mar 2024)
Cumulative views and downloads (calculated since 15 Mar 2024)

Viewed (geographical distribution)

Total article views: 586 (including HTML, PDF, and XML) Thereof 586 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 24 Jul 2024
Download
Short summary
We introduce a new deep-learning model that addresses limitations of existing urban flood models in handling varied terrains and rainfall events. Our model subdivides the city into small patches and presents a novel approach to incorporate broader spatial information. It accurately predicts high-resolution flood maps across diverse rainfall events and cities (on a minutes and meters scale) that haven’t been seen by the model, which offers valuable insights for urban flood mitigation strategies.