03 Nov 2022
03 Nov 2022
Status: a revised version of this preprint is currently under review for the journal NHESS.

Transferability of data-driven models to predict urban pluvial flood water depth in Berlin, Germany

Omar Seleem, Georgy Ayzel, Axel Bronstert, and Maik Heistermann Omar Seleem et al.
  • Chair of Hydrology, Institute of Environmental Science and Geography, University of Potsdam

Abstract. Data-driven models have been recently suggested to surrogate computationally expensive hydrodynamic models to map flood hazards. However, most studies focused on developing models for the same area or the same precipitation event. It is hence not obvious how transferable the models are in space. This study evaluates the performance of a convolutional neural network (CNN) based on the U-Net architecture and the random forest (RF) algorithm to predict flood water depth, the models' transferability in space and performance improvement using transfer learning techniques. We used three study areas in Berlin to train, validate and test the models. The results showed that (1) the RF models outperformed the CNN models for predictions within the training domain, presumable at the cost of overfitting; (2) the CNN models had significantly higher potential than the RF models to generalize beyond the training domain; and (3) the CNN models could better benefit from transfer learning technique to boost their performance outside training domains than RF models.

Omar Seleem et al.

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on nhess-2022-263', Anonymous Referee #1, 07 Nov 2022
    • AC1: 'Reply on RC1', Omar Seleem, 19 Dec 2022
  • RC2: 'Comment on nhess-2022-263', Anonymous Referee #2, 16 Nov 2022
    • AC2: 'Reply on RC2', Omar Seleem, 19 Dec 2022
      • AC3: 'Reply on AC2', Omar Seleem, 19 Dec 2022

Omar Seleem et al.

Omar Seleem et al.


Total article views: 510 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
399 95 16 510 6 5
  • HTML: 399
  • PDF: 95
  • XML: 16
  • Total: 510
  • BibTeX: 6
  • EndNote: 5
Views and downloads (calculated since 03 Nov 2022)
Cumulative views and downloads (calculated since 03 Nov 2022)

Viewed (geographical distribution)

Total article views: 496 (including HTML, PDF, and XML) Thereof 496 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 04 Feb 2023
Short summary
Data-driven models are raising as a surrogate that overcomes the limitations of the computationally expensive two-dimensional hydrodynamic models to map urban flood hazards. However, the models' ability to generalise outside the training domain is still a major challenge. We evaluate the performance of random forest and convolutional neural networks to predict urban floodwater depth and extent and examine their transferability outside the training domain.