Data‐driven flood emulation: Speeding up urban flood predictions by deep convolutional neural networks


Loading...

Date

2021-03

Publication Type

Journal Article

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

Computational complexity has been the bottleneck for applying physically based simulations in large urban areas with high spatial resolution for efficient and systematic flooding analyses and risk assessment. To overcome the issue of long computational time and accelerate the prediction process, this paper proposes that the prediction of maximum water depth can be considered an image‐to‐image translation problem in which water depth rasters are generated using the information learned from data instead of by conducting simulations. The proposed data‐driven urban pluvial flood approach is based on a deep convolutional neural network trained using flood simulation data obtained from three catchments and 18 hyetographs. Multiple tests to assess the accuracy and validity of the proposed approach were conducted with both design and real hyetographs. The results show that flood prediction based on neural networks use only 0.5% of the time compared with that of physically based models, with promising accuracy and generalizability. The proposed neural network can also potentially be applied to different but relevant problems, including flood analysis for flood‐safe urban layout planning.

Publication status

published

Editor

Book title

Volume

14 (1)

Pages / Article No.

e12684

Publisher

Wiley

Event

Edition / version

Methods

Geographic location

Date collected

Date created

Subject

Convolutional neural network; Data-driven emulation; Fast water depth prediction; Flood modelling

Organisational unit

Notes

Funding Info about funding

Related publications and datasets