Data‐driven flood emulation: Speeding up urban flood predictions by deep convolutional neural networks
Autor: | Guo, Zifeng, Leitao, Joao P., Simoes, Nuno E., Moosavi, Vahid |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2021 |
Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Data-driven emulation lcsh:Disasters and engineering Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition lcsh:TC530-537 convolutional neural network lcsh:TA495 Convolutional neural network Fast water depth prediction Flood modelling lcsh:River protective works. Regulation. Flood control Machine Learning (cs.LG) data‐driven emulation flood modelling Computer Science - Computers and Society Computers and Society (cs.CY) fast water depth prediction |
Zdroj: | Journal of Flood Risk Management, Vol 14, Iss 1, Pp n/a-n/a (2021) Journal of Flood Risk Management, 14 (1) |
Popis: | 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. Journal of Flood Risk Management, 14 (1) |
Databáze: | OpenAIRE |
Externí odkaz: |