A deep convolutional neural network model for rapid prediction of fluvial flood inundation

JOURNAL OF HYDROLOGY

卷:590

Article

Kabir, Syed^1,2  Patidar, Sandhya²  Xia, Xilin¹  Liang, Qiuhua¹  Neal, Jeffrey³  Pender, Gareth² 

[1] Loughborough Univ, Sch Architecture Bldg & Civil Engn, Loughborough LE11 3TU, Leics, England

[2] Heriot Watt Univ, Sch Energy Geosci Infrastruct & Soc, Edinburgh, Midlothian, Scotland

[3] Univ Bristol, Sch Geog Sci, Bristol, Avon, England

关键词: Rapid flood modelling;    Deep learning;    Convolutional neural network;    Machine learning;    Flood inundation;   

DOI  :  10.1016/j.jhydrol.2020.125481

来源: Elsevier

【 摘 要 】

Most of the two-dimensional (2D) hydraulic/hydrodynamic models are still computationally too demanding for real-time applications. In this paper, an innovative modelling approach based on a deep convolutional neural network (CNN) method is presented for rapid prediction of fluvial flood inundation. The CNN model is trained using outputs from a 2D hydraulic model (i.e. LISFLOOD-FP) to predict water depths. The pre-trained model is then applied to simulate the January 2005 and December 2015 floods in Carlisle, UK. The CNN predictions are compared favourably with the outputs produced by LISFLOOD-FP. The performance of the CNN model is further confirmed by benchmarking against a support vector regression (SVR) method. The results show that the CNN model outperforms SVR by a large margin. The CNN model is highly accurate in capturing flooded cells as indicated by several quantitative assessment matrices. The estimated error for reproducing maximum flood depth is 0-0.2 m for the 2005 event and 0-0.5 m for the 2015 event at over 99% of the cells covering the computational domain. The proposed CNN method offers great potential for real-time flood modelling/forecasting considering its simplicity, superior performance and computational efficiency.

【 授权许可】

Free