MS_Revised.pdf (14.48 MB)
Download fileA deep convolutional neural network model for rapid prediction of fluvial flood inundation
journal contribution
posted on 2020-09-11, 09:05 authored by Syed Kabir, Sandhya Patidar, Xilin Xia, Qiuhua LiangQiuhua Liang, Jeffrey Neal, Gareth PenderMost 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 predicting maximum flood depth is 0 ∼ 0.2 meters for the 2005 event and 0 ∼ 0.5 meters 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.
Funding
This work is partly funded by the Newton Fund and UK Met Office ‘WCSSP-India Lot 7: Building a Flood Hazard Impact Model for India (FHIM-India) (DN394978)’ project.
History
School
- Architecture, Building and Civil Engineering
Published in
Journal of HydrologyVolume
590Publisher
ElsevierVersion
- AM (Accepted Manuscript)
Rights holder
© ElsevierPublisher statement
This paper was accepted for publication in the journal Journal of Hydrology and the definitive published version is available at https://doi.org/10.1016/j.jhydrol.2020.125481.Acceptance date
2020-08-26Publication date
2020-09-06Copyright date
2020ISSN
0022-1694Publisher version
Language
- en