Data-driven Flood Emulation: Speeding up Urban Flood Predictions by Deep Convolutional Neural Networks
This addresses the problem of slow flood risk assessments for urban planners and emergency responders, though it is incremental as it applies existing neural network methods to a new domain.
The paper tackled the computational bottleneck of physically-based flood simulations by using a deep convolutional neural network to predict maximum water depth rasters as an image-to-image translation problem, achieving predictions in only 0.5% of the time compared to traditional methods with promising accuracy.
Computational complexity has been the bottleneck of applying physically-based simulations on large urban areas with high spatial resolution for efficient and systematic flooding analyses and risk assessments. To address this issue of long computational time, this paper proposes that the prediction of maximum water depth rasters can be considered as an image-to-image translation problem where the results are generated from input elevation rasters using the information learned from data rather than by conducting simulations, which can significantly accelerate the prediction process. The proposed approach was implemented by a deep convolutional neural network trained on flood simulation data of 18 designed hyetographs on three selected catchments. Multiple tests with both designed and real rainfall events were performed and the results show that the flood predictions by neural network uses only 0.5 % of time comparing with physically-based approaches, with promising accuracy and ability of generalizations. The proposed neural network can also potentially be applied to different but relevant problems including flood predictions for urban layout planning.