A machine learning approach for forecasting and visualising flood inundation information

摘要

This paper presents a new data-driven modelling framework for forecasting probabilistic flood inundation maps forreal-time applications. The proposed end-to-end (rainfall–inundation) method combines a suite of machine learning(ML) algorithms to forecast discharge and deliver probabilistic flood inundation maps with a 3 h lead time. To classifywet/dry cells, the method applies rainfall–discharge models based on random forest technique on top of classifiersbased on multi-layer perceptron. The hybrid modelling framework was tested using two subsets of data created froman observed fluvial flood event in a small flood-prone town in the UK. The results showed that the model caneffectively emulate the outcomes of a hydrodynamic model (Flood Modeller (FM)) with considerably high accuracymeasured in terms of flood arrival time error and classification accuracy. The mean arrival time difference betweenthe proposed model and the hydrodynamic model was 1 h 53 min. The classification accuracy was measured against asynthetic aperture radar image, producing accuracies of 88.22% and 86.58% for the proposed data-driven model andFM, respectively. The key features of the proposed modelling framework are that it is simple to implement, detectsflooded cells effectively and substantially reduces computational time.