Development of flood hazard map and emergency relief operation system using hydrodynamic modeling and machine learning algorithm

Abstract

This study performs flood hazard mapping and evaluates community flood coping strategies. In addition, it proposes a humanitarian aid information system (HAIS) to enhance emergency support for flood victims. First, a flood hazard map was prepared using the hydrodynamic model (HM)–FLO 2D coupled with a machine learning algorithm (MLA)-scaled conjugate gradient neural network (SCG-NN). The performance of the MLA was evaluated using a validation dataset and statistical measures such as the mean square error (MSE: 0.080), root mean square error (RMSE: 0.282), and coefficient of determination (R2 = 0.830). According to the generated flood hazard map, most of the study area was classified as low (47.85%) or moderate (27.47%) hazardous zones, whereas only a small portion was delineated as high (20.64%) or very high (4.04%) hazardous zones. The accuracy of the hazard map (HM-MLA) versus the ground truth was tested statistically and was found to be high. Second, an investigation of local flood management strategies revealed that the current information system is not well prepared for emergencies, including the quantification of emergency relief necessities. Therefore, an HAIS, which specifies hazard information and quantifies emergency aids (food items) for flood victims, can be an effective emergency preparedness tool. We calculated the required emergency aid considering satellite-derived flood data. Finally, we conclude that the proposed HAIS will help humanitarian organizations and government agencies coordinate and perform relief operations effectively in the worst-hit regions across the country.