Urban flash flood hazard mapping using machine learning, Bahir Dar, Ethiopia

Abstract

ABSTRACT Increased frequency and magnitude of flooding pose a significant natural hazard to urban areas worldwide. Mapping flood hazard areas are crucial for mitigating potential damage to human life and property. However, conventional hydrodynamic approaches are hindered by their extensive data requirements and computational expenses. As an alternative solution, this paper explores the use of machine learning (ML) techniques to map flood hazards based on readily available geo-environmental variables. We employed various ML classifiers, including decision tree (DT), random forest (RF), XGBoost (XGB), and k-nearest neighbor (kNN), to assess their performance in flood hazard mapping. Model evaluation was conducted using the area under the receiver operating characteristic curve (AUC) and root mean square error (RMSE). Our results demonstrated promising outcomes, with AUC values of 93% (DT), 97% (RF), 98% (XGB), and 91% (kNN) for the validation dataset. RF and XGB have slightly higher performance than DT and kNN and distance to river was the most important factor. The study highlights the potential of ML for urban flood modeling, offering reasonable accuracy and supporting early warning systems. By leveraging available geo-environmental variables, ML techniques provide valuable insights into flood hazard mapping, aiding in effective urban planning and disaster management strategies.