Comparison of Machine Learning Algorithms for Flood Susceptibility Mapping

Floods are one of the most destructive natural disasters, causing financial and human losses every year. As a result, reliable Flood Susceptibility Mapping (FSM) is required for effective flood management reducing its harmful effects. In this study, new machine learning model based on Cascade Forest Model (CFM) was developed FSM. Satellite imagery, historical reports, field data were used to determine flood-inundated areas. The database included 21 flood-conditioning factors obtained from different sources. performance proposed CFM evaluated over two study areas, results compared with those other six methods, including Support Vector Machine (SVM), Decision Tree (DT), Random (RF), Deep Neural Network (DNN), Light Gradient Boosting (LightGBM), Extreme (XGBoost), Categorical (CatBoost). result showed produced highest accuracy models both Overall Accuracy (AC), Kappa Coefficient (KC), Area Under Receiver Operating Characteristic Curve (AUC) more than 95%, 0.8, 0.95, respectively. Most these recognized southwestern part Karun basin, northern northwestern regions Gorganrud basin as susceptible