Analyzing sensitivity of flood susceptible model in a flood plain river basin

Flood is considered one of the most dangerous natural disasters among all-natural disasters. Prediction of flood susceptible areas is a primary task for adopting management plans for minimizing the colossal failure of the flood. The present work intended to identify the flood susceptible areas by using multi Machine Learning (ML) algorithms based on fourteen flood conditioning parameters in Tangon river basin of Indo-Bangladesh. Apart from statistical tests (AUC of ROC, Friedman test, Wilcoxon Signed Rank Test), Index of Flood Vulnerability (IFV) using field data-sets and 2 D flood simulation model using HEC-RAS software were used to validate the flood susceptibility models. The ML models predicted 4.95% to 17.53% area comes under a very high flood susceptible zone. Support vector machine model best suit model compared to all models. Sensitivity analysis of the model clarified that geology, rainfall, elevation, and drainage factors played a dominant role for determining the model.