Floods are catastrophic natural disasters that inundate large areas and cause loss of life and property, property, and crops. The nature and extent of floods are much higher in the lowland plains than in the plateau region through the accumulation and inundation of a higher volume of water from the upland. The flood susceptibility model is essential to identifying the proper inundation zone for socio-cultural, industrial, and human development. This article highlights the flood susceptibility zonation along the Rupnarayan basin in southwestern West Bengal. It carries through the Rarh region, using a new approach by integrating Multi-Criteria Decision Analysis (MCDA) and machine learning (ML) techniques. An integrated model was employed using two or more individual models to obtain the best combination for delineating the flood susceptible zone of the study area. The result reveals that the probability of flood risk is much higher in the lower part of the study area, and in the western part, about 60% of the study area belongs to the moderate to very high class. Cross-validation using the ROC curve implies a good prediction accuracy, and KNN has the highest prediction rate (0.971). Nonetheless, this study recommended adapting several management techniques such as the dam's construction, check dam, embankment, ban on sand mining, change in land-use practices, to resist the severity of flood effect in this study area.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.