Assessment of flood vulnerability in a coastal metropolitan city for sustainable environmental using Machine Learning methods

Abstract Floods are very destructive natural catastrophes that significantly harm people, the environment, and structures. Due to their dynamic nature, flash flood-prone locations are difficult to predict. We used cutting-edge machine learning algorithms for early flash flood detection to overcome this. To evaluate flood vulnerability in Chennai, Tamil Nadu, India, we employed and evaluated two combined ensemble models: the Artificial Neural Network (ANN) and Random Forest (RF). To put these models into practice, we built a GIS framework out of 280 historical flooding sites and twelve flood-related parameters. Using information gain ratio and multicollinearity diagnostic tests, we evaluated the association between flood occurrences and pertinent factors. Statistical criteria like "Freidman" were used to compare the prediction abilities of ANN and RF models. Both ANN and RF models performed better than expected when simulating flood susceptibility. In order to reduce flood-related hazards and create efficient mitigation plans, state and local authorities, as well as policymakers, will benefit from the study's findings and methodology. Flood susceptibility percentages were 18% very low, 16% low, 13% moderate, 22% high, and 31% extremely very high, according to the research of ANN. While this was going on, RF revealed that the likelihood of flooding was 7% very low, 11% low, 34% moderate, 31% high, and 18% extremely very high. Maintaining a strong drainage system, using regulated building techniques in sensitive regions, setting up early warning systems, creating resilient infrastructure, and educating people are all necessary to reduce floods in Chennai. For resource allocation, disaster response, and readiness exercises, effective coordination between government agencies, non-governmental organizations (NGOs), and local populations is essential. Chennai's resistance to floods depends on a multi-pronged approach that includes infrastructure improvement, pro-active planning, and public awareness.