Machine Learning for Flood Susceptibility Mapping of the Chennai Floods of 2023

Rapid and precise urban flood forecasting is crucial for promptly implementing preventive actions. This article presents a review of the literature focusing on soft computing techniques and algorithms for predicting urban floods. We also present two famous machine learning algorithms viz., Random Forest (RF) and XGBoost to create a Flood Susceptibility Map (FSM) for the city of Chennai in the state of Tamil Nadu, India based on the historical data of the 2023 floods of Chennai. A decent classification accuracy of 65% and 70% has been achieved using our approach for both RF and XGBoost algorithms respectively.