Coastal flooding presents a considerable risk to urban infrastructure and communities, particularly in low-lying areas such as Chennai, India, where swift urban development and climate change intensify susceptibility. This study combines geospatial intelligence with machine learning techniques to forecast flood risks and produce practical insights for managing disasters. Utilizing Digital Elevation Models (DEMs), rainfall patterns, tidal data, and historical flood records, the analysis pinpoints areas susceptible to flooding and models possible inundation scenarios. Utilizing advanced machine learning models such as Random Forest and Gradient Boosting allows for the exploration of relationships between geospatial and meteorological variables, thereby improving the accuracy of flood predictions. Moreover, geospatial visualization methods, such as interactive flood risk maps, provide valuable resources for urban planning and informed decision-making. The findings illustrate the effectiveness of integrating machine learning with geospatial analysis to enhance flood prediction precision and facilitate proactive disaster mitigation approaches. This study presents a flexible and scalable framework for assessing flood risk, which can be utilized by other coastal cities encountering comparable challenges.