AI Urban Flood Prediction Using Satellite Images and Weather Data

Flooding in urban areas has become a serious challenge due to rapid city growth and changing climate patterns. This project focuses on creating a reliable system to predict urban floods by analysing various environmental and weather-related data. Using real-time data such as rainfall, river levels, soil moisture, and drainage conditions, the system applies advanced machine learning techniques to forecast flooding events accurately. The goal is to provide early warnings that can help city planners and emergency services take timely action to reduce damage and protect residents. By integrating multiple data sources and improving prediction accuracy, this system aims to support better flood management and enhance urban safety. This system leverages data collected from various sources like IoT sensors, weather stations, and satellite imagery to capture the dynamic urban environment. Advanced data preprocessing methods are applied to clean and normalize the data, ensuring accurate model training. The project employs machine learning models such as Random Forest and Long Short-Term Memory (LSTM) networks to analyse patterns and predict flood occurrences.