Climate change, driven by both natural and human activities, presents a significant challenge with profound environmental impacts, including rising temperatures, sea levels, and extreme weather events. Flooding, a prominent consequence of climate change, is intensifying due to increased rainfall and rising sea levels, threatening coastal and riverine communities worldwide. This article explores the integration of Artificial Intelligence (AI) and Machine Learning (ML) to develop advanced flood prediction and management systems, aiming to mitigate these risks. Our research focuses on utilizing ML algorithms to enhance the accuracy of flood forecasting and improve emergency response strategies. We employed a diverse dataset, comprising Sentinel-2 satellite images and meteorological data, to train our models. The flood detection model, based on Convolutional Neural Networks (CNN), demonstrated a high accuracy of 97%, effectively identifying flooded areas from satellite images. For flood prediction, we explored models such as Support Vector Machines (SVM), Decision Trees, and K-Nearest Neighbors (KNN). The SVM model achieved the highest accuracy at 86%, making it the most effective for predicting flood events. Additionally, we have developed an application leveraging the selected ML model to provide real-time flood predictions. This app delivers timely warnings and actionable insights, enhancing preparedness and reducing the impact of floods on vulnerable communities. By combining the predictive power of AI with expert knowledge, our approach represents a significant advancement in flood management, contributing to a more adaptive and sustainable future in the face of escalating climate risks.