Natural or man-made disasters can have a severe impact on individuals, causing significant harm or even completely destroying their lives. The focus of the paper under discussion is the issue of flooding, which can be caused by various factors such as natural calamities or human error. Regardless of the cause, flooding can lead to a considerable loss of life and devastating financial consequences, turning even wealthy individuals into paupers in just a matter of hours. The primary objective of the research is to locate areas that are prone to flooding and rescue those who may be affected. The research will use a vast dataset of flood photographs and train the AI model for flood prediction. The Unet Segmentation technique will be utilized to implement flood detection. The suggested approach is more successful and promising compared to existing methods, as it is based on a newly developed algorithm. The research will focus on identifying flood-prone locations to help prevent future incidents. Flood prediction using machine learning algorithms has become increasingly popular in recent years, as it can provide an accurate forecast of potential flooding in specific areas, allowing for timely intervention and saving lives. The use of machine learning techniques to predict floods is a promising approach because it offers several advantages. Additionally, machine learning algorithms can learn and improve over time as new data becomes available, resulting in more accurate predictions. The proposed approach will use the Unet Segmentation technique, a popular deep learning architecture for image segmentation tasks. In conclusion, the research aims to locate flood-prone areas and rescue those affected using machine learning techniques. The Unet Segmentation technique will be utilized for flood deta, which is a promising approach compared to existing methods. With the increasing frequency of natural disasters, the use of machine learning to predict and prevent flooding can save countless lives and prevent devastating financial consequences.