With the increasing unpredictability of climate change and the resulting rise in flood incidents, accurate and timely flood mapping is essential for efficient disaster relief. This study examines the use of satellite and aerial images taken during flood events to map floods in the Larissa region using a Decision Support System (DSS). The suggested DSS analyzes aerial photos using sophisticated image processing and Machine Learning (ML) methods to extract relevant data essential for mapping flood extents. The DSS takes a holistic approach, combining meteorological inputs, topographical features, and historical flood data to improve the accuracy and reliability of flood mapping. The technology uses Artificial Intelligence (AI) to automate decision-making so that it can provide quick and precise flood estimates. Our system supports early warning via real-time monitoring, giving authorities the ability to proactively handle any flood concerns in the city. Moreover, this work emphasizes the need of customized decision support systems for flood mapping in geographically particular areas, adding to the ongoing efforts to use technology for disaster risk reduction and emergency response. The results have important ramifications for strengthening resilience and lessening the effects of flooding in Larissa and similar areas.