Lebanon faces challenges with flooding due to its diverse topography and climate. Accurate flood mapping plays a crucial role in visualizing the severity and extent of floods, aiding both immediate response efforts and long-term planning. Precise recognition of flood-prone areas is essential for enacting efficient mitigation strategies and guiding decision-making procedures. This study aims to use remote sensing techniques, and machine learning algorithms to improve flood extent mapping and flood forecasting in Lebanon. The integration of satellite data, hydrological parameters, terrain data, and land cover classifications enhance the ability to mitigate floods. The approach consists of two main parts: flood mapping and flood areas extent modeling. In flood mapping, satellite imagery, radar technology, and metrics are combined to create models that effectively visualize the distribution and severity of floods across Lebanon, identifying key regions more prone to floods. The results from flood mapping are then used as a parameter for forecasting flood extent areas. In flood areas modeling, three different machine learning algorithms are tested and gave high performances, indicating enhanced predictive accuracy and reduced errors. This interdisciplinary approach seeks to improve flood forecasting methods and flood mapping specific to Lebanon’s unique geography and environment, ultimately increasing resilience to climate change.