Floods are among the most destructive natural disasters, causing significant socioeconomic and environmental impacts worldwide. This chapter examines how Artificial Intelligence (AI), encompassing Machine Learning (ML), Deep Learning (DL), and hybrid models, can be leveraged for flood susceptibility mapping in the governorate of El Tarf, northeastern Algeria. The study area is particularly prone to flooding due to its diverse climatic and hydrological characteristics, including heavy rainfall and river overflows. The study utilized twelve flood-conditioning factors, including land cover, rainfall, SPI, TWI, and elevation, to train and evaluate various AI models, including LightGBM, Random Forest, CNN, and CNN-LSTM. Among these, LightGBM achieved the highest classification performance, with an accuracy of 90% and an AUC of 0.96, demonstrating its effectiveness in identifying flood-prone areas with minimal false positives and negatives. Despite the promising results, the study highlights the challenges posed by limited data availability and the need for larger, diverse datasets to improve model generalization and applicability to other regions. This research underscores the potential of AI-driven approaches in flood risk management, offering an innovative and scalable solution for mitigating flood impacts in vulnerable areas like El Tarf.