Beyond Major Floods: Deep Learning for Detecting Shallow Water Inundation in Agricultural Areas
29th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES 2025), 2025
Abstract
Flood detection using satellite imagery is crucial for environmental monitoring and disaster management. We introduced a three-class segmentation framework that distinguishes sea, inland water, and land, improving flood detection accuracy in complex coastal farmland. Ten deep learning models were evaluated. DeepLabv3+ and a hybrid ResNet-UNet outperformed the others.