Flood Detection in Satellite Imeges Using Deep Learning

Abstract

Floods are one of the most common and dangerous natural disasters. They can damage homes, roads, and important services, and they often happen without warning. To reduce the damage, it is important to detect floods quickly and accurately. This study uses deep learning methods to detect floods in satellite images. A total of 380 images were used, divided equally into flood and non-flood classes. Several deep learning models were tested, including VGG, ResNet, DenseNet, MobileNet, and Inception. These models were improved using transfer learning, which helps save time and improves results. The best models, such as ResNet50V2 and DenseNet, achieved high accuracy (up to 97%) in classifying the images. The study also tested a new idea by adding a quantum layer to the models using the PennyLane library. These hybrid models showed promising results. This research shows that deep learning and transfer learning are powerful tools for flood detection. In the future, this work can be improved by using more data and trying new ideas to make it even more accurate and useful.