Multimodal and Multitemporal Data Fusion for Flood Extent Segmentation Exploiting Kurosiwo and WorldFloods Sentinel Datasets

In this work, we introduce a synergistic framework to perform multitemporal and multimodal flood extent mapping from multispectral and SAR satellite image time series. Two state-of-the-art flood datasets, Kuro Siwo and WorldFloods, have been used to create a dataset with pre-flood and post-flood images from Sentinel-1 and Sentinel-2, along with hand-labeled reference flood masks for each data source. We develop deep learning based fusion models achieving an Intersection over Union (IoU) ∼70% in our best fusion model, which outperforms single modality models by ∼10%. With this work, we pave the road to develop improved flood detection services by exploiting all available flood segmentation datasets and available satellite images.