under the water A global multi-temporal satellite dataset for rapid flood mapping

The total size of the compressed dataset is 1.33 TB, with the GRD component (including the DEMs and metadata) taking 705.8 GB and the SLC 492.6 GB. All code and data will be maintained at the project's repo. On the left hand side we present the post-event SAR image used for the prediction, captured in 22/05/2023, while on the right hand side the respective Sentinel-2 RGB image captured in 23/05/2023 (one day later). In Figure 1 we assess the performance of our best model, i.e. Unet-ResNet50, on the recent floods of Emiglia-Romana, Italy, which took place on May 2023.