OMBRIA dataset.

This repo contains the OMBRIA dataset. A Sentinel-1 and Sentinel-2 imagery dataset was constructed for benchmarking the OmbriaNet deep learning CNN architecture. OmbriaNet was designed to address the flood mapping problem. Each satellite module contains three folders: The folder named BEFORE contains images of regions taken before a selected flood event The folder named AFTER contains images of the same regions taken after the flood event The folder named MASK contains a binary ground truth image of the region as produced by the EMS Rapid mapping.