MMFlood: A Multimodal Dataset for Flood Delineation from Satellite Imagery
<p>MMFlood is remote sensing dataset derived from Sentinel-1 (VV-VH), MapZen (DEM) and OpenStreetMap (Hydrography). It provides a complete and well-rounded set of data specifically designed for flood events, focusing on three main features: worldwide distribution, manually validated annotations and multiple modalities.</p> <ul> <li>1748 pairs of SAR images and pixel-level annotations exclusively based around flooded areas and taking into account 95 flood events in 42 different countries around the world, in a time span ranging from 2014 to 2021.</li> <li>Image size <2000x2000, image resolution of 20m .</li> <li>Manually verified flood events across the world with raw SAR acquisitions derived from Sentinel-1.</li> <li>Includion of Digital Elevation Model (DEM) images.</li> </ul>
ShareScore
36/100
Overall dataset sharing score
Score breakdown
These five areas show where the dataset supports — or may limit — practical reuse.
- Stewardship
- 8
- Harmonization
- 4
- Access
- 16
- Reuse readiness
- 0
- Engagement
- 8