SEN12-FLOOD: Sentinel-1 SAR and Sentinel-2 Time Series for Flood Detection
- Provider
- Rambour, Audebert, Koeniguer, Le Saux, Crucianu and Datcu (CNAM, ESA)
- License
- CC-BY-4.0 (source)
- Format
- JSON (in sampled files)
- Stored at
- Azure Blob Storage, https://radiantearth.blob.core.windows.net/mlhub/sen12floods
- Access
- Free and public. No account with the data provider is needed.
- DOI
- 10.21227/w6xz-s898
- Category
- Earth Observation & Geospatial
- Source
- https://doi.org/10.21227/w6xz-s898
About SEN12-FLOOD: Sentinel-1 SAR and Sentinel-2 Time Series for Flood Detection
Co-registered time series of Sentinel-1 synthetic aperture radar (SAR) and Sentinel-2 multispectral images for detecting flood events, built at CNAM with ESA. Floods usually come with heavy cloud, so the dataset pairs cloud-penetrating SAR with optical imagery over the same flood-prone areas, starting in December 2018, with each acquisition labelled flooded or not flooded. Measured 2026-11-15: 335 sequence folders under imagery/ /, each holding Sentinel-1 IW GRD scenes as calibrated VV and VH GeoTIFFs and Sentinel-2 acquisitions as one GeoTIFF per band (S2_ _B01.tif and so on); more than 40,000 files in all (at least 18.6 GB listed) and per-image GeoJSON labels under labels/, plus STAC JSON. Read with rasterio; the reference paper trains recurrent and convolutional models on the paired series. Released under CC BY 4.0; cite Rambour et al. (2020), 'Flood Detection in Time Series of Optical and SAR Images', ISPRS Archives XLIII-B2-2020, and the IEEE DataPort record doi:10.21227/w6xz-s898.
How to access this dataset in Python
import adlfs
fs = adlfs.AzureBlobFileSystem(account_name='radiantearth', anon=True)
fs.ls('mlhub/sen12floods/')[:10]Lists the files with anonymous access. Runs on any machine, with no cloud account.
Data structure
File types in sampled files: JSON
Files
Example file: .source/metadata.json
Analyze this dataset without downloading it
On Scigantic, SEN12-FLOOD: Sentinel-1 SAR and Sentinel-2 Time Series for Flood Detection opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.
This page is also available as Markdown and as JSON.
Related Earth Observation & Geospatial datasets
- RADARSAT-1
- HIFLD Archive
- Satellite - Sea surface temperature - AusTemp - SST anomaly - Australia - Rolling daily
- DOE Open Energy Data Initiative: Buildings Sector Scenarios (BSS)
- NASA LAMBDA: COBE/Diffuse Infrared Background Experiment (DIRBE)
- Trazo Training Data
- NASA LAMBDA: COBE/Differential Microwave Radiometer (DMR)
- LandCoverNet Africa: Annual Land Cover Labels on Sentinel-1, Sentinel-2 and Landsat-8 Time Series (2018)