← Directory
dataset · Global
sen1floods
Hugging Face dataset harshinde/sen1floods
Claim this listing
Represent sen1floods? Send a claim for review so we can discuss listing updates. Claims do not automatically grant ownership or verification.
What's in it
- Data offered docs-verified
- Sentinel-1 SAR (VV, VH) chips · Sentinel-2 MSI Level-1C chips (13 bands) · Hand-labelled water/not-water ground truth chips (QC layer) · Event metadata (GeoJSON)
- Coverage llm-inferred
- Global (ENTRY regions); events identified by country, e.g. Bolivia, Spain
- Resolution docs-verified
- 10 m ground resolution; 512 x 512 px chips
- Formats docs-verified
- GeoTIFF · GeoJSON
- Access docs-verified
- Free, open access via Hugging Face (HF bucket 'senfloods11'); licence CC-BY-4.0
Useful for
- Use cases llm-inferred
- Training and validating deep-learning flood-extent segmentation from Sentinel-1 SAR · Benchmarking water classification from Sentinel-2 against hand-labelled reference chips · Testing flood-mapping algorithms as a method check before applying them to a site study
- Audience llm-inferred
- GIS analysts · hydrologists · flood consultants · remote-sensing and ML engineers
Limitations
- Constraints docs-verified
- Hugging Face dataset viewer unavailable for this dataset · Chips are 512 x 512 px tiles, so not a continuous coverage product · Requires citation of Bonafilia et al. (2020) under CC-BY-4.0
- Licence
- cc-by-4.0
- Authentication
- Unknown — review source docs
- GitHub stars
- Unknown
- Last commit
- Unknown
- Last successful page check
- 14/10/2026
- Page health
- healthy
- Package
- Not recorded
- Verification
- Not independently verified
Provenance & evidence
Verified 2026-10-15 via HF API: exists; 259 downloads/30d, 2 likes.
Metadata observed 14/10/2026 · research sweep: manual-2026-10-15 (Hugging Face datasets)