Skip to content
← Directory

dataset · Global

Satellite-Images-of-Hurricane-Damage

Hugging Face dataset jonathan-roberts1/Satellite-Images-of-Hurricane-Damage

Claim this listing

Represent Satellite-Images-of-Hurricane-Damage? Send a claim for review so we can discuss listing updates. Claims do not automatically grant ownership or verification.

Explore paid sponsorship →

What's in it

Data offered docs-verified
post-hurricane satellite image patches (128x128 px) · binary image labels (2 classes), with class 0 = flooded or damaged buildings
Resolution docs-verified
128 x 128 px image patches; ground sample distance not stated
Formats docs-verified
parquet · image
Access docs-verified
Open access; licence CC BY 4.0; no authentication listed in entry

Useful for

Use cases llm-inferred
Benchmarking or training a flood/damage building classifier on post-event satellite imagery · Prototyping rapid post-flood building damage screening before field survey · Building a labelled test set for remote-sensing damage detection workflows
Audience llm-inferred
GIS analysts · remote sensing analysts · machine learning engineers

Limitations

Constraints llm-inferred
Geographic coverage (which hurricane or region) is not stated in the docs · Only a train split is shown; no validation or test split is documented · Small 128x128 px patches limit detail · Only two labels; the name of the second class is not given · Sensor, source imagery and ground resolution are not documented · Hurricane damage imagery, not UK-specific; no flood-extent or water-depth labels documented
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; 33 downloads/30d, 8 likes.

Metadata observed 14/10/2026 · research sweep: manual-2026-10-15 (Hugging Face datasets)