Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ ZENODOarrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
ZENODO
Dataset . 2026
License: CC BY
Data sources: ZENODO
ZENODO
Dataset . 2026
License: CC BY
Data sources: Datacite
ZENODO
Dataset . 2026
License: CC BY
Data sources: Datacite
versions View all 2 versions
addClaim

Urban Flood Observations

Authors: Mukherjee, Rohit; Friedrich, Hannah; Tellman, Elizabeth; Zhang, Zhijie;

Urban Flood Observations

Abstract

Urban Flood Observations (UFO) Chip-level dataset for binary surface-water segmentation over urban flood scenes, derived from PlanetScope imagery. Contents ufo-benchmark/ ├── README.md ├── stac/ │ ├── catalog.json │ ├── collection.json │ ├── items/ # 215 STAC Items, one per chip │ ├── scene_metadata/ # 61 per-scene Planet metadata files │ └── scene_index.json └── urbanFloodsObservationsPUBLIC/ ├── PS_uint8/ # 215 four-band (B,G,R,NIR) uint8 GeoTIFFs, 1024x1024 └── labels/ # 215 single-band uint8 GeoTIFFs, 1024x1024 Item / file convention Each chip is named: LOC_YYYYMMDD_HHMMSS_STRIP_CHIP.tif Where: LOC: three-letter location code (e.g., BEI, BNA, CMO, HTX, SPS) YYYYMMDD_HHMMSS_STRIP: source Planet scene identifier (date, time, strip ID) CHIP: four-character hash uniquely identifying the chip within the scene Image and label files share identical filenames. The chip filename preserves the original extraction naming convention. For a small number of scenes, the Planet scene ID includes an additional suffix. In these cases: The STAC property ufo:scene_id The filename in scene_metadata/*.json contain the exact resolved scene ID. Label convention Label rasters are single-band uint8: Pixel value Class name 0 non-water 1 surface water Per-chip label statistics (water pixel count, total pixel count, water fraction) are stored in each STAC Item under ufo:label_* properties. Imagery convention Source: PlanetScope (PSScene item type) Bands: Blue, Green, Red, NIR Pixel type: uint8 Spatial size: 1024 × 1024 pixels Resolution: original scene GSD Note: Planet Labs PBC granted permission to redistribute uint8-converted imagery alongside labels. These are not original surface reflectance products. STAC catalog The dataset follows STAC 1.0.0 with the following extensions: eo projection raster view label Validated using pystac. Structure: stac/catalog.json: root catalog stac/collection.json: collection metadata including spatial/temporal extent, providers, and summaries stac/items/*.json: one STAC Item per chip with image/label assets and metadata stac/scene_metadata/*.json: per-scene metadata (61 scenes) stac/scene_index.json: mapping between scenes and chips Planet metadata redistribution Only the following fields are included (per agreement with Planet Labs PBC): acquired (acquisition datetime) geometry (scene footprint, EPSG:4326) instrument cloud_cover sun_elevation gsd (ground sample distance) quality_category (e.g., standard, test) License Labels, STAC metadata, derived statistics, and redistributed imagery: CC-BY-4.0 PlanetScope imagery note: distributed imagery consists of uint8-converted products prepared for this dataset release, not original reflectance values. Redistribution is explicitly permitted by Planet Labs PBC. Citation Urban Flood Observations dataset (UFO). Zenodo. https://doi.org/10.5281/zenodo.15238470 Acknowledgments We would like to thank Simone Holliday, Patrick Hellmann, Natasha Rapp, and Linn Ji for their assistance with labeling. Funding The creation of the UFO dataset was supported by a NASA Terrestrial Hydrology Program grant (\#80NSSC21K1044).

Keywords

validation, flooding, surface inundation, segmentation, surface water, satellite imagery, urban, computer vision

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average