Radiant MLHub

NASA Flood Extent Detection

satellite

This dataset contains synthetic aperture radar (SAR) raster imagery for various flood events acquired from the European Space Agencys Sentinel-1A and Sentinel-1B missions, providing C-Band dual-polarized imagery that spans geographical areas of interest in the United States and Bangladesh. The main emphasis was on the labeling of open water areas where specular reflection of the radar signal off of the relatively still, flat open water surface results in reduced backscatter, low amplitude, and an overall darkened appearance within the image. The labels for the water surface reflectance are also provided in GeoTiff rasterized file format in scenes aligned with the SAR source raster imagery.

Dataset ID

nasa_floods_v1

DOI

10.34911/rdnt.ebk43x

Creator

University of Alabama in Huntsville

Contact

ig0004@uah.edu

Documentation

Citation

Gahlot, S., Gurung, I., Molthan, A., Maskey, M., & Ramasubramanian, M. (2021) "Flood Extent Data for Machine Learning", Version 1.0, Radiant MLHub. [Date Accessed] https://doi.org/10.34911/rdnt.ebk43x

Python Client example

from radiant_mlhub import Dataset

ds = Dataset.fetch('nasa_floods_v1')
for c in ds.collections:
    print(c.id)

Python Client quick-start guide

Download Dataset

Source Imagery Collection

Description

NASA Flood Extent Source Imagery

License

CC-BY-4.0

Collection ID

nasa_floods_v1_source

Download

Labels Collection

Description

NASA Flood Extent Labels

License

CC-BY-4.0

Collection ID

nasa_floods_v1_labels

Download