Radiant MLHub

Sentinel-2 Cloud Cover Segmentation Dataset

satellite

In many uses of multispectral satellite imagery, clouds obscure what we really care about - for example, tracking wildfires, mapping deforestation, or monitoring crop health. Being able to more accurately remove clouds from satellite images filters out interference, unlocking the potential of a vast range of use cases. With this goal in mind, this training dataset was generated as part of crowdsourcing competition, and later on was validated using a team of expert annotators. The dataset consists of Sentinel-2 satellite imagery and corresponding cloudy labels stored as GeoTiffs. There are 22,728 chips in the training data, collected between 2018 and 2020.

Dataset ID

ref_cloud_cover_detection_challenge_v1

DOI

10.34911/rdnt.hfq6m7

Creator

Radiant Earth Foundation

Contact

ml@radiant.earth

Documentation

Citation

Radiant Earth Foundation. (2022). Sentinel-2 Cloud Cover Segmentation Dataset (Version 1). Radiant MLHub. [Date Accessed] https://doi.org/10.34911/rdnt.hfq6m7

Python Client example

from radiant_mlhub import Dataset

ds = Dataset.fetch('ref_cloud_cover_detection_challenge_v1')
for c in ds.collections:
    print(c.id)

Python Client quick-start guide

Download Dataset

Source Imagery Collections

Description

Sentinel-2 Cloud Cover Segmentation Train Source Imagery

License

CC-BY-4.0

Collection ID

ref_cloud_cover_detection_challenge_v1_train_source

Download

Description

Sentinel-2 Cloud Cover Segmentation Test Source Imagery

License

CC-BY-4.0

Collection ID

ref_cloud_cover_detection_challenge_v1_test_source

Download

Labels Collections

Description

Sentinel-2 Cloud Cover Segmentation Train Labels

License

CC-BY-4.0

Collection ID

ref_cloud_cover_detection_challenge_v1_train_labels

Download

Description

Sentinel-2 Cloud Cover Segmentation Test Labels

License

CC-BY-4.0

Collection ID

ref_cloud_cover_detection_challenge_v1_test_labels

Download