{"success":true,"data":{"author":"Radiant Earth Foundation","bucketAccessType":"public","bucketListable":true,"bucketName":"https://radiantearth.blob.core.windows.net/mlhub","bucketPrefix":"ref_cloud_cover_detection_challenge_v1","category":"Earth Observation & Geospatial","cloudProvider":"azure","createdAt":"2026-11-16T02:38:26.527Z","description":"Pixel-level cloud masks for Sentinel-2 L2A imagery, first produced through the DrivenData 'On Cloud N' crowdsourcing competition and later reviewed and corrected by a team of expert annotators at Radiant Earth Foundation. The training data hold 22,728 chips of 512 x 512 pixels at 10 m sampled from scenes acquired between 2018 and 2020 across Africa, South America and Australia; each chip has the B02, B03, B04 and B08 bands (blue, green, red, near infrared) as separate GeoTIFFs and a binary cloud / no-cloud label raster. Measured 2026-11-15: more than 40,000 files (at least 21 GB listed) under final/public/ (train_features/<chip_id>/B0x.tif, train_labels/, train_labels.zip, train_metadata.csv with location and acquisition time) and final/private/ (the held-out test chips), plus chip_id_crosswalk.csv mapping competition ids to Sentinel-2 scenes. Read with rasterio; DrivenData's PyTorch Lightning benchmark uses the Planetary Computer for extra bands. Useful for cloud masking, compared with Fmask and s2cloudless. Released under CC BY 4.0; cite Radiant Earth Foundation (2022), Sentinel-2 Cloud Cover Segmentation Dataset, doi:10.34911/rdnt.hfq6m7.","displayTitle":"Sentinel-2 Cloud Cover Segmentation Dataset (DrivenData challenge, expert-validated)","doi":"10.34911/rdnt.hfq6m7","fuseMountBrowsable":true,"id":"7d6a08bd-ce5f-5364-8502-5a4b804ae229","license":"CC-BY-4.0","licenseEvidenceUrl":"https://radiantearth.blob.core.windows.net/mlhub/ref_cloud_cover_detection_challenge_v1/README.md","objectCountEstimate":2,"probeStatus":"ok","referenceUrl":"https://doi.org/10.34911/rdnt.hfq6m7","schemaCard":{"accessHints":[{"language":"python-local","snippet":"import os\nsorted(os.listdir('/mnt/azure-archive/data'))[:20]"},{"language":"python-adlfs","snippet":"import adlfs\nfs = adlfs.AzureBlobFileSystem(account_name='radiantearth', anon=True)\nfs.ls('mlhub/ref_cloud_cover_detection_challenge_v1/')[:10]"},{"language":"http","snippet":"curl -s 'https://radiantearth.blob.core.windows.net/mlhub?restype=container&comp=list&prefix=ref_cloud_cover_detection_challenge_v1/&delimiter=/&maxresults=20'"}],"format":"binary","generatedAt":"2026-11-16T02:38:33.497Z","layout":{"example":".source/metadata.json","pattern":"{prefix}/{filename}"},"mountPath":"/mnt/azure-archive/data","sampleHeaders":[{"bytes":"{\n    \"description\": \"In many uses of multispectral satellite imagery, clouds obscure what we really care about - for example,\\ntracking wildfires, mapping deforestation, or monitoring crop health. Being able to more accurately remove\\nclouds from satellite images filters out interference, unlocking the potential of a vast range of use cases.\\nWith this goal in mind, this training dataset was generated as part of [crowdsourcing competition](https://www.drivendata.org/competitions/83/cloud-cover/), and later","encoding":"utf8","key":".source/metadata.json","truncatedAt":512}],"sampleObjects":[".source/metadata.json"],"sidecars":[{"bytes":"# Sentinel-2 Cloud Cover Segmentation Dataset\nIn many uses of multispectral satellite imagery, clouds obscure what we really care about - for example,\ntracking wildfires, mapping deforestation, or monitoring crop health. Being able to more accurately remove\nclouds from satellite images filters out interference, unlocking the potential of a vast range of use cases.\nWith this goal in mind, this training dataset was generated as part of [crowdsourcing competition](https://www.drivendata.org/competitions/83/cloud-cover/), and later\non was validated using a team of expert annotators. The dataset consists of Sentinel-2 satellite imagery \nand corresponding cloudy labels stored as GeoTiffs. There are 22,728 chips in the training data, \ncollected between 2018 and 2020.\n\n## Documentation\n* [Link](https://radiantearth.blob.core.windows.net/mlhub/ref_cloud_cover_detection_challenge_v1/documentation.pdf)\n\n## Tutorials\n* [How to use deep learning, Pytorch Lightning, and the Planetary Computer to predict cloud cover in satellite imagery.](https://www.drivendata.co/blog/cloud-cover-benchmark/) by [Katie Westone](https://www.drivendata.co/)\n\n## Creator & Contact\n* [Radiant Earth Foundation](https://radiant.earth)\n* ml@radiant.earth\n\n## License\n* [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/)\n\n## Citation & DOI\nRadiant Earth Foundation. (2022). Sentinel-2 Cloud Cover Segmentation Dataset (Version 1). Radiant MLHub. [Date Accessed] https://doi.org/10.34911/rdnt.hfq6m7\n","encoding":"utf8","key":"README.md","name":"README.md","size":1485,"truncated":false},{"bytes":"{\n    \"description\": \"In many uses of multispectral satellite imagery, clouds obscure what we really care about - for example,\\ntracking wildfires, mapping deforestation, or monitoring crop health. Being able to more accurately remove\\nclouds from satellite images filters out interference, unlocking the potential of a vast range of use cases.\\nWith this goal in mind, this training dataset was generated as part of [crowdsourcing competition](https://www.drivendata.org/competitions/83/cloud-cover/), and later\\non was valid\",\n    \"tags\": [\n        \"sentinel-2\",\n        \"segmentation\",\n        \"cloud\"\n    ]\n}","encoding":"utf8","key":".source/metadata.json","name":"metadata.json","size":612,"truncated":false}],"sourceObjectKey":"ref_cloud_cover_detection_challenge_v1/.source/metadata.json","starterCell":"path = '/mnt/azure-archive/data/.source/metadata.json'\nwith open(path, 'rb') as fh:\n    print(fh.read(64))","starterSamplePath":"/mnt/azure-archive/data/.source/metadata.json","totalObjects":"2 top-level prefixes"},"summary":"Pixel-level cloud masks for Sentinel-2 L2A imagery, first produced through the DrivenData 'On Cloud N' crowdsourcing competition and later reviewed and corrected by a team of…","title":"Sentinel-2 Cloud Cover Segmentation Dataset (DrivenData challenge, expert-validated)","updatedAt":"2026-11-16T16:14:07.201Z","visibility":"public","websiteUrl":"https://radiantearth.blob.core.windows.net/mlhub/ref_cloud_cover_detection_challenge_v1/README.md"}}