{"success":true,"data":{"author":"BigEarthNet team, TU Berlin (Sumbul et al. 2019)","bucketAccessType":"public","bucketListable":true,"bucketName":"https://radiantearth.blob.core.windows.net/mlhub","bucketPrefix":"bigearthnet","category":"Earth Observation & Geospatial","cloudProvider":"azure","createdAt":"2026-11-18T17:37:22.929Z","description":"The original BigEarthNet benchmark (version 1) for multi-label land cover classification of satellite image patches, as hosted on Radiant MLHub. 590,326 Sentinel-2 Level-2A patches were cut from 125 tiles acquired between June 2017 and May 2018 over Austria, Belgium, Finland, Ireland, Kosovo, Lithuania, Luxembourg, Portugal, Serbia and Switzerland, atmospherically corrected with sen2cor, and labeled with multiple CORINE Land Cover 2018 (CLC 2018) classes; the matching Sentinel-1 GRD patches (BigEarthNet-S1, VV and VH backscatter) are included, making the multi-modal BigEarthNet-MM set. Each patch is a folder named after its source scene and grid position (S2A_MSIL2A_..._row_col/ or S1A_IW_GRDH_..._row_col/) holding one GeoTIFF per band and a labels_metadata.json with the CLC labels and acquisition details. Use for multi-label scene classification, self-supervised pretraining and SAR-optical fusion with PyTorch, TorchGeo or rasterio. This is v1; the reprocessed BigEarthNet v2.0 (reBEN) is a separate catalog row. Licensed CDLA-Permissive-1.0; cite Sumbul, Charfuelan, Demir and Markl (2019), IGARSS, pp. 5901-5904.","displayTitle":"BigEarthNet v1 (BigEarthNet-MM): Sentinel-1 and Sentinel-2 Multi-Label Land Cover Patches with CORINE 2018 Labels","fuseMountBrowsable":true,"id":"5e760274-369c-5ae2-9e29-7eba356da229","license":"CDLA-Permissive-1.0","licenseEvidenceUrl":"https://bigearth.net/","objectCountEstimate":99,"probeStatus":"ok","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/bigearthnet/')[:10]"},{"language":"http","snippet":"curl -s 'https://radiantearth.blob.core.windows.net/mlhub?restype=container&comp=list&prefix=bigearthnet/&delimiter=/&maxresults=20'"}],"caveats":["Container has a large top-level fan-out: never recursively list; scope reads by prefix."],"format":"binary","generatedAt":"2026-11-18T17:39:29.641Z","layout":{"example":".source/metadata.json","pattern":"{prefix}/{filename}"},"mountPath":"/mnt/azure-archive/data","sampleHeaders":[{"bytes":"{\n    \"description\": \"BigEarthNet is a new large-scale Sentinel-2 benchmark archive, consisting of 590,326 Sentinel-2 image patches. To construct BigEarthNet, 125 Sentinel-2 tiles acquired between June 2017 and May 2018 over the 10 countries (Austria, Belgium, Finland, Ireland, Kosovo, Lithuania, Luxembourg, Portugal, Serbia, Switzerland) of Europe were initially selected. All the tiles were atmospherically corrected by the Sentinel-2 Level 2A product generation and formatting tool (sen2cor). Then, they wer","encoding":"utf8","key":".source/metadata.json","truncatedAt":512}],"sampleObjects":[".source/metadata.json"],"sidecars":[{"bytes":"# BigEarthNet\nBigEarthNet is a new large-scale Sentinel-2 benchmark archive, consisting of 590,326 Sentinel-2 image patches. To construct BigEarthNet, 125 Sentinel-2 tiles acquired between June 2017 and May 2018 over the 10 countries (Austria, Belgium, Finland, Ireland, Kosovo, Lithuania, Luxembourg, Portugal, Serbia, Switzerland) of Europe were initially selected. All the tiles were atmospherically corrected by the Sentinel-2 Level 2A product generation and formatting tool (sen2cor). Then, they were divided into 590,326 non-overlapping image patches. Each image patch was annotated by the multiple land-cover classes (i.e., multi-labels) that were provided from the CORINE Land Cover database of the year 2018 (CLC 2018).\n\n## Documentation\n* [Link](http://bigearth.net/static/documents/BigEarthNetManual.pdf)\n\n## Tutorials\n* [Accessing BigEarthNet through the Radiant MLHub API](https://nbviewer.org/github/radiantearth/mlhub-tutorials/blob/main/notebooks/radiant-mlhub-bigearthnet.ipynb) by [Kevin Booth](https://www.linkedin.com/in/kbgg/)\n\n## Publications\n* [BigEarthNet: A Large-Scale Benchmark Archive for Remote Sensing Image Understanding](http://bigearth.net/static/documents/BigEarthNet_IGARSS_2019.pdf) by [Gencer Sumbul](https://www.linkedin.com/in/gencer-s%C3%BCmb%C3%BCl-b558b625/)\n\n## Creator & Contact\n* [BigEarthNet](http://bigearth.net/)\n* contact@bigearth.net\n\n## License\n* [CDLA-Permissive-1.0](http://bigearth.net/downloads/documents/License.pdf)\n\n## Citation & DOI\nG. Sumbul, M. Charfuelan, B. Demir, V. Markl, \"[BigEarthNet: A Large-Scale Benchmark Archive for Remote Sensing Image Understanding](http://bigearth.net/static/documents/BigEarthNet_IGARSS_2019.pdf)\", IEEE International Geoscience and Remote Sensing Symposium, pp. 5901-5904, Yokohama, Japan, 2019.\n","encoding":"utf8","key":"README.md","name":"README.md","size":1791,"truncated":false},{"bytes":"{\n    \"description\": \"BigEarthNet is a new large-scale Sentinel-2 benchmark archive, consisting of 590,326 Sentinel-2 image patches. To construct BigEarthNet, 125 Sentinel-2 tiles acquired between June 2017 and May 2018 over the 10 countries (Austria, Belgium, Finland, Ireland, Kosovo, Lithuania, Luxembourg, Portugal, Serbia, Switzerland) of Europe were initially selected. All the tiles were atmospherically corrected by the Sentinel-2 Level 2A product generation and formatting tool (sen2cor). Then, they were divided \",\n    \"tags\": [\n        \"land cover\",\n        \"image classification\",\n        \"sentinel-2\"\n    ]\n}","encoding":"utf8","key":".source/metadata.json","name":"metadata.json","size":621,"truncated":false}],"sourceObjectKey":"bigearthnet/.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":"99 top-level prefixes"},"summary":"The original BigEarthNet benchmark (version 1) for multi-label land cover classification of satellite image patches, as hosted on Radiant MLHub.","title":"BigEarthNet v1 (BigEarthNet-MM): Sentinel-1 and Sentinel-2 Multi-Label Land Cover Patches with CORINE 2018 Labels","updatedAt":"2026-11-18T19:09:49.681Z","visibility":"public","websiteUrl":"https://bigearth.net/"}}