{"success":true,"data":{"author":"Orion Lab, National Observatory of Athens / NTUA (Bountos et al.)","bucketAccessType":"public","bucketName":"orion-ai-lab/Kuro-Siwo-GeoTIFFs","bucketPrefix":"","category":"Earth Observation & Geospatial","cloudProvider":"huggingface","createdAt":"2026-11-16T14:11:25.353Z","description":"Kuro Siwo is a manually annotated, multi-temporal Sentinel-1 SAR dataset for rapid flood mapping, presented at NeurIPS 2024 (Datasets and Benchmarks). It covers 43 flood events on six continents and three climate zones between 2015 and 2022, about 33 billion square metres of annotated area at 10 m. For every event there is one post-flood acquisition and two pre-flood acquisitions, a DEM layer, and an expert photo-interpreted mask with three classes (no water, permanent water, flood) plus a valid-pixel mask. Two components are provided: GRD (VV and VH backscatter) and SLC (four channels: VV phase, VH amplitude, VV amplitude, VH phase), each under its own folder; a sample's info.json carries event and acquisition metadata. This repository holds the GeoTIFFs (about 1 TB) for building embeddings or extending the dataset; a WebDataset copy sits in orion-ai-lab/Kuro-Siwo-Webdataset. The authors release Kuro Siwo under a CC BY licence; cite Bountos et al. 2024.","displayTitle":"Kuro Siwo: Global Multi-Temporal Sentinel-1 SAR Flood Mapping Dataset (GeoTIFF)","id":"d2098d6d-7741-5bba-8f35-c93fbdcc8639","license":"CC-BY-4.0","licenseEvidenceUrl":"https://github.com/Orion-AI-Lab/KuroSiwo","objectCountEstimate":53,"probeStatus":"ok","referenceUrl":"https://proceedings.neurips.cc/paper_files/paper/2024/hash/43612b0662cb6a4986edf859fd6ebafe-Abstract-Datasets_and_Benchmarks_Track.html","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"orion-ai-lab/Kuro-Siwo-GeoTIFFs\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"orion-ai-lab/Kuro-Siwo-GeoTIFFs\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=orion-ai-lab, license:cc-by-4.0, downloads=1219"],"format":"mixed","generatedAt":"2026-11-16T14:11:31.051Z","layout":{"example":"GRD/00000.tar","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"2e2f2e2f40506178486561646572000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000030303030303030003030303030303000303030303030300030303030303030303032360030303030303030303030300030313032313300207800000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000757374617200303000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000","encoding":"hex","key":"GRD/00000.tar","truncatedAt":512}],"sampleObjects":["GRD/00000.tar","GRD/00001.tar","GRD/00002.tar","GRD/00003.tar","GRD/00004.tar"],"sidecars":[{"bytes":"---\nlanguage:\n- en\ntask_categories:\n- image-classification\n- image-segmentation\npretty_name: Kuro Siwo GeoTIFFs\ntags:\n- earth-science\n- remote-sensing\n- flood-mapping\n- sar\n- radar\n- flash-flood\n- flood\n- earth-observation\nlicense: cc-by-4.0\nconfigs:\n- config_name: GRD\n  data_files: \"GRD/*.tar\"\n- config_name: SLC\n  data_files: \"SLC/*.tar\"\n---\n\n# Kuro Siwo GeoTIFFs\n\n[**Paper**](https://proceedings.neurips.cc/paper_files/paper/2024/hash/43612b0662cb6a4986edf859fd6ebafe-Abstract-Datasets_and_Benchmarks_Track.html) | [**GitHub**](https://github.com/Orion-AI-Lab/KuroSiwo/tree/main) |\n\n## Dataset Details\n\n### Dataset Description\n\nKuro Siwo is a global multi-temporal SAR dataset for rapid flood mapping. It contains 43 flood events in 6 continents and 3 climate zones, over the period 2015-2022. The annotations have been produced through meticulous photointerpretation by a team of experts, at 10m spatial resolution. For each flood event, we provide one Sentinel-1 post-flood and two Sentinel-1 pre-flood captions, along with a Digital Elevation Model (DEM). For research purposes, we opted to include both GRD and SLC products.\n\nThis particular repo contains the GeoTIFF files of Kuro Siwo, aiming to facilitate experimentation, incorporation of learned embeddings, and expansion of the dataset.\n\n- **Funded by:** ThinkingEarth (grant agreement No 101130544) and MeDiTwin (grant agreement No 101159723) of the European Union’s Horizon\nEurope research and innovation programme\n- **License:** CC BY\n\n## Dataset Structure\n\n### Sample fields\n\nEach sample in the GRD webdatasets has the following fields:\n\n- `flood_vv.npy` (float32): The VV band of the post-flood image\n- `flood_vh.npy` (float32): The VH band of the post-flood image\n- `sec1_vv.npy` (float32): The VV band of the first pre-flood image\n- `sec1_vh.npy` (float32): The VH band of the first pre-flood image\n- `sec2_vv.npy` (float32): The VV band of the second pre-flood image\n- `sec2_vh.npy` (float32): The VH band of the second pre-flood image\n- `dem.npy` (float32): The DEM\n- `info.json`: Metadata on this particular sample\n- `mask.npy` (float32): The label (0: no water, 1: permanent water, 2: flood)\n- `valid_mask.npy` (float32): A mask depicting the valid pixels (0: invalid, 1: valid)\n\nAccordingly, each sample in the SLC dataset has the following fields:\n\n- `flood.npy` (float32): The post-flood image *\n- `sec1.npy` (float32): The first pre-flood image *\n- `sec2.npy` (float32): The second pre-flood image *\n- `dem.npy` (float32): The DEM\n- `info.json`: Metadata on this particular sample\n- `mask.npy` (float32): The label (0: no water, 1: permanent water, 2: flood)\n- `valid_mask.npy` (float32): A mask depicting the valid pixels (0: invalid, 1: valid)\n\n* In the SLC component, each image has 4 channels: Phase VV, Amplitude VH, Amplitude VV, Phase VH. \n\n\n## Citation\n\n**BibTeX:**\n\n```\n@inproceedings{NEURIPS2024_43612b06,\n author = {Bountos, Nikolaos Ioannis and Sdraka, Maria and Zavras, Angelos and Karavias, Andreas and Karasante, Ilektra and Herekakis, Themistocles and Thanasou, Angeliki and Michail, Dimitrios and Papoutsis, Ioannis},\n booktitle = {Advances in Neural Information Processing Systems},\n editor = {A. Globerson and L. Mackey and D. Belgrave and A. Fan and U. Paquet and J. Tomczak and C. Zhang},\n pages = {38105--38121},\n publisher = {Curran Associates, Inc.},\n title = {Kuro Siwo: 33 billion m\\^{}2 under the water. A global multi-temporal satellite dataset for rapid flood mapping},\n url = {https://proceedings.neurips.cc/paper_files/paper/2024/file/43612b0662cb6a4986edf859fd6ebafe-Paper-Datasets_and_Benchmarks_Track.pdf},\n volume = {37},\n year = {2024}\n}\n```\n\n**APA:**\n\nBountos, N. I., Sdraka, M., Zavras, A., Karavias, A., Karasante, I., Herekakis, T., Thanasou, A., Michail, D. & Papoutsis, I. (2024). Kuro Siwo: 33 billion $ m^ 2$ under the water. A global multi-temporal satellite dataset for rapid flood mapping. Advances in Neural Information Processing Systems, 37, 38105-38121.\n\n## Dataset Card Authors\n\nMaria Sdraka","encoding":"utf8","key":"README.md","name":"README.md","size":4024,"truncated":false}],"sourceObjectKey":"GRD/00000.tar","starterCell":"from huggingface_hub import hf_hub_download\npath = hf_hub_download(repo_id=\"orion-ai-lab/Kuro-Siwo-GeoTIFFs\", filename=\"GRD/00000.tar\", repo_type=\"dataset\")\nprint(path)","starterSamplePath":"GRD/00000.tar","totalObjects":53},"summary":"Kuro Siwo is a manually annotated, multi-temporal Sentinel-1 SAR dataset for rapid flood mapping, presented at NeurIPS 2024 (Datasets and Benchmarks).","title":"Kuro Siwo: Global Multi-Temporal Sentinel-1 SAR Flood Mapping Dataset (GeoTIFF)","updatedAt":"2026-11-16T17:02:04.539Z","visibility":"public","websiteUrl":"https://huggingface.co/datasets/orion-ai-lab/Kuro-Siwo-GeoTIFFs"}}