{"success":true,"data":{"author":"Huot, Hu, Goyal, Sankar, Ihme, Chen (Google Research); TACO repackaging by ISP, Universitat de Valencia","bucketAccessType":"public","bucketName":"isp-uv-es/next-day-wildfire-spread-taco","bucketPrefix":"","category":"Earth Observation & Geospatial","cloudProvider":"huggingface","createdAt":"2026-11-16T14:11:25.832Z","description":"Next Day Wildfire Spread (IEEE TGRS, 2022) is a curated benchmark for predicting where an active wildfire will be tomorrow, aggregated in Google Earth Engine from nearly a decade of fires across the contiguous United States. It has 18,545 chips of 64x64 pixels at 1 km, each pairing yesterday's MODIS fire mask and twelve covariates with the next day's fire mask: SRTM elevation, VIIRS NDVI, gridMET wind speed and direction, minimum and maximum temperature, humidity and precipitation, drought index (PDSI), energy release component, and population density. Both fire masks use -1 for uncertain pixels, kept as an ignore index. The release carries no coordinates or dates, so none are given here. Splits are 14,979 train, 1,877 validation and 1,689 test. About 1.7 GB in TACO format, read with tacoreader. Published by the authors on Kaggle under CC BY 4.0; cite Huot et al. 2022.","displayTitle":"Next Day Wildfire Spread: 1 km Fire Mask Transition Dataset for the Contiguous US (TACO)","id":"7ff8ed07-15a4-5e82-989f-f146ab1ff6f6","license":"CC-BY-4.0","licenseEvidenceUrl":"https://www.kaggle.com/datasets/fantineh/next-day-wildfire-spread","objectCountEstimate":9,"probeStatus":"ok","referenceUrl":"https://arxiv.org/abs/2112.02447","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"isp-uv-es/next-day-wildfire-spread-taco\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"isp-uv-es/next-day-wildfire-spread-taco\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=isp-uv-es, license:cc-by-4.0, size_categories:10K<n<100K, downloads=534"],"format":"mixed","generatedAt":"2026-11-16T14:11:30.796Z","layout":{"example":"assets/logos.png","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"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","encoding":"hex","key":"assets/logos.png","truncatedAt":512}],"sampleObjects":["assets/logos.png","assets/sample_0.png","assets/sample_1.png","assets/sample_2.png","assets/sample_3.png"],"sidecars":[{"bytes":"---\nlicense: cc-by-4.0\npretty_name: \"Next Day Wildfire Spread\"\nsize_categories:\n- 10K<n<100K\ntask_categories:\n- image-segmentation\ntags:\n- earth-observation\n- remote-sensing\n- taco\n---\n\n<p align=\"center\"><img src=\"assets/logos.png\" width=\"546\" alt=\"Image and Signal Processing Group, Universitat de València · ELLIOT\"></p>\n\n# Next Day Wildfire Spread\n\n> **This is a repackaging, not a new dataset.** It is **Next Day Wildfire Spread** by Google Research (Huot, Hu, Goyal, Sankar, Ihme, Chen), gridMET / USGS / NASA MODIS, converted to TACO. Pixel values and labels are kept as released except where the description below says otherwise. All credit belongs to the original authors: if you use it, please cite them and follow their licence.\n>\n> [original dataset](https://www.kaggle.com/datasets/fantineh/next-day-wildfire-spread) · [paper](https://doi.org/10.48550/arXiv.2112.02447) · licence: CC-BY-4.0\n>\n> Repackaged into TACO by the [Image and Signal Processing Group (ISP)](https://isp.uv.es/), Universitat de València, within the [ELLIOT](https://elliot-ai.eu) project.\n\n## Citation\n\nPlease cite the original work:\n\n```bibtex\n@article{huot2022next,\n  title   = {Next Day Wildfire Spread: A Machine Learning Dataset to Predict Wildfire Spreading From Remote-Sensing Data},\n  author  = {Huot, Fantine and Hu, R. Lily and Goyal, Nita and Sankar, Tharun and Ihme, Matthias and Chen, Yi-Fan},\n  journal = {IEEE Transactions on Geoscience and Remote Sensing},\n  volume  = {60},\n  pages   = {1--13},\n  year    = {2022},\n  doi     = {10.1109/TGRS.2022.3192974}\n}\n```\n\n## About the data\n\n18545 chips of 64x64 at 1 km over the continental United States, each pairing twelve covariates and yesterday's fire mask with tomorrow's fire mask. The supervision is a state transition rather than a description of an image.\n\n**18,545 samples** · splits: `test` 1,689 · `train` 14,979 · `validation` 1,877 · tasks: `semantic-segmentation`\n\nPackaged as [TACO v3](https://asterisk.coop/taco/spec/).\n\n<details>\n<summary>Full description</summary>\n\n**Inputs.** Most are not remote sensing, because fire spread is driven by weather and fuel.\n- Elevation and NDVI are remote sensing.\n- Wind speed and direction, humidity, minimum and maximum temperature and precipitation are gridMET reanalysis.\n- Drought severity and energy release are fire-danger indices, and population density is a census product.\n\n**Labels.** Both fire masks use -1 for an uncertain label, kept as the ignore index rather than folded into `no fire`.\n\n**Georeferencing.** The release ships no spatio-temporal information, and the Zarr copy this is converted from sets its coordinates to pixel and sample indices, so no CRS, transform or date is carried.\n\n**Nodata.** Temperature declares nodata=0, the release's fill: 99.99% of out-of-range temperature values are exactly zero, and the two temperature bands are bad on exactly the same pixels.\n\n**Splits.** train 14979, val 1877, test 1689.\n\n</details>\n\n## Getting started\n\n```bash\ngit clone --recursive https://github.com/OscarPellicer/taco\npip install -e \"taco/python[ml]\"     # builds the reader: C++23, CMake, Ninja, pkg-config, libcurl >= 7.83, OpenSSL >= 3\n```\n\nRead it straight from the Hub:\n\n```python\nimport os\nfrom huggingface_hub import hf_hub_download, snapshot_download\nfrom taco.ml import Dataset, plot_sample\n\npath = hf_hub_download(\"isp-uv-es/next-day-wildfire-spread-taco\", \"next-day-wildfire-spread.zip\", repo_type=\"dataset\")\nds = Dataset(path)\nplot_sample(ds[0])\n```\n\nor from a local copy:\n\n```python\nds = Dataset(\"next-day-wildfire-spread.zip\")\nsample = ds[0]                      # {slot name: SlotValue}, arrays decoded\nsample[\"elevation\"].array.shape\n```\n\nMetadata without decoding anything:\n\n```python\nimport taco\ntaco.read(\"next-day-wildfire-spread.zip\")              # one Arrow table, levels joined\n```\n\n## Samples\n\n![sample](assets/sample_0.png)\n![sample](assets/sample_1.png)\n![sample](assets/sample_2.png)\n![sample](assets/sample_3.png)\n![sample](assets/sample_4.png)\n\n## What a sample contains\n\n| role | slot | holds | modality | detail |\n|---|---|---|---|","encoding":"utf8","key":"README.md","name":"README.md","size":5536,"truncated":true}],"sourceObjectKey":"assets/logos.png","starterCell":"from huggingface_hub import hf_hub_download\npath = hf_hub_download(repo_id=\"isp-uv-es/next-day-wildfire-spread-taco\", filename=\"assets/logos.png\", repo_type=\"dataset\")\nprint(path)","starterSamplePath":"assets/logos.png","totalObjects":9},"summary":"Next Day Wildfire Spread (IEEE TGRS, 2022) is a curated benchmark for predicting where an active wildfire will be tomorrow, aggregated in Google Earth Engine from nearly a decade…","title":"Next Day Wildfire Spread: 1 km Fire Mask Transition Dataset for the Contiguous US (TACO)","updatedAt":"2026-11-16T17:11:55.725Z","visibility":"public","websiteUrl":"https://huggingface.co/datasets/isp-uv-es/next-day-wildfire-spread-taco"}}