CanadaFireSat Raw: Sentinel-2, ERA5-Land and MODIS Predictor Archives for High-Resolution Wildfire Forecasting in Canada
- Provider
- EPFL ECEO lab (Porta, Dalsasso, McCarty, Tuia)
- License
- MIT (source)
- Size
- 51 files
- Stored at
- Hugging Face (https://huggingface.co/datasets/EPFL-ECEO/CanadaFireSat-Raw)
- Access
- Free and public. No account with the data provider is needed.
- Category
- Environmental Science
- Source
- https://arxiv.org/abs/2506.08690
About this dataset
The raw, compressed source archives of CanadaFireSat, a benchmark from the EPFL Environmental Computational Science and Earth Observation (ECEO) lab for high-resolution forecasting of where wildfires will burn across Canada. Labels come from National Burned Area Composite (NBAC) fire polygons since 2015, aggregated to a 2.8 x 2.8 km grid and 8-day windows. For each grid cell the inputs are a Sentinel-2 L1C image time series (at least 3 cloud-free images over the 64 days before prediction), hydrometeorological drivers from ERA5-Land and MODIS11 land surface temperature, MODIS13 and MODIS15 vegetation indices (NDVI, EVI, LAI, FPAR), and Fire Weather Index and Drought Code from the Copernicus Emergency Management Service, with 2020 NALCMS land cover for adversarial sampling and analysis. The repository is about 775 GB in six folders of split zip archives for positive and negative samples in spatial and tabular forms, plus a hard test set, with metadata/ holding split definitions and variable column lists. Use it with the CanadaFireSat-Data and CanadaFireSat-Model GitHub repositories; a cleaned Parquet version is published separately as EPFL-ECEO/CanadaFireSat. Released under the MIT license; cite Porta, Dalsasso, McCarty and Tuia, ISPRS Journal of Photogrammetry and Remote Sensing 2026.
How to load this dataset in Python
from huggingface_hub import hf_hub_download
path = hf_hub_download(repo_id="EPFL-ECEO/CanadaFireSat-Raw", filename="ENV/neg_spatial.z01", repo_type="dataset")
print(path)Data structure
Files
Example file: ENV/neg_spatial.z01
Analyze this dataset without downloading it
On Scigantic, CanadaFireSat Raw: Sentinel-2, ERA5-Land and MODIS Predictor Archives for High-Resolution Wildfire Forecasting in Canada opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.
This page is also available as Markdown and as JSON.
Related Environmental Science datasets
- SelvaBox: 83,000 Tropical Tree Crown Bounding Boxes on 4.5 cm Drone Orthomosaics from Brazil, Ecuador and Panama (CanopyRS)
- Mangrove Aboveground and Belowground Biomass and Soil Carbon Stocks in Côte d’Ivoire (Fresco and Sassandra) with Sentinel-1 and Sentinel-2 Bands (data354)
- BIRDeep Audio Annotations: Expert-Labeled Bird Song Recordings from AudioMoth Recorders in Doñana National Park, Spain (EBD-CSIC and Universidad de Córdoba)
- Moorings - Estuarine and coastal water quality monitoring - Near real time
- DEA Fuel Moisture Content (Sentinel-2, Australia)
- NEON Tree Crowns, DeepTreeAttention Edition: 41,738 Species-Labelled Crowns at 38 NEON Sites
- GLOBIO 4 Terrestrial Mean Species Abundance (MSA) Biodiversity Intactness, 2015 and SSP 2050 Scenarios
- Multi-perspective plains zebras: four drone-swarm missions on one synchronised timebase