ImpactMesh-Fire: Multimodal Multitemporal Wildfire Burn Scar Dataset
- Provider
- IBM Research, DLR, ESA Phi-lab
- License
- CC-BY-4.0 (source)
- Size
- 22 files
- Stored at
- Hugging Face (https://huggingface.co/datasets/ibm-esa-geospatial/ImpactMesh-Fire)
- Access
- Free and public. No account with the data provider is needed.
- Category
- Earth Observation & Geospatial
- Source
- https://github.com/IBM/ImpactMesh
About ImpactMesh-Fire: Multimodal Multitemporal Wildfire Burn Scar Dataset
Wildfire subset of ImpactMesh, the multimodal, multitemporal disaster mapping benchmark from IBM, DLR and ESA Phi-lab. It pairs Sentinel-2 L2A (all bands), Sentinel-1 RTC SAR and Copernicus DEM with burn scar annotations from the Copernicus Emergency Management Service, with four time steps per sample (pre-month, pre-event, event and post-event). Version 1 holds 16,512 samples covering 229 wildfire events (11,852 train, 1,864 validation, 2,796 test), cleaned to reduce label noise, and a 1,270-sample test_holdout of events absent from training and validation. The listing (measured 2026-11-14) shows train/, val/, test/ and split/ folders with per-modality tar archives (S2L2A, S2RGB, S1RTC, DEM, MASK); the repository uses about 153 GB. Untar the archives as the card shows and read samples with rasterio or xarray. Intended for burned area segmentation, fire impact mapping and fine-tuning geospatial foundation models with optical and radar time series. Released under CC-BY-4.0, with Copernicus Sentinel attribution; a companion flood subset is ImpactMesh-Flood.
How to load ImpactMesh-Fire: Multimodal Multitemporal Wildfire Burn Scar Dataset in Python
from huggingface_hub import hf_hub_download
path = hf_hub_download(repo_id="ibm-esa-geospatial/ImpactMesh-Fire", filename="test/DEM.tar", repo_type="dataset")
print(path)Data structure
Files
Example file: test/DEM.tar
Analyze this dataset without downloading it
On Scigantic, ImpactMesh-Fire: Multimodal Multitemporal Wildfire Burn Scar Dataset 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 Earth Observation & Geospatial datasets
- DOE Open Energy Data Initiative: University of Miami Coupled Model (UMCM) for Hurricanes Ike and Sandy
- NASA LAMBDA: COBE/Far-InfraRed Absolute Spectrophotometer (FIRAS)
- Department of Energy's Open Energy Data Initiative (OEDI)
- geocoding-cng
- geozarr-examples
- Source Cooperative Manifests
- FTW Field Boundaries
- Wildfire Boundary Polygons from USGS and CalFire in cloud native formats