{"success":true,"data":{"author":"IBM Research, DLR, ESA Phi-lab","bucketAccessType":"public","bucketName":"ibm-esa-geospatial/ImpactMesh-Fire","bucketPrefix":"","category":"Earth Observation & Geospatial","cloudProvider":"huggingface","createdAt":"2026-11-14T14:15:15.763Z","description":"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.","displayTitle":"ImpactMesh-Fire: Multimodal Multitemporal Wildfire Burn Scar Dataset","id":"11a284ee-90d1-548e-9a98-9693fd8841b9","license":"CC-BY-4.0","licenseEvidenceUrl":"https://huggingface.co/datasets/ibm-esa-geospatial/ImpactMesh-Fire","objectCountEstimate":22,"probeStatus":"ok","referenceUrl":"https://github.com/IBM/ImpactMesh","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"ibm-esa-geospatial/ImpactMesh-Fire\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"ibm-esa-geospatial/ImpactMesh-Fire\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=ibm-esa-geospatial, license:cc-by-4.0, size_categories:10K<n<100K, downloads=202"],"format":"mixed","generatedAt":"2026-11-14T14:15:19.366Z","layout":{"example":"test/DEM.tar","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"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","encoding":"hex","key":"test/DEM.tar","truncatedAt":512}],"sampleObjects":["split/impactmesh_fire_test.txt","split/impactmesh_fire_test_holdout.txt","split/impactmesh_fire_test_seen_events.txt","split/impactmesh_fire_train.txt","split/impactmesh_fire_val.txt"],"sidecars":[{"bytes":"---\nlicense: cc-by-4.0\npretty_name: ImpactMesh-Fire\nsize_categories:\n- 10K<n<100K\nviewer: false\ntask_categories:\n- image-feature-extraction\n---\n\n[![arXiv](https://img.shields.io/badge/arXiv-comming_soon-b31b1b?logo=arxiv)](https://arxiv.org/abs/todo)\n[![Code](https://img.shields.io/badge/GitHub-ImpactMesh-EE4B2B?logo=github)](https://github.com/IBM/ImpactMesh)\n[![IBMblog](https://img.shields.io/badge/Blog-IBM-0F62FE)](https://research.ibm.com/blog/geospatial-flood-and-wildfire-mapping)\n\n\n# ImpactMesh-Fire\n\nImpactMesh is a large-scale multimodal, multitemporal dataset for flood and wildfire mapping, released by IBM, DLR, and the ESA Φ-lab. \nIt integrates **Sentinel-1 SAR**, **Sentinel-2 optical**, **Copernicus DEM**, and high-quality annotations from Copernicus EMS.\nThe technical report is released soon. You find the flood subset here: https://huggingface.co/datasets/ibm-esa-geospatial/ImpactMesh-Flood.\n\n![events_world](https://github.com/IBM/ImpactMesh/raw/main/assets/events_world_light.png)\n\n---\n## Features\n- Multimodal: SAR, optical, DEM\n- Multitemporal: Four time steps (pre-month, pre-event, event, post-event)\n- Global coverage: 200+ fire events\n- Scale: over 16K samples\n- License: CC-BY 4.0\n\n## Modalities\n\n| File | Content |\n|---|---|\n| `S2L2A.tar` | Sentinel-2 Level-2A, all bands, four time steps |\n| `S2RGB.tar` | Sentinel-2 RGB quicklook of the event time step |\n| `S1RTC.tar` | Sentinel-1 RTC SAR, four time steps |\n| `DEM.tar` | Copernicus DEM |\n| `MASK.tar` | Burn scar annotations from Copernicus EMS |\n\n## Splits\n\n| Split | Samples |\n|---|---|\n| train | 11,852 |\n| val | 1,864 |\n| test | 2,796 |\n| **total** | **16,512** |\n\nCovering 229 wildfire events.\n\n`test_holdout` (1,270 samples) is a subset of `test`, listing the samples whose\nevent does not appear in `train` or `val`. Use it to evaluate generalisation to\nentirely unseen events.\n\n## Versions\n\nThe current release is **v1**, which we generally recommend using.\n\nCompared to the initial v0, we performed extensive quality cleaning to improve\ntraining and reduce label noise. This removed a substantial number of noisy\nsamples, so v1 is smaller but of higher quality. The v0 version is still\navailable on request, please open a discussion in the Community tab.\n\n## Quick Start\n\nDownload the dataset:\n```shell\nhf download ibm-esa-geospatial/ImpactMesh-Fire --repo-type dataset --local-dir data/ImpactMesh-Fire\n\n# Only download a single modality (e.g., S2L2A)\nhf download ibm-esa-geospatial/ImpactMesh-Fire --repo-type dataset --include \"*/S2L2A.tar\" --local-dir data/ImpactMesh-Fire\n\n# Only download a single split (e.g., validation)\nhf download ibm-esa-geospatial/ImpactMesh-Fire --repo-type dataset --include \"val/*\" --local-dir data/ImpactMesh-Fire\n```\n\nUntar the samples:\n```shell\nmkdir data/ImpactMesh-Fire/data\nfor f in data/ImpactMesh-Fire/*/*.tar; do\n  echo \"Extracting $f\"\n  tar -xf \"$f\" -C data/ImpactMesh-Fire/data\ndone\n```\n\nThe samples from all splits are saved in shared folders `data/ImpactMesh-Fire/data/{modality}`. After extracting, you can delete the tars:\n```shell\nrm -r data/ImpactMesh-Fire/train\nrm -r data/ImpactMesh-Fire/val\nrm -r data/ImpactMesh-Fire/test\n```\n\nWe use [TerraTorch](https://terrastackai.github.io/terratorch/stable/) for the model fine-tuning and provide data modules for ImpactMesh. You can download the code and configs for the fine-tuning from https://github.com/IBM/ImpactMesh.\n\nAlternatively, you can install the data loading code with:\n\n```shell\npip install impactmesh\n```\n\n```shell\nterratorch fit --config configs/terramind_v1_tiny_impactmesh_fire.yaml\n```\n\n## Citation\n\nOur technical report is released soon!\n\n## Acknowledgement\n\nImpactMesh was developed as part of the FAST‑EO project funded by the European Space Agency Φ‑Lab (contract #4000143501/23/I‑DT).\n\nSentinel-2 Level-2A data were downloaded from Microsoft Planetary Computer and are provided under Copernicus Sentinel license conditions (© European Union 2015–2025, ESA) (https://planetarycomputer.microsoft.com/dataset/sentinel-2-l2a).\n\nSentinel-1 Radiometrically Terrain Corrected (RTC)","encoding":"utf8","key":"README.md","name":"README.md","size":4708,"truncated":true}],"sourceObjectKey":"test/DEM.tar","starterCell":"from huggingface_hub import hf_hub_download\npath = hf_hub_download(repo_id=\"ibm-esa-geospatial/ImpactMesh-Fire\", filename=\"test/DEM.tar\", repo_type=\"dataset\")\nprint(path)","starterSamplePath":"split/impactmesh_fire_test.txt","totalObjects":22},"summary":"Wildfire subset of ImpactMesh, the multimodal, multitemporal disaster mapping benchmark from IBM, DLR and ESA Phi-lab.","title":"ImpactMesh-Fire: Multimodal Multitemporal Wildfire Burn Scar Dataset","updatedAt":"2026-11-14T17:53:05.037Z","visibility":"public","websiteUrl":"https://huggingface.co/datasets/ibm-esa-geospatial/ImpactMesh-Fire"}}