--- library_name: pytorch license: mit pipeline_tag: other tags: - wildfire - geospatial - weather - earth-observation - foundation-models - evaluation - pytorch pretty_name: WildFIRE-FM ---

WildFIRE-FM

A wildfire-specialized reference backbone for fixed-contract Earth-FM transfer evaluation

Five seeded PyTorch checkpoints, paper-aligned evaluation artifacts, final figure previews, and source-data access notes for 12-hour wildfire occupancy prediction on a 5 km California grid.

Read the paper · Download checkpoints · Load the model · Inspect task-contract results

5 Seeded Checkpoints · 16-Channel Gridded Input · 12-Hour Occupancy Lead · 6 Fixed Task-Contract Views

Why WildFIRE-FM · Release Navigation · Visual Tour · Quick Start · Task Snapshot · Data Sources · How to Cite

---

WildFIRE-FM overview

## Release Navigation

Paper Page

Visit the paper page on Hugging Face for the full manuscript, discussions, and related research.

Model Checkpoints

Access five seeded WildFIRE-FM weights with manifest metadata and SHA-256 hashes for release auditing.

Model Code

Inspect the compact U-Net implementation used to load the released wildfire occupancy backbone.

Quick Start

Clone the repository, instantiate the model, load a seeded checkpoint, and run the artifact check.

Task Snapshot

View the final-paper task-contract summary for occupancy, spread, retrieval, burned area, smoke, and heat.

Numeric Artifacts

Use sanitized CSV and JSON summaries that back the public model-card tables and figure previews.

Visual Tour

Browse final-paper previews for matching-rule sensitivity, selection regret, and task-form ranking changes.

Data Sources

See the public provider links and roles for HRRR, FIRMS, LANDFIRE, WRC, LandScan, WFIGS, and MTBS.

Repository Layout

Find where checkpoints, manifests, scripts, paper outputs, and release documentation live in this Hub repo.

--- ## Why WildFIRE-FM Wildfire Earth-FM transfer scores depend strongly on the contract used for comparison: task form, metric, matching rule, spatial scope, and head-selection criterion. The paper studies these choices by holding outputs or features fixed and then changing only the evaluation contract. WildFIRE-FM is the in-region reference model used in those comparisons. It is trained for 12-hour gridded wildfire occupancy on a California 5 km grid, then evaluated under the same task-specific contracts as the transferred Earth-FM backbones. --- ## Key Features - **Wildfire-specialized reference model:** Compact U-Net for 12-hour occupancy prediction on a projected California grid. - **Five seeded checkpoints:** Seeds `1`, `7`, `42`, `99`, and `123` are released with manifest hashes. - **Fixed-contract artifacts:** Compact summaries cover matching-rule, head-selection, and task-form comparisons from the final paper. - **Source-data aware release:** Provider links and data roles are documented for each public resource used by the study. - **Paper-aligned previews:** Figure assets summarize selection regret, supporting-task rank changes, and primary-task rank changes. --- ## Quick Start Clone the Hub repository or download the files you need: ```bash git clone https://huggingface.co/RAI-Lab/Wildfire-FM cd Wildfire-FM ``` Load a seeded checkpoint: ```python import torch from models.wildfire_fm.modeling_unet import UNetSmallFlex model = UNetSmallFlex( in_ch=16, base=32, dropout=0.1, norm_type="group", norm_groups=8, use_aux_spatial_head=True, ) checkpoint = torch.load( "models/wildfire_fm/checkpoints/seed_1/best_firms_prauc.pt", map_location="cpu", ) state = checkpoint.get("model", checkpoint) model.load_state_dict(state) model.eval() ``` The checkpoint expects the same 16-channel gridded input described in the paper and in `data_sources/DATA_SOURCES.md`. --- ## Task-Contract Snapshot | Task contract | Best final-paper mean | Winner | |---|---:|---| | Occupancy union F1 | `60.1506 ± 7.5865` percent | ClimaX | | Fire-spread spatial F1 | `80.9700 ± 2.0200` percent | WildFIRE-FM | | Final burned-area log-RMSE | `1.1657 ± 0.0126`, lower is better | WildFIRE-FM | | Analog retrieval nDCG@10 | `0.5099 ± 0.0336` | WildFIRE-FM | | Smoke PM2.5 RMSE | `4.4403 ± 0.0488`, lower is better | AlphaEarth | | Extreme-heat RMSE-C | `0.2179 ± 0.0043`, lower is better | WildFIRE-FM | --- ## How To Cite If you use WildFIRE-FM, the released checkpoints, the fixed-contract evaluation artifacts, or the paper-aligned scripts, please cite: ```bibtex @misc{wildfire_fm_evaluation_contracts_2026, title = {Does Your Wildfire Prediction Model Actually Work, or Just Score Well?}, author = {Yangshuang Xu and Yuyang Dai and Liling Chang and Qi Wang and Yushun Dong}, year = {2026}, note = {WildFIRE-FM model and fixed-contract wildfire evaluation artifacts} } ``` --- WildFIRE-FM is released to make wildfire Earth-FM transfer comparisons easier to inspect, reproduce at the artifact level, and evaluate under explicit contracts.