WildfireScore
Methodology
How WildfireScore risk scores are computed: data sources, modeling approach, and limitations.
WildfireScore publishes wildfire risk scores at neighborhood resolution across the US West and fire-prone interior. Every score on this site is computed by PerilScore using the same data layer used by insurance and risk management professionals.
Data sources
We start from public scientific records. Every input is auditable, and we don’t use proprietary or paywalled data.
- USGS Monitoring Trends in Burn Severity (MTBS): decades of fire perimeter records with severity classification.
- LANDFIRE: fuel models, vegetation, and topography (elevation, slope, aspect) for the contiguous US.
- NOAA / NWS weather records: long-run fire-weather indices including Burning Index (BI), Energy Release Component (ERC), Keetch-Byram Drought Index (KBDI), and Fire Weather Index (FWI).
- US Forest Service WUI maps: Wildland-Urban Interface classification for exposure context.
Modeling approach
We combine fuel behavior, fire-weather climatology, and topography into a fire-spread probability model. The result is a single 0 to 10 probability score at each neighborhood-scale sample point (about 5 km²).
Output metrics include long-run fire frequency, expected burned area, flammability index, fuel load, and WUI exposure flag.
Resolution
Scores are computed at neighborhood resolution: approximately 5 km² sample points across the contiguous US. This is much finer than the county-level averages most public wildfire data provides.
Update cadence
The model is refreshed annually following each fire season, incorporating the prior year’s perimeter records and updated fuel layers. Major model updates are versioned and disclosed.
Validation
Models are evaluated against held-out historical fire perimeters and benchmarked against published reference datasets where available. The exact validation protocol is documented in the PerilScore technical papers.
Limitations
- Forecast boundary. WildfireScore reflects long-run probability from the historical record. Current drought and fuel-moisture conditions still need active local sources.
- Property-specific detail. Scores reflect a neighborhood-scale sample point. For a property-specific score that incorporates defensible space, construction class, and ignition-resistant materials, use the free PerilScore app.
- Fuel layers lag reality. Recent vegetation change, including post-fire regrowth and urban development, may take several years to appear in LANDFIRE.
Attribution
Risk scores powered by PerilScore. Visit perilscore.com for the full platform, API access, and commercial-use licensing.
Methodology
Public data. Real science. No black boxes.
Every score is computed from decades of public weather records using physics-based probability modeling. It's the same approach used by insurance and risk management professionals.
- Decades of public weather data
Hurricane tracks, storm intensities, fire perimeters, hail reports, all drawn from public scientific archives. We don't use proprietary data. You can audit every input.
- Physics-based probability modeling
Scores reflect how the actual peril behaves: wind fields, fire spread, ground shaking, and storm tracks. The model keeps the physics visible instead of flattening every place into a broad average.
- Used by professionals
The same PerilScore data layer is used by insurance and risk management professionals. We publish it here so anyone can find authoritative risk numbers for their location.
Frequently asked questions
Where does the wildfire risk score come from?
Does this account for current drought or fuel conditions?
How is this different from CAL FIRE Hazard Severity Zones?
Want the full picture for a specific property?
The scores on this site show the representative wildfire layer for a local area. Enter a street address to add building age, construction type, roof details, occupancy, surroundings, and property-level context.
Free results for any US street address.