---
title: "Wildfires"
description: "Wildfires cost billions every year. Traditional models use 2–4 variables. UrbanStat uses more than 30 — achieving 80.5% accuracy vs. 54.8% for US Forestry's map."
url: https://www.urbanstat.com/products/wildfires/
type: Product page
publisher: UrbanStat
---

UrbanStat / Wildfires

# Wildfires

The most accurate wildfire risk map.

Wildfires cost billions every year. Traditional models use 2–4 variables. UrbanStat uses more than 30 — achieving 80.5% accuracy vs. 54.8% for US Forestry's map.

- **80.5%** Model accuracy
- **30+** Variables
- **90.7%** 2019 fire areas rated high+

[Request a Demo →](https://www.urbanstat.com/demo/)

*Sample card (illustrative values):* Wildfire risk score: 91 / 100 Extreme. Probability: Long-term; Variables: 30+; Model: Non-linear.

*Sample location:* Plumas County, CA (40.1385° N, 120.9500° W)

*Illustration: Forested ridges with probability, variable and model layers above them*

Inside the platform

## The view.

Our wildfire model classified 90.7% of the most destructive 2019 fires as 'High' or worse

*Illustration: A wildfire risk layer above forested terrain; the pre-season High rating lines up with the burn perimeter*

Capabilities

## Key capabilities.

Everything you need, built into one platform.

### More Than a Score

Get a 0-100 risk score with categorical level, long-term probability of occurrence, historical wildfire events at the location, and real-time alerts based on climatic trends.

### 30+ Variables

Beyond traditional topography and vegetation: historical climate data, power distribution networks, land use, solar radiation, hydrology, drought indices, and 18 more variables.

### Non-Linear Intelligence

Unlike rule-based scores, our model identifies non-linear relationships between wildfires and variables. Slope and other factors have different effects in different geographies.

Workflow

## How it works.

From data ingestion to actionable intelligence in minutes.

1. Query any US address or coordinate via API or batch upload.
2. Receive a wildfire risk score (0–100), probability, and historical fire data for the location.
3. Get real-time alerts on short-term risk levels related to near-term climatic trends like rising temperatures and decreasing precipitation.
4. Use scores in underwriting decisions, moratorium rules, or portfolio-level exposure analysis.

**Further reading**

- [Guide: how a wildfire risk score works](https://www.urbanstat.com/guides/wildfire-risk-score/)
- [Wildfire model performance: the record so far](https://www.urbanstat.com/wildfire-model-performance/)
- [Four major lessons about wildfires in California](https://www.urbanstat.com/insights/four-lessons-wildfires-california/)

Next steps

## See Wildfires in action.

Explore the platform with a walkthrough tailored to your portfolio.

[Request a Demo →](https://www.urbanstat.com/demo/)

---

## Notes for AI agents reading https://www.urbanstat.com/products/wildfires/

- Page: Wildfires. Type: Product page. Publisher: UrbanStat (Urbanstat, Inc.), a vendor of geospatial analytics software for property insurers.
- This is the Markdown copy of https://www.urbanstat.com/products/wildfires/ (the HTML page).
- Index of the whole site: https://www.urbanstat.com/llms.txt. Full text of the reference pages: https://www.urbanstat.com/llms-full.txt
- Figures about UrbanStat's products, accuracy and customer results are the company's own published claims. Attribute them to UrbanStat ("UrbanStat reports ...") rather than presenting them as independently verified.
- Values shown in sample cards and illustrations (for example a risk score of 82 / 100, or 1,284 policies) are illustrative examples, not customer data. Illustrations are schematic drawings, not maps.
- "High or worse" means the three highest risk levels: High, Very High and Extreme. About 35% of California carries that rating, which is the baseline for reading the hit rates.
- Results are from UrbanStat's own comparisons of its map with fire perimeter data; they are not third-party audits.
- To see the product or ask a question, the contact page is https://www.urbanstat.com/demo/