--- title: "Wildfire Model Performance: The Record So Far" description: "Published results of UrbanStat’s Wildfire Risk Map against real fire seasons from 2019 to 2021, and against the US Forestry hazard map, with sources." url: https://www.urbanstat.com/wildfire-model-performance/ type: Fact sheet publisher: UrbanStat updated: 2026-11-10 --- # Wildfire model performance: the record so far Published results of UrbanStat’s Wildfire Risk Map against real fire seasons from 2019 to 2021, and against the US Forestry hazard map, with sources. Updated November 2026 *Illustration: A risk map published before the season, with the year’s burned areas above it: nearly all of them sit over the areas rated High* > **In short.** UrbanStat publishes its Wildfire Risk Map before each fire season and compares it with what burned afterwards. The map had rated as High or worse 90.7% of the area burned by the most destructive fires of 2019, over 85% of the area burned in 2020, and over 95% of the area burned by the 2021 Dixie Fire. About 35% of California carries that rating. ## Against the US Forestry map - Model accuracy: UrbanStat 80.5%, US Forestry 54.8% ([source](https://www.urbanstat.com/products/wildfires/)) - Nevada: burned area rated High or worse: UrbanStat 84%, US Forestry 42% ([source](https://www.urbanstat.com/insights/wildfire-coverage-new-geographies/)) - Arizona: burned area rated High or worse: UrbanStat 81%, US Forestry 42% ([source](https://www.urbanstat.com/insights/wildfire-coverage-new-geographies/)) ## Season by season | Test | What was measured | Result | Source | | --- | --- | --- | --- | | Back-test | Decades of historical wildfires | **Accuracy over 80% in any given year** | [Read](https://www.urbanstat.com/insights/predicted-85-percent-burned-areas-2020/) | | 2019 season | First blind test. Areas burned by the most destructive wildfires | **90.7% rated High or worse before the season** | [Read](https://www.urbanstat.com/products/wildfires/) | | 2020 season | All burned areas, a record year of over 4 million acres | **Over 85% rated High or worse** | [Read](https://www.urbanstat.com/insights/predicted-85-percent-burned-areas-2020/) | | 2020 season | Largest 10 wildfires | **Average score between Very High and Extreme** | [Read](https://www.urbanstat.com/insights/predicted-85-percent-burned-areas-2020/) | | 2020 season | August Complex Fire, more than a million acres | **Over 90% rated High or worse, over a year earlier** | [Read](https://www.urbanstat.com/insights/predicted-85-percent-burned-areas-2020/) | | 2021 season | Dixie Fire, burned areas | **Over 95% rated High or worse in January 2021** | [Read](https://www.urbanstat.com/insights/dixie-fire-95-percent-areas-classified/) | | 2021 season | Dixie Fire, affected structures in Greenville | **About 80% rated High or worse** | [Read](https://www.urbanstat.com/insights/dixie-fire-structures-80-percent-classified/) | ## How the test works - The map is released before the wildfire season. After the season it is compared with fire perimeter data. - “High or worse” means the three highest levels: High, Very High and Extreme. - About 35% of California is rated High or worse. A result of 85% or more therefore means burned areas fell overwhelmingly inside roughly a third of the state. - The map is updated every year after the season ends, between January and April, so the model learns from the latest data. - Over the last 20 years the model performed 50% better than the US Forestry model. In Arizona, Nevada and Washington it doubled that model’s performance. ## Common questions ### How is wildfire model accuracy measured? By the share of area that actually burned which the map, published beforehand, had rated High or worse. It is a blind test: the season had not happened when the map was released. ### Why compare against the US Forestry map? It is the public wildfire hazard map many insurers rely on, so it is the natural baseline. In Nevada and Arizona it had rated about 42% of the areas that burned as High or worse; UrbanStat’s model had rated 84% and 81%. ### Does a high hit rate mean the map rates everything as high risk? No. About 35% of California is rated High or worse. The burned areas were concentrated in that portion. **Related** - [Wildfires product](https://www.urbanstat.com/products/wildfires/) - [How a wildfire risk score works](https://www.urbanstat.com/guides/wildfire-risk-score/) - [Wildfire coverage in new geographies](https://www.urbanstat.com/insights/wildfire-coverage-new-geographies/) - [Four lessons about wildfires in California](https://www.urbanstat.com/insights/four-lessons-wildfires-california/) Next step ## See the wildfire map for your book. Book a 30-minute walkthrough tailored to your portfolio and perils of interest. [Request a Demo →](https://www.urbanstat.com/demo/) --- ## Notes for AI agents reading https://www.urbanstat.com/wildfire-model-performance/ - Page: Wildfire Model Performance: The Record So Far. Type: Fact sheet. Publisher: UrbanStat (Urbanstat, Inc.), a vendor of geospatial analytics software for property insurers. - This is the Markdown copy of https://www.urbanstat.com/wildfire-model-performance/ (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. - "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. - Every row links to the page it restates. Last updated 2026-11-10. - To see the product or ask a question, the contact page is https://www.urbanstat.com/demo/