See the danger before the spark.

PRECEDE scores wildfire danger across about 1,857 locations in 11 western states, refreshed around the clock, so the people who protect communities can act before a fire starts, not after.

The problem

Satellites tell you a fire has already started. They cannot tell you that this afternoon, in a particular stretch of country, conditions have lined up so that whatever ignites will be hard to stop. That gap, the hours before a spark, is where lives and homes are saved or lost. PRECEDE was built to close it.

What PRECEDE does

PRECEDE watches the fire-prone parts of 11 western states from about 1,857 monitored locations and scores wildfire danger continuously, well below the level of a whole county. Each location gets a single risk number, refreshed around the clock, that reflects whether conditions have entered the zone where a fire would likely turn destructive. When a location crosses that line, it surfaces as an alert someone can act on. The output is simple on purpose: a score, a place, a trend, and a clear threshold for when to pay attention.

How well it works

Across the catastrophic California fires of the last decade, the ones that destroy homes rather than just burn acreage, PRECEDE flags about three out of four before they ignite, measured against the real fire record. (This validated catch rate is measured on California's structure-destroying fires; the wider western footprint is monitoring coverage, not a restatement of that accuracy figure.) The result we trust most came from a deliberately hard test. We trained the model only on fires through 2023, then turned it loose on the 2024 and 2025 fire years it had never seen. It still flagged most of the destructive fires in that window, the January 2025 Los Angeles fires among them. It does this while staying quiet on the overwhelming majority of ordinary days, because a warning that fires on every warm afternoon trains people to ignore it.

Knowing when it is safe, too

The same conditions that make a day dangerous to leave alone make it dangerous to put fire on the ground on purpose. The forecast that flags rising danger also flags upcoming windows when conditions favor safer prescribed burning and fuel work, giving crews a head start on planning controlled burns instead of guessing. This is about timing — when conditions are working for or against a burn — not about telling anyone where to treat. Knowing when not to burn is as valuable as knowing when you can.

How you can trust the numbers

We do not ask anyone to take our word for it, and we do not hand over the inner workings either. We let an independent expert design and control the test. The model is locked and fingerprinted up front. The validator builds a private list of dates and places, mixing real fire days with decoys of their own, and we score it blind. Across a full fire season, each day's predictions are committed in advance and scored by an independent party against the public record at the end. What comes out is a signed letter stating what was tested and what the results were, which can be shown to a county, a utility, or an investor, without us revealing how the model works.