Karen Short, a research ecologist with the Forest Service who contributed to the study and maintains a historical database of national wildfire reports, says prevention and educating the public are essential. Strategic prevention seems to work: According to the National Fire Protection Association, house fires in the US have decreased by nearly half since the 1980s.
In 2024, Short expanded her wildfire archive to include more information useful to investigators, such as weather, elevation, population density and the timing of a fire. ‘We need to capture the things in the data to track them over time. We’re still following things from the 1900s,” she said.
According to Short, wildfire trends in the western United States have shifted with human activity. In recent decades, ignitions from power lines, fireworks, and firearms have become more frequent, in contrast to the once more frequent railroad and sawmill fires.
The study found that vehicles and equipment are likely to be the biggest culprits, possibly causing 21 percent of wildfires without a known cause since 1992. The airport fire in California was just such an event that was more than 23,000 hectares. And an increasing number of fires are the result of arson and accidental ignition – whether from smoke, gunfire or campfires – which account for another 18 percent. In 2017, an Arizona couple’s choice of a blue smoke-spewing firework for a baby revealed that it had ignited the Sawmill Fire, which ignited approximately 47,000 acres.
But these results are not definitive. Machine learning models like those used for the study are trained to predict the likelihood of a given fire’s cause, rather than proving that a specific ignition occurred. Although the model’s model showed 90 percent accuracy between lightning or human activity as the ignition source when tested on fires with known causes, it had more trouble determining exactly which of 11 possible human behaviors were to blame, but it only get it right half the time.
Yavar Pourmohamad, a PhD researcher in data science at Boise State University who led the study, says that knowing the likely causes of a fire can help authorities warn people in high-risk areas before a blaze starts. actually start. “It can give people a hint of what’s most important to be careful about,” he said. “Perhaps AI can become a reliable tool for real action in the future.”
Synolakis, the USC professor, says Pourmohamad and Short’s research is important to understanding how the risks are changing. He advocates proactive actions such as burying power lines underground where they cannot be tied down by winds.
In a 2018 study, it was found that fires along the power lines – such as the Camp Fire that went down in Paradise, California – were increasing the same year. Although the authors note that the power lines do not account for many fires, they are associated with larger areas of burned land.
“We really need to make sure that our communities are more resilient to climate change,” Synolakis said. “As we’re seeing with the extreme conditions in Los Angeles, fire suppression doesn’t.”