Artificial intelligence is already used to detect and monitor wildfires, and researchers are now testing whether it can also help fire officials decide how to allocate crews when multiple fires burn at once.
Why it matters
Climate change is lengthening and intensifying wildfire seasons, increasing the frequency of concurrent fires and forcing high-stakes decisions about how to prioritize limited resources. AI tools can process and organize information faster, potentially speeding up those prioritization choices.
Current state
Jason Fallon, division chief for wildland fire intelligence at the U.S. Wildland Fire Service, told Axios that AI is embedded across many areas of wildfire management in the United States, including detection, monitoring, information dissemination and data transfer. AI-powered cameras, satellite systems and weather-prediction tools are helping agencies in Western states detect fires and deploy crews earlier.
Fallon said AI can "help us quickly work through a workflow to separate noise from reality" when triaging satellite data.
Research approach
Léonard Boussioux, an information systems professor at the University of Washington Foster School of Business, is part of a team researching how machine learning and optimization might assist officials deciding where to send crews during simultaneous wildfires. Their approach predicts how multiple fires could evolve under different suppression levels, then uses a mathematical model to recommend crew deployments. The paper describing the work has not yet been peer reviewed.
Numbers and trends
Last year, 77,850 wildfires were recorded across the U.S., which the National Interagency Coordination Center described as "noticeably higher than the five- and 10-year averages." According to the National Interagency Fire Center, this year’s wildfire season is exceeding the 10-year average in both number of fires and acres burned.
What experts say
"What's hard to do is to predict which fire is going to blow up," Boussioux told Axios. "Which fire should we prioritize right now, knowing that we don't necessarily have [the] resources?" His team is attempting to anticipate how multiple fires might behave simultaneously, making two-week-ahead forecasts and modeling behavior under different suppression scenarios.
Reality check
Fallon noted such research has potential to aid decision-making, but "I don't think we know yet to what degree." He emphasized that AI is intended to augment firefighters, decision-makers and analysts, not replace them. Fire officials remain in control of strategy and action.
AI can reduce cognitive workload and accelerate insights in complex, fast-changing environments, but expertise, experience and risk decisions must still come from humans. "The machine doesn't have 30 years of experience fighting fire," Fallon said. He added that a model might not know local social details — for example, that residents at the end of a road lack vehicles and would need evacuation assistance — because "it only knows what we can provide to it."
Limits and risks
Matt Weiner, CEO of Megafire Action, a nonprofit focused on reducing catastrophic wildfire risk, told Axios that AI won’t solve the problem of massive, destructive wildfires. Still, he said AI can already help prioritize where that work will be most efficient at every scale and help direct the right resources to the right fire.
The Government Accountability Office has warned that AI can provide inaccurate information that could endanger lives and property, and that limited data on rare, extreme events can impede AI’s ability to forecast those fires.
What’s next
Researchers are developing more sophisticated tools to model complex wildfire decisions, but their usefulness will depend on the quality and organization of underlying data. As Boussioux put it: "We already have technology to make things better, but we do not necessarily have data available, or it's not properly managed or organized."
Amy Harder contributed reporting.
