Eyes in the Sky: How Artificial Intelligence Is Changing the Fight Against Wildfires

View guidelines for use of these broadcast-ready news packages.

Click here for the full media package

BY BEN TRACY, SENIOR CLIMATE CORRESPONDENT ON ASSIGNMENT FOR CLIMATE CENTRAL

Wildfires are now among the deadliest and most costly natural disasters in the United States. In 2024 alone, nearly 65,000 wildfires burned close to 9 million acres of land and destroyed more than 4,500 structures, according to the National Interagency Fire Center.

With fire seasons becoming longer and more intense due to climate change, early detection has never been more critical. Now, artificial intelligence is helping to spot wildfires before they explode into dangerous infernos — and in some cases, even before anyone calls 911.

High in the mountains above Denver, two technicians scale a 150-foot cell tower to inspect a new kind of wildfire detection tool: a pair of AI-powered cameras developed by Pano AI.

“There are two Pano AI cameras,” says Arvind Satyam, co-founder of the San Francisco-based startup. “They’re sitting on top of that cell tower.”

Over the past four years, Pano AI has deployed nearly 1,000 high-resolution cameras across 10 western states. Each six-megapixel camera can swivel, scan, and capture sweeping views of fire-prone landscapes.

So what exactly is Artificial Intelligence (AI) doing?

“The AI algorithms are being run continuously on that imagery to say ‘smoke, not smoke,’” Satyam explains. “At nighttime, we’re looking at heat signatures — so heat versus cold. And then we’re able to zoom in and validate that it is a potential fire start.”

Once a potential fire is detected, a human analyst reviews the image, and if needed, alerts fire agencies — often within minutes.

“It’s a great tool to validate what’s going on,” says Brendan Finnegan, Assistant Chief with West Metro Fire Rescue near Denver. “Having those eyes that can alert us well in advance of potentially a 911 call make it a valuable tool for us.”

Asked whether this technology is a nice-to-have or a must-have, Finnegan is direct: “I think it's a have-to-have in our toolbox now.”

The urgency behind this new technology is driven by the reality of a warming climate. Climate Central reports that in some western regions, the number of fire weather days has increased by two months per year compared to the 1970s. That means more hot, dry, and windy days — the perfect conditions for fast-spreading fires.

In California, Cal Fire has its own AI-powered camera system known as Alert California. It includes more than 1,200 cameras, and Chief Phillip Selegue says they’ve become a critical part of fire response.

“So this is all of our cameras,” Selegue says, standing in front of a bank of monitors. 

Nearly 40% of the time, the system has detected fires before anyone calls 911. In one case this past July, a camera spotted a fire near Fresno a full 20 minutes before the first emergency call came in. That fire was quickly contained.

“At Cal Fire, one of our missions is to suppress 95% of our fires at 10 acres or less,” Selegue says. “This system helps us in accomplishing that goal.”

When asked how much they trust the AI system, Selegue responds: “We trust it enough that when we receive that detection, we’re already starting the process of sending resources to it.”

And while these may not be the fires that make headlines, they’re the ones that could have — if AI hadn’t caught them first.

“The fires that this system has helped us dispatch resources to are the fires you don’t read about in the papers,” says Selegue. “The ones you don’t see.”