A little after 6:25 am on November 8, 2018, a 911 dispatcher received the first report of a fire near the Poe Dam in northern California. Nineteen minutes later firefighters caught sight of what would become known as the Camp Fire. Drought had dried out plants in the area, and strong winds were blowing in the direction of Paradise, a town 10 miles to the southeast. “This has got potential for a major incident,” fire chief Matt McKenzie reported back to incident command.

An hour later hot embers were raining down on the south side of Paradise, sparking spot fires in advance of the main front. Within 40 minutes of the first spot fires igniting, the main fire front had reached the town. The Camp Fire would go on to burn for another two weeks, destroying Paradise and killing 85 people. It is, along with the recent LA fires, one of the costliest wildfires in US history.

The speed and devastation of recent wildfires has focused attention on early detection—the hope that catching a fire shortly after it ignites will give fire crews enough time to douse it before it becomes uncontrollable. Cameras, satellites, and tree-mounted sensors are all touted as ways to identify blazes as they begin, but firefighters warn that early detection has its limits—and that in some cases no amount of early detection can stop the worst fires from burning out of control.

As was the case with the Camp Fire, 911 calls still make up the majority of first detections, says Marcus Hernandez, deputy chief at the California Department of Forestry and Fire Protection’s office of wildfire technology research and development. Cal Fire also uses AlertCalifornia, a network of more than 1,144 high-definition cameras across the state that can see as far as 60 miles in the daytime and 120 miles at night. The camera network is based at UC San Diego and is monitored by fire professionals at command and control centers across the state.

In mid-2023, AlertCalifornia added the capability to automatically detect smoke columns from its camera footage using AI. “Just the situational awareness that comes from those strategically located cameras was already a benefit before the giant leap forward related to AI anomaly detection,” says Hernandez. Cal Fire also uses a system called FireGuard that uses military satellites to detect heat from wildfires. “That just puts us on alert to check our other tools to figure out if there is a fire or not. We’re going to automatically dispatch.”

Dryad Networks, a startup based in Germany, wants to improve early wildfire detection by fitting trees with remote sensors that can detect wildfire smoke. “It’s a low-cost, solar-powered gas sensor, like an electronic nose. It’s similar to what you have in your home on the ceiling, but it has AI in there and wireless communications built in,” says Carsten Brinkschulte, cofounder and CEO of the company.

According to Brinkschulte each device costs about $104 and can protect about a hectare of forest. California alone has about 13 million hectares of forest, but Brinkschulte says that his company wants to focus on much smaller, high-risk areas where wildfires are more likely to start. Areas of interest to Dryad include near train lines, roads, hiking paths, and power lines, which have been linked to more than 3,600 Californian wildfires since 1992, including the Camp Fire.

“We’re not saying we can detect any fire, particularly lightning-induced fires,” says Brinkschulte. “What we’re focusing on is human-induced fires” in the areas where humans and wildlands interact. Brinkschulte says that the system has been trialed in 50 different deployments, mostly in southern Europe but also twice in California. In one trial the company is working with a lumber firm in South Africa to protect commercial forests from wildfires.

But according to Hernandez, tree-mounted sensors are unproven technology and are expensive to deploy at scale. “We currently do not use those. We experimented with them, and we are happy with AlertCalifornia,” he says. Often the devices would detect fires that weren’t really there. “Anecdotally we had a large quantity of false positives,” says Hernandez, adding that the sensors Cal Fire trialed also struggled to maintain power and signal. Hernandez declined to specify which tree-mounted sensors Cal Fire had tried.

One edge that better wildfire monitoring could provide is the ability to see in real time how wildfires are moving through the environment. “Our effort is really about continuous tracking of the fire after it starts,” says Tim Ball, who, along with Carl Pennypacker, is a principal investigator at the Fire Urgency Estimator in Geostational Orbit (Fuego) project at UC Berkeley.

Popular fire-tracking app Watch Duty already gathers wildfire data and presents it to normal people in real time. The service gained 600,000 users in just one night during the LA fires, unseating ChatGPT to top Apple’s App Store. But this app brings together public data rather than gathering new data for firefighters or officials to use.

Ball and Pennypacker’s idea is to send a satellite into orbit that stays at a fixed location above the western US. The pair say the satellite would be able to detect a five-square-meter wildfire burning at around 500 degrees Celsius. This would be particularly helpful for monitoring spot fires that flare up many miles ahead of the main fire front. The system could be used to detect spot fires igniting in zones that haven’t been evacuated yet and alert the authorities, Ball says.

The researchers are still looking for support to get Fuego off the ground. “We’re working hard to get the government on board,” Ball says. But launching a satellite is expensive and there is—as always—the question of who should pay for wildfire monitoring. “Our biggest challenge is to form a public–private partnership that can get a substantial amount of money and get this thing into space.”

Both Ball and Hernandez agree that early detection can’t stop every wildfire from taking hold. The combination of strong Santa Ana winds, dry conditions, and lots of fuel in the form of dry vegetation for the LA fires was a worst-case scenario. “Early detection would have made no difference in keeping those fires small,” says Ball.