When the Old Trails fire burned through a neighborhood in Spokane, Washington, on 10 August 2026, it showed how quickly wildfires can turn into a community emergency. New detection systems are being built around one goal: find fires while they are still small enough to stop.
That effort now reaches from mountain towers to orbit. Artificial intelligence is helping cameras search for smoke and heat on the ground, while a new satellite network called FireSat is designed to scan the planet for early signs of fire.
FireSat brings wildfire detection into orbit
A SpaceX rocket carried the first three FireSat satellites into orbit in July. The network is designed to fill a gap in wildfire detection by spotting fires as small as a beach bonfire, then scanning every point on Earth about every 20 minutes once the full constellation is deployed.
The satellites use infrared sensors and artificial intelligence to search for heat that could signal a new wildfire. FireSat compares new images with earlier ones and checks factors such as weather conditions and nearby heat sources before sending alerts to emergency responders.
That comparison matters because not every hot spot is a wildfire. A system that reacts to every source of heat could overwhelm emergency crews with false alarms, so FireSat aims to identify real fires while reducing those mistaken alerts.
The satellite network is designed to work alongside a growing group of AI-powered cameras on the ground. Together, these systems offer different views of the same problem: satellites can scan broad areas from orbit, while cameras can keep watch over specific landscapes from towers and mountain tops.
Ground cameras keep watch day and night
Pano AI has installed more than 1,400 cameras across 17 states. The cameras continuously scan the landscape, reviewing images for smoke during the day and heat after dark. Their AI systems run on the incoming imagery, looking for smoke or heat signatures that might signal a fire.
Arvind Satyam, co-founder of Pano AI, described the equipment during a camera installation: “There are two Pano AI cameras. They’re sitting on top of that cell tower.”
He explained how the system sorts the images: “The AI algorithms are being run continuously on that imagery to say ‘smoke, not smoke,’ At night-time, 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.”
Human analysts review potential fire images before alerts go to responders. The image review and alert process often takes only a few minutes, giving firefighters a head start before a fire grows.
Brendan Finnegan, assistant chief with West Metro fire rescue near Denver, described the value of that early warning: “Having those eyes that can alert us well in advance of potentially a 911 call make it a valuable tool for us.”
California has built one of the largest camera networks in the country through Alert California, which includes more than 1,200 cameras used by Cal Fire. Chief Phillip SeLegue has stood before a wall of live cameras connected to that system, showing how many separate views can feed into wildfire response.
Colorado spots fires before they become large
Colorado’s wildfire fight now begins from the air in some cases, before a fire is visible to the naked eye. Two Pilatus single engine aircraft searching for lightning-caused fire starts detected 164 fires across the state during July, and most never grew into large wildfires.
Andrea Drinkhouse, an aerial fire spotter for the Colorado Division of Fire Prevention & Control, has worked in that role for eight seasons. During one flight, she and the other spotters found 25 fires. On another shift, they found 23 and 22 fires.
The fires detected in July were often extremely small, about the size of a dinner plate. The aircraft may have only a few minutes over each one before moving on to search for the next possible fire, making fast detection and clear decisions important.
Jesse Moreng captured the appeal of finding a fire before it spreads: “It’s so cool to find them small.” Drinkhouse put the mission more simply: “It’s the purpose of our job.”
Lightning-caused fires are now appearing at higher elevations, in places that historically would have been protected by snow during the summer. The Elk Fire in Hinsdale County has burned over 7,000 acres, showing how a small ignition can become a major threat.
The cost of wildfire smoke reaches beyond the burn area. Michigan suffered $6.68 billion in economic losses due to wildfire smoke in July, adding another reason for emergency teams to find fires before they spread and smoke travels far from the flames.
FireSat, AI cameras, and aircraft spotters do not replace firefighters. They give those teams more ways to see a fire at the start, when a few minutes can shape everything that follows.
Based on
