AI eyes in the sky: New satellites and artificial intelligence are transforming wildfire detection
Ben Tracy from Climate Central reports on how Earth Fire Alliance satellites and A.I.-powered camera networks are helping detect wildfires earlier, giving firefighters critical time to stop small blazes before they threaten communities.
As firefighters battle fast moving wildfires near Spokane, Washington, thousands of residents
have been forced to evacuate, homes have been destroyed, and thick smoke has blanketed
parts of the Inland Northwest. The fires are the latest reminder that when a wildfire is detected
can be just as important as where it starts. A blaze found within minutes can often be contained
before it spreads. Wait too long, and a small spark can become a major disaster.
A new effort to shorten that timeline began in July when a SpaceX rocket carried the first three
FireSat satellites into orbit. The trio is the first part of a planned network of 50 satellites built
solely to spot wildfires while they are still small enough to stop.
FireSat is designed to fill an important gap. Existing weather and Earth observing satellites can
detect large fires, but they often lack the resolution or revisit the same location too infrequently
to spot small fires shortly after they ignite. FireSat is designed to detect fires as small as a
beach bonfire and, once the full constellation is deployed, scan every point on Earth about every
20 minutes.
The satellites use infrared sensors and artificial intelligence to search for heat that could signal a
new wildfire. The system compares new images with earlier ones and accounts for factors such
as weather conditions and nearby sources of heat before sending alerts to emergency
responders. The goal is to identify real wildfires while reducing false alarms.
FireSat is designed to work alongside a growing network of cameras on the ground that use
artificial intelligence to search for smoke and heat. Together, the systems could give firefighters
their earliest warning yet that a fire has started.
Flames and smoke seen in Spokane County, Washington, on Aug. 3, 2026. (Image credit: DNR)
Finding fires faster
Wildfires have become one of the most destructive natural disasters in the United States. Rising
temperatures, prolonged drought, and more frequent stretches of hot, dry, and windy weather
have made fires easier to ignite and harder to contain.
Climate Central reports that some parts of the western United States now experience about two
more months of fire weather each year than they did in the 1970s.
For firefighters, every minute matters.
Cameras That Never Stop Watching
High in the mountains west of Denver, two technicians climb a 150-foot cell tower to inspect a
pair of wildfire detection cameras built by Pano AI.
“There are two Pano AI cameras,” said Arvind Satyam, co-founder of the San Francisco startup.
“They’re sitting on top of that cell tower.”
Pano AI has installed more than 1,400 cameras across 17 states. The cameras continuously
scan the landscape from towers and mountain tops. Artificial intelligence reviews every image,
searching for smoke during the day and heat after dark.
“The AI algorithms are being run continuously on that imagery to say ‘smoke, not smoke,’”
Satyam explained. “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.”
If the system spots a possible fire, a human analyst reviews the images before an alert is sent to
fire agencies. That process often takes only a few minutes.
Getting there before the first 911 call
Firefighters say that head start can make all the difference.
“It’s a great tool to validate what’s going on,” said 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.”
California has built one of the largest camera networks in the country through Alert California.
The system includes more than 1,200 cameras used by Cal Fire.
“This is all of our cameras,” said Chief Phillip Selegue standing before a wall of live camera
feeds in one of Cal Fire’s control centers.
Selegue says the system now detects about half of all wildfires before anyone calls 911.
One recent fire near Fresno was spotted about 20 minutes before the first emergency call
reached dispatchers. Firefighters were able to respond quickly and keep the blaze from
growing.
“At Cal Fire, one of our missions is to suppress 95% of our fires at 10 acres or less,” Selegue
said. “This system helps us in accomplishing that goal.”
“We trust it enough that when we receive that detection, we’re already starting the process of
sending resources to it.”
The fires people never hear about
Ground cameras can only see the landscapes in front of them. Satellites can watch vast
stretches of remote forests, mountains, and grasslands where there are no cameras and often
no people to report a fire. The two systems are designed to work together. Together, they could
give firefighters a faster and more complete picture of where fires are starting.
A fire that is detected quickly and extinguished while it is still small rarely attracts attention. That
is exactly the outcome firefighters are working toward.
“The fires that this system has helped us dispatch resources to are the fires you don’t read
about in the papers,” Selegue said. “The ones you don’t see."
