As the world burns hotter and hotter, we are having to find new ways to deal with fire. I have two stories about fire and technology in the Northern Hemisphere. Perhaps later this year I will be able to round this out with stories about fire and technology from the Southern Hemisphere once the seasons shift. Although I world prefer that at least part of this planet has a quiet fire season.
Europe: France, Spain, and Portugal
John Laurenson wrote an August 4 (?), 2026 article for the British Broadcasting Corporation (BBC) news online about the technology being developed to fight fires
Hundreds of thousands of people have been forced to leave their homes across France, Spain and Portugal as wildfires tore through forests and countryside.
In France, four men have already lost their lives fighting the wildfires and another 150 have been injured.
But why are humans and 30-year old planes being used? Why can drones replace soldiers in Ukraine but not firefighters?
Chief sergeant Guillaume Millet, a firefighter of 24 years experience heads the Fire and Rescue Service branch of the CFDT union in the Gironde, the region worst hit by wildfires in France this summer.
He says that while the techniques for tackling fire have not changed much, technology in forest fire detection has.
“The big change, especially in my département, is that now we’ve got cameras assisted by artificial intelligence to watch the forest and see where fires are starting,” Millet says.
“In the Gironde, cameras have replaced the human look-outs we had in watch towers in every town throughout the summer months,” he says. Those lookouts were often students.
The switch has reduced false alarms, he says. “An AI-assisted camera can distinguish with almost total certainty between smoke and dust thrown up by a tractor in a field, for example.”
They have an impressive range as well, detecting fires up to 20km (12 miles) away.
In the Gironde, the system was installed by a company called Midgard. In other parts of France, it’s another French start-up called FireTracking.
“As soon as the system detects a fire, there’s an alert on the fire fighters’ telephones. They open the application and see what the camera is seeing with a x40 [40 times] zoom,” explains FireTracking’s CEO Jean-Simon Chaudier.
“Next to that real-time video there’s a map with the exact location of the fire, the position of any nearby houses and a simulation of how, given the weather, the level of humidity and so on, it is expected to spread from minute to minute,” he adds.
And every minute is vital. “For the past 10 days, for example, we have the feedback from a firefighter that our AI detected seven fires 15 minutes before the first phone call. If you can help a firefighter to save 15 minutes, it’s the difference between a catastrophe and a fire which can be limited to two or three hectares,” Chaudier says.
“After one minute you can put out a fire with a glass of water, after two you need a tank of water, after three minutes you need to send a Canadair,” Chaudier says, talking about the amphibious planes that scoop up water from rivers, lakes and the sea to dump it on the flames that are the spearhead of forest fire fighting here and around the world.
…
AI fire detection is going to get better over the coming years. The French civil protection service has a programme called Condor, for example, which is testing solar-powered drones that carry out continuous patrols with electro-optical cameras and AI.
There are also projects with sensors placed among the trees. Spain’s SenForFire, for example, which measures gases released before flames become visible.
…
TankerVision: AI-powered fire prediction (a Canadian initiative)
A July 16, 2026 University of Toronto news release by Amanda Hacio spotlights TankerVision, Note: A link has been removed,
As wildfires grow larger, faster and impact more communities across Canada, researchers at the University of Toronto Institute for Aerospace Studies (UTIAS) are developing new technology that could give first responders a critical advantage: the ability to predict how a fire will evolve hours into the future.
Professor Steven Waslander (UTIAS) is working with researchers at Natural Resources Canada and Simon Fraser University on TankerVision — a project aimed at creating more accurate, AI-powered fire prediction models.
…
The team has partnered with government agencies and industry, including BC Wildfire, Alberta Wildfire, Canadian Forestry Services, aircraft operator Conair Aerial Firefighting, and Voxelis, a wildfire monitoring service provider.
“Wildfire growth is currently estimated using 15 to 20 prescribed burns from the 1980s, plus data on weather, wind and forest conditions, all fused with decades of human experience,” says Waslander.
“But this method hasn’t been adapted to current fire severity increases due to climate change and involved a great deal of extrapolation from a limited dataset.”
“Our big idea here is to use AI and computer vision to capture unprecedented numbers of fires from the air to build more sophisticated, data-driven wildfire prediction models.”
To do this, high‑resolution colour and infrared cameras and computers are installed inside the piloted aircraft that are currently used to monitor and fight fires.
In 2024, the team began collecting data onboard a bird-dog aircraft, which circles above wildfires to guide water bombers. These planes spend hours tracking the fire line, making them ideal for gathering continuous, high‑quality footage.
:All the storage is on board the aircraft so our partners can review the data before we start working on it to make sure we aren’t logging any confidential information.”
First, each image is segmented by AI to identify which pixels correspond to fire, smoke or ground. This is trickier than it sounds, as capturing the extent of smoke in an image can be difficult for modern segmentation techniques.
The task poses similar challenges to autonomous navigation in adverse weather conditions — variables Waslander is already familiar with as the lead investigator of the WinTOR all-weather driving program.
…
“Last season, we logged 50 fires, which is currently the highest number recorded in one season,” says Waslander.
“This year, we plan to expand the data collection efforts to three aircraft and hope to capture more than 100 wildfires, sufficient to start developing and validating our prediction models.”
The team is now preparing hardware for this fire season and hopes to expand partnerships across the country, including in Ontario, to help transform how Canada responds to wildfires.
The team’s first research paper, focused on segmentation, has been submitted, with a full-system paper and public dataset planned for release in fall 2026.
Waslander says the project resonates deeply with students and researchers who have witnessed the increase in severe fires firsthand.
“I think everyone involved in the project really feels passionately about the direction we’re going and see it as an opportunity to make a real impact on keeping us safe in the years to come as things get hotter,” says Waslander.
…
I can’t find anything more about TankerVision on the Natural Resources Canada or Simon Fraser University websites. Hopefully more information will become available.
Replacing firefighters?
The short answer is: not anytime soon. All these technology initiatives are aimed at improving our ability to find hot sports and fires and to respond quickly.
