AI sensors in the forest can smell a wildfire before it spreads

Across the globe this year, from Greece and Portugal to Canada and Hawaii, wildfires have been burning out of control. And as the world heats up, blazes like these are only predicted to get worse and more frequent.

Faced with this imminent threat to lives and infrastructure, authorities are doubling down on tried and tested firefighting techniques. But they are also investing in new, high-tech approaches, pioneered by an emerging segment of ‘firetech’ startups.   

Telecoms specialist Dryad Networks, based out of Berlin, is one of them. By tapping AI and Internet of Things (IoT) technologies, Dryad hopes to bring down wildfire detection time from several hours to just a few minutes, giving firefighters time to respond more effectively.

“Today, we still largely rely on human sightings to detect fires. But by the time someone can see a wildfire burning through the canopy it is already very hard to extinguish,” Dryad’s CEO Carsten Brinkschulte tells TNW. “The message we’re getting over and over again is that when it comes to battling wildfires — timing is everything.”

Internet of Trees

Dryad has developed a suite of technologies installed throughout the forest that detect wildfires before they spread — an ‘Internet of Trees’ if you will. Unlike conventional tools, like satellites, cameras, and watchtowers, Dryad’s network doesn’t need to see a fire to know it’s there. 

Solar-powered sensors, placed about one per hectare throughout the forest’s understory, detect wildfires in their early smouldering phase by ‘smelling’ tell-tale gases like hydrogen and carbon monoxide in microscopic quantities. They also monitor temperature, humidity, and air pressure. 

an image of a dryad wildfire sensor hanging on a tree