The first place winner, worth $500,000, was SIRIUS Wildfire Alliance, based in the United Kingdom. That organization offered a system capable of identifying and modeling the possible spread of forest fires, based on optical and radar data from satellites.
A $250,000 prize went to the second-place winner, Arizona-based Team Snuffed. The competition’s press release credited Team Snuffed for providing “transparent, auditable and uncertainty-aware wildfire detection” and highlighted the solution as especially easy to use for firefighters.
Special recognition awards of $100,000 each went to Florida-based MyRadar, Louisiana-based DeepFire and German company Mayday.AI which adapted an algorithm originally designed to detect volcanic ash to help detect wildfire smoke through cloud cover.
Send the drones
Detecting wildfires quickly is one challenge, but getting firefighting resources to the scene quickly enough to stop the spread is another. Teams competing in the autonomous wildfire response track put their technologies to the final test in the sparsely developed rural landscape of Nenana, Alaska, near Fairbanks, in June 2026.
Finalists typically deployed ground sensors and sometimes drones to help detect wildfires in a 386-square-mile area of Alaska, about the size of the San Francisco Bay Area in California or San Antonio in Texas. Once a high-risk fire was detected, they launched their own versions of firefighting drones that flew to the scene and attempted to extinguish the fire.
The three finalists successfully detected the high-risk fire in less than 10 minutes, while two of the three also deployed drones that attempted to put out the main fire. But none of them managed to completely extinguish the fire, so the grand prize was also out of reach on this track.
