The Pulse
XPRIZE Wildfire Teams Detect Fires, but Miss Suppression Goal
XPRIZE’s Alaska trial showed that detecting a wildfire within 10 minutes did not guarantee teams could extinguish it in time. Three finalists shared $2.5 million in awards.
AI.info Team · Written with AI · fact-checked ·
“The really exciting part was, we did have a team that was able to do all of the actions within the 10 minutes and very accurately hit the fire,” Santy said. “But they weren’t able to put enough suppressant on it to knock it down entirely.”
Andrea Santy, program director of XPRIZE Wildfire, speaking to Ars Technica
Detection passed; suppression did not
XPRIZE named the awardees in its $11 million Wildfire competition on September 23, 2026, after field trials tested how teams could detect and respond to wildfires. In the Alaska autonomous-response trial, all three finalist teams detected the high-risk fire in under 10 minutes. Two sent drones to attack it, but none fully extinguished the fire in time to claim the track’s grand prize.
The competition set a demanding test: teams had to find and suppress a high-risk fire across 1,000 square kilometers of challenging terrain without disturbing nearby decoy fires. XPRIZE awarded $2.5 million among the three finalists, while the grand prize went unclaimed. The trial showed that teams could detect the target quickly, but not that they could complete the full response within the deadline.
Anduril and Dryad took different routes
First-place winner Anduril Industries received $1.2 million for a system built around its Lattice software platform, which linked cameras, sensors and drones in a detection-to-suppression process. The company also received a separate $1 million Lockheed Martin bonus for rapid and precise detection. Ars Technica reported that Anduril used a sensor-equipped tower, aerial surveillance drones and a Ghost-X aircraft that dropped fire-retardant balls.
Dryad Networks won $800,000 with a ground-based approach: a 170-sensor field network paired with Silvaguard drones. The sensors were designed to detect gases associated with smoldering fires; an observation drone then helped locate the fire before a suppression drone was sent in. AURA Foresight, a collaboration between UK and Australian teams, took third place and received $500,000. XPRIZE said AURA met the critical 10-minute detection gate.
Satellite systems earned separate awards
XPRIZE also recognized five teams in its space-based detection and intelligence track, awarding $1.05 million in total. The final trial took place in Australia in April 2026. SIRIUS Wildfire Alliance won $500,000 for integrating radar and optical satellite data to characterize fires and model their spread; Team Snuffed received $250,000 for a probabilistic data-fusion system designed to make detections auditable and account for uncertainty.
MyRadar, DeepFire and Mayday.AI each received $100,000 in special-recognition awards. Their cited strengths included commercial readiness, operational fire-spread alerts and adapting an algorithm developed for volcanic ash to identify smoke through cloud cover.
The remaining gap is the last mile
For the Alaska finalists, detecting a fire did not guarantee enough suppressant reached it quickly enough to stop it. The competition’s autonomous-response test required the full chain—from identification to suppression—to work inside the same 10-minute window. As Santy told Ars Technica, one team completed the actions and accurately reached the fire within the time limit, but did not deliver enough suppressant to knock it down entirely.
XPRIZE says the competition will move into an impact phase focused on further testing and integration with wildfire agencies. The award announcement identifies the prize recipients and their technologies; the trial reporting adds that full suppression remained beyond the finalists’ results.