Drones Compete to Spot and Extinguish Brushfires

To the untrained eye, it did not look like a particularly complicated mission. A large black quadcopter drone, more than two meters spanning the propeller tips, sat parked on the grass. Nestled between the legs of its landing gear was a red balloon filled with water. Not far away, on a concrete pad, a stack of wood pallets was ablaze, the flames whipping around in a heavy wind. A student at the University of Maryland (UMD) would fly the Alta X drone all of about 25 meters to the fire. There it would drop the water balloon to extinguish the flames.

In the XPrize contest, drones must distinguish between dangerous fires—like this one—and legitimate campfires. Jayme Thornton

But, of course, it was complicated. The drone needed to hover at about 13.5 meters overhead, and the balloon was configured to detonate at a specific point in midair to ensure optimal water dispersal, as calculated by UMD’s Department of Fire Protection Engineering. On a signal, Andrés Felipe Rivas Bolivar, a doctoral student in aerospace engineering, launched the Alta X toward the fire. As a second, smaller drone outfitted with a thermal camera surveyed the scene from above, Rivas maneuvered the balloon-laden drone to the proper position. After about a half minute, he released the water bomb...and the balloon plummeted to the ground just wide of the platform, bursting with a thwaaaap.

On this warm but blustery day in mid-October, a team of about 20 UMD students and professors were gathered at a fire and rescue training center in La Plata, Md., to demonstrate the building blocks of what could be the future of wildfire fighting. They called their team Crossfire. Their guests were a handful of officials from the XPrize Foundation, which has organized a pair of competitions to vastly speed up wildfire detection and suppression. Twelve other teams are competing with Crossfire in the semifinals for the autonomous wildfire-suppression track of the competition. In the final round, to be held in June 2026, five of those teams will have to find a fire within 1,000 square kilometers of what XPrize calls “environmentally challenging” terrain and then navigate to and extinguish it, all within 10 minutes. The winner collects a US $3.5 million purse—and, hopefully, the world’s wildfire-fighting armies get a powerful new weapon for their arsenals.

The Wildfire Problem

Wildfires are growing more severe and affecting more people worldwide. The November 2018 Camp Fire that burned down 620 square kilometers of Northern California, including most of the town of Paradise, was the most deadly and destructive in the state’s recorded history, and it sent Pacific Gas and Electric, the giant utility responsible for starting the fire, into bankruptcy. XPrize had long been based in the Los Angeles area, so that catastrophe was undoubtedly on the minds of its staffers when they formulated the competition in 2019. “This was just something that was really personal and close to a lot of the individuals at the organization,” says Andrea Santy, program director for the wildfire competition. XPrize eventually organized a separate track of the competition to award $3.5 million for detecting small fires with satellites.

Andrea Santy, one of the program managers from XPrize in charge of the wildfire competition, looks on during Crossfire’s trials.Jayme Thornton

Santy says XPrize’s competition designers met with more than 100 experts in the field, including fire scientists, agency officials, and technologists—“all the experts that you would want at the table were at the table.” Where their views aligned, Santy says, XPrize researchers detected the “core problems.” One of the most important was response time. In the best case, an hour can often pass between when a fire is first detected and when it’s extinguished. XPrize aims to shrink that drastically. An additional $1 million will go to the teams that (per the rules) “successfully demonstrate accurate, precise, and rapid detection.”

Arnaud Trouvé, chair of the UMD’s Fire Protection Engineering department, thinks even the 10-minute limit may not be good enough. “On a red flag day with high-wind conditions, a fire that starts is going to be taking a big size within a matter of tens of seconds,” he said as we waited for the Alta X to try again. “So even the 10 minutes you have to go do something will be too slow.” Whatever comes from the XPrize, he says, will be adopted, but more likely in developed areas, where fires spread more slowly and could be extinguished early on, when firefighters are often busy evacuating residents.

In any event, the time limit pointed most teams—and all the teams to make the semifinals—toward drones. Firefighters have worked, or tried to work, given bureaucratic and other hurdles, with drones for years, but mainly for reconnaissance, says Bob Roper, a senior wildfire advisor for the Western Fire Chiefs Association. Many of the hurdles around using drones have been cleared, but no drone exists yet that can carry enough suppressant to be useful on its own, says Roper. (The smallest helicopter bucket carries 270 liters.) Roper says government-funded fire agencies seldom “have available unrestricted dollars to be able to develop something that’s new.” By sprinkling startups and universities with research funding, the XPrize is poised to make, he says, “a quantum leap difference.”

Team Crossfire

Word of the XPrize wildfire competition reached Trouvé’s desk soon after it launched in April 2023. He joined forces with colleagues in aerospace and mechanical engineering and with xFoundry, a new organization that uses competitions to spur entrepreneurship. (xFoundry’s founder, Amir Ansari, happened to be one of the sponsors of the first XPrize in 1994; his sister-in-law Anousheh is the CEO of the XPrize Foundation.) It didn’t take long to sketch out most of what they brought to La Plata.

The University of Maryland’s Yaseen Taha [right] pilots a spotter drone while Brian Tran looks on. Jayme Thornton

The day began with tests of the detection drone. Its dock opened like flower petals unfolding and the drone, a much smaller quadcopter than the Alta X, shot up into the air. Using a handheld controller, undergraduate Yaseen Taha flew it to a point 35 meters above the burning pallets. Like all the technology Crossfire has deployed, the scout was an off-the-shelf model, made by the Chinese manufacturer DJI. It came with a lot of important features already programmed in, including obstacle avoidance and lidar, and cost just $25,000, according to xFoundry head of products and ventures Phillip Alvarez. “We get a really nice, well-polished system for a pretty low price here, and then we can spend the rest of development on solving the hard stuff,” he said. In total, Crossfire has spent around $300,000, most of it raised from UMD donors, he added.

xFoundry’s Philip Alvarez stands behind the Crossfire team’s drone that’s used for detecting wildfires. Jayme Thornton

The hard stuff, some of it anyway, was visible on a large display monitor showing the feeds from the drone’s two cameras. On the right was the infrared feed; on it, a red square labeled “fire” bracketed the burning pallets. A smaller red fire square appeared up and to the right of this; this was a pile of glowing embers in a bin not far away. These were meant to represent a campfire—the contest rules required systems to distinguish between potentially destructive conflagrations and “decoy fires” that don’t pose a threat. Crossfire’s system made those distinctions based on the drone’s color video feed. That feed runs through an open-source deep learning model known as YOLO (“You Only Look Once”), which recognizes images.

One of Crossfire’s drones scans the terrain and distinguishes between a burning pile of pallets and a small fire in a bin. Robb Mandelbaum

To train it, UMD students fed 40,000 photographs of fires to the model—manually identifying the blazes in about 1,200 of these. The result was that when the program processed the color feed from the drone, it concluded that pallets were a fire, marked on the screen in a blue box, and ignored the bin. Now both camera feeds indicated a blaze in the same place, and the monitor threw up a warning in red: “FIRE DETECTED.” As turkey vultures looked on from high above, the drone identified the fire again from a higher altitude, then with the cameras pointed at a different angle, it finally flew a preprogrammed back-and-forth route through the air that looks like a lawnmower’s path.

An electric Ford F150 truck serves as charger and home base for Crossfire’s system. Jayme Thornton

An electric Ford F-150 pickup, front trunk open, sat off to the side powering a bank of computers that operate the two drones. In the field, it will also process feeds from cameras mounted on poles throughout the forest—an early detection system that will trigger the scouting drone. This was designed by Alvarez, who happens to have a Ph.D. in biophysics, using an even newer version of image-reading AI developed just last year.

All of the teams, Santy says, have proposed something broadly similar: sensors and cameras on the ground or on one or more drones, or both, and AI interpreting the data. How teams get to the fire has been driven by regulation—the FAA has restrictions on drones weighing more than 25 kilograms (55 pounds), as well as autonomous systems dropping payloads, which is why Rivas had to pilot the Alta X. “Some are looking at how we can address the problem within the current regulations, so they’re trying to stay within the 55 pounds,” says Santy. Others are designing systems that ultimately could be deployed only under new regulations. That primarily comes down to either using a swarm of smaller drones or one heavy-lift drone. Teams that fly heavy in the finals will have to get FAA approval for the contest, just as Crossfire would need it to operate the Alta X autonomously.

Crossfire’s fire-suppression drone flies toward a fire carrying a balloon full of water. Jayme Thornton

Curiously, the XPrize appears not to have spurred much innovation in actually putting out a fire. Most teams are using water, though they’re dropping it in a variety of different ways. It’s a work in progress, says Santy. “Teams have been thinking very hard about what works under challenging conditions” like wind, drone movement, and proximity to the fire.

The University of Maryland’s Dahlia Andres works on the Crossfire team’s fire-suppression drone.Jayme Thornton

Crossfire’s approach of detonating water balloons in midair—which has yet to be patented so the team would not describe it in detail—could eventually change the calculation about how much suppressant is needed to fight fires. Typically, aircraft flying at high altitude release a lot of water, which, says Trouvé, mostly misses the burning biomass. “Releasing the water at low elevations and directly above the burning biomass requires much less water,” he says.

With a new balloon installed on the Alta X, the team attempted to attack the fire a second time. This time, Rivas spent several minutes maneuvering the drone to get it in place before dropping the balloon, which appeared to partially detonate, spewing water as it fell. The balloon didn’t completely burst until it hit the platform, spraying water all over and creating a huge puff of steam. But when the smoke cleared, the fire still burned. Crossfire’s detonators, it turned out, were rated for warmer weather than this October day. “We’ve tested this probably 20 different times, and 20 different times it’s been successful,” Alvarez said ruefully.

Crossfire’s drone carries a water balloon skyward, finds the fire, and drops the balloon. Jayme Thornton

But the third attempt, several hours later, was the charm. Rivas whisked the Alta X over the fire. Taha, on the other side of the fire, checked its position and motioned for release. The balloon exploded a few meters below the drone, and a shower of water blanketed the fire. The thermal camera on the observation drone confirmed the fire had been extinguished. Muted “yays” and a smattering of applause broke out.

Crossfire’s Abdullah Shamsan, Derek Paley, Matthew Ayd, and Joshua Gaus [from left] monitor a drone flight. Jayme Thornton

Crossfire is already looking beyond the competition, regardless of whether it makes it to the finals in 2026. Along with Taha, aerospace engineering professor Derek Paley has talked to some 40 potential customers—mainly fire departments and government agencies—for the system Crossfire is developing. He’s currently uncertain whether there are enough organizations willing to adopt the technology to make it commercially viable. So far, he says, “it’s a little bit of an uphill battle, but we’re hoping with the visibility brought to the problem by XPrize” and the momentum of being a finalist—and, better still, some prize money in hand—“we’ll have enough to have a compelling business model.”

Roper, of the Western Fire Chiefs Association, acknowledges that “political considerations” around existing fleets of crewed aircraft will challenge the transition to drones, but he says that these can gain a foothold by operating when and where crewed aircraft can’t, at night, for example. Still, it will take multiple companies commercializing the technology to prod fire departments to purchase drones. Even then, he says, “it’s probably going to have to be adopted either at the federal or the state level first and then there’s a trickle-down effect to the local fire departments.”

If not, Paley says, “our tech is applicable to law enforcement, and other aspects of public safety. It’s just a question of, are we starting a wildfire company, or are we starting a robotics company.”