Maxwell Brodie vividly remembers the destructive wildfires he experienced while growing up in the interior of British Columbia.
One night in 2003, lightning struck a tree around 4 a.m., sparking a massive fire that ravaged Mount Okanagan Park. The winds picked up, the sky turned orange and more than 30,000 people were evacuated from his hometown. Brodie remembers helping his father attach a garden hose to protect their cedar roof from falling ash.
That experience would inspire Brodie nearly two decades later to launch a software startup that gives autonomous helicopters and other aircraft the ability to sense and suppress wildfires.
“It’s something you don’t forget as a kid,” said Brodie, co-founder and chief executive of Rain, a company based in Alameda. “As we face these increasingly frequent and severe fires, it becomes more important to expand response capacity to include the ability to respond at night in conditions of smoke and high winds. »
Brodie is part of a small but growing group of California entrepreneurs promising new technologies — much of it powered by artificial intelligence — that could radically change the way firefighters prevent and fight wildfires.
In the face of budget shortfalls, fire departments have historically been cautious about adopting expensive and often experimental firefighting technologies that have not been proven in the field. But the scale of this unprecedented situation Fires in Los Angeles which destroyed thousands of structures and killed at least 27 people has sparked new interest and urgency to find more effective ways to fight wildfires.
“It’s just a completely different scale…We’re going to have to find new ways to fight (the fires),” said Josh Wilkins, a retired fire captain with the San Bernardino County Fire Department.
In Silicon Valley, major tech companies, including Google and AI giant Nvidia, have invested in research that could help firefighters better detect and track wildfires.
Nvidia announced in 2021 that it is partnering with Lockheed Martin, the U.S. Department of Agriculture Forest Service and the Colorado Division of Fire Prevention and Control to create a digital version of a fire that allows firefighters and commanders to intervention to better understand how a fire spreads and suggest more enlightened ways to delete it.
“The 21st century security technologies we are developing to address security threats are directly applicable to the complex environment of a wildfire,” said Dan Lordan, senior program manager at the Lockheed Martin Artificial Intelligence Center in the Connecticut.
AI-based decision aids may soon be able to support first responders’ command decisions, but they depend on the availability of data and its proximity to real time, Lordan said.
Space agency NASA is also working on technology that could allow drones and remotely piloted helicopters to fly at the same time to fight wildfires, even when visibility is low.
Fire departments across the state are already using an AI tool, run by UC San Diego, that can detect fires in video footage so they can quickly respond to flames. Known as ALERTCalifornia, the program deploys more than 1,144 cameras and sensor networks that capture live video 24 hours a day.
The California Department of Forestry and Fire Protection worked with ALERTCalifornia and DigitalPath to develop the AI tool.
“It creates a network that monitors California,” said Cal Fire Battalion Chief David Acuña.
There have been some successes. Last month, for example, ALERTCalifornia’s AI system detected a fire in Black Star Canyon and alerted the Orange County Fire Authority by 2 a.m., firefighters extinguished the fire and contained it to less than a quarter of an acre.
Still, while ALERTCalifornia helped save lives, its limitations were also exposed during the Los Angeles fires, in which powerful winds fueled flames that spread so quickly that firefighters couldn’t keep up. .
To improve its capabilities, Cal Fire is testing new equipment with BurnBot, a South San Francisco company that operates large vehicles capable of conducting controlled burns with little or no smoke. The advanced vehicles, called RXs, are equipped with propane torches that allow operators to control the length and temperature of the flames. They also have water spray nozzles and a heavy roller to extinguish flames.
Wilkins, who advises BurnBot and other wildfire prevention startups, believes the vehicles could have slowed the spread of the Los Angeles fires if they had been deployed.
“Once we get to wind-driven fires, you’re fighting the embers,” Wilkins said. “Basically, it’s millions and millions of matches flying through the air and a big bush on fire can transmit thousands of embers, and each of those embers has the potential to ignite whatever it lands on. “
Acuña said the agency is still evaluating BurnBot’s vehicles and waiting for data to help determine how or if they will be used.
One of the obstacles to more widespread use of these futuristic firefighting tools, including sensors capable of detecting smoke and fires, is a lack of funding from the private and public sectors.
“This has been a wake-up call to all of us as to what we are facing,” said Sonia Kastner, co-founder and chief executive of San Francisco-based Pano AI. “We need a step change in our approach to firefighting and natural resource management. »
Kastner knows the challenges well. She launched Pano AI, which built an AI-based platform to detect fires and alert emergency responders, after the Campfire 2018 which left 85 people dead, burned 153,336 acres and caused losses estimated at $16.5 billion.
Pano AI relies on cameras, placed on high vantage points like cell phone towers, to scan the surrounding area and transmit video images to emergency personnel. They have been used in Ukiah and Rancho Palos Verdes in California and other states.
The Department of Homeland Security operates a technology center within its Washington-based Science and Technology Directorate, which has supported the development of sensors to detect fires and toxic chemicals.
S&T and N5 Sensors conducted a controlled burn in Stafford, Virginia ahead of the 2023 wildfire season. The data collected was used to improve the sensors and their detection capabilities.
(N5 sensors)
About 450 so-called Alpha and Beta sensors, which can cost a few thousand dollars each, have been deployed in areas including Orange County and Bay Area cities and have helped detect fires in Hawaii, Colorado and in Oakland, California.
To support the initiative, Homeland Security received $4 million in funding over four years, but the agency has been unable to secure more federal money, said Jeff Booth, director of the United Nations Technology Center. sensors and platforms of the Ministry’s Science and Technology Directorate.
“I no longer have federal funding to go further,” Booth said. “Maybe with the new administration, they might see the benefit of rolling this out even further.” »
Teams prepare for a SuperVolo XL flight at Monterey Bay Academy Airport near Watsonville, California.
(Don Richey/NASA Ames)
For startups like Rain, getting buy-in from investors and firefighters is essential.
Founded in 2019, Rain operates out of a former traffic control tower at the former Naval Air Station Alameda. The company, which has 15 employees, raised $9.7 million in seed funding led by venture capital firm DBL Partners.
Rain has been working with Lockheed Martin’s Sikorsky Company and the Orange County Fire Department in hopes of putting his technology into use.
“When there is that partnership between innovators in the fire community and technologists, that’s what opens up entirely new tools, technologies and markets,” said CEO Brodie.