The nation’s most wildfire-prone state is teaming up with an artificial intelligence platform that “never sleeps” and can detect potential fires before they spiral into chaos.
The California Department of Forestry and Fire Protection (Cal Fire) is partnering with University of California San Diego’s ALERTCalifornia, a public safety program that studies natural disasters, to test a $24 million AI program.
“We’ve got an automated system that never sleeps, never rests, watching the North Bay 24 hours, seven days a week,” Cal Fire Napa-Lake-Sonoma Unit Chief Mike Marcucci told Fox 2.
California is the state most threatened by wildfires in the nation, with 7,396 recorded wildfires in 2021 alone, and 2.5 million acres burned. The Golden State recorded another 7,447 wildfires last year, which burned a combined 331,360 acres.
California’s 2018 Camp Fire was the most deadly and destructive in state history, killing 85 people and injuring 17 civilians and firefighters.
The new AI trial will include collaboration with fire units in San Bernardino, Sonoma-Lake-Napa, Madera-Mariposa-Merced, Nevada Yuba Placer, Shasta-Trinity, and San Luis Obispo, according to Cal Fire.
The program will deploy more than 1,000 high-definition, pan-tilt zoom cameras throughout the state that will work nonstop monitoring for smoke or other signs a fire has sparked.
“From the Oregon border to the Mexican border and everywhere in between,” Marcucci said, “cameras are being added as we speak.”
The high-tech cameras can capture images from 60 miles away during clear days, and 120 miles during clear nights, thanks to its near-infrared night vision.
“They’re mounted on all sorts of different platforms,” Marcucci told NBC Bay Area. “They can spin 360 degrees. They can see at night. We’re working on the infrared technology right now. They can zoom out to great distances. Some pretty crisp images that come out of them. They can also see a pretty large area as well.”
ALERTCalifornia trained an AI system to detect abnormalities on the camera feeds, such as heat, fire, or smoke, while differentiating from other natural particles in the air, such as smog or mist. Emergency centers are alerted once an abnormality is detected, allowing humans to quickly investigate if the situation is an actual threat.
“By harnessing the power of AI, we have the opportunity to revolutionize our firefighting strategies by analyzing vast amounts of data, predicting fire behavior, and providing real-time insights to firefighters on the ground,” Cal Fire said in its announcement of the trial.
California has also embraced drone technology in recent years to help fight fires, deploying the autonomous flying machines to monitor where fires are spreading and the location of trapped individuals.
Democratic Gov. Gavin Newsom has touted the state’s use of high-powered tech to fight fires, saying last month it will keep “more Californians safer from wildfire.”
“In just five years, California’s wildfire response has seen a tech revolution. We’re enlisting cutting-edge technology in our efforts to fight wildfires, exploring how innovations like artificial intelligence can help us identify threats quicker and deploy resources smarter,” Newsom said in June. “And with the world’s largest aerial firefighting force and more firefighters on the ground than ever before, we’re keeping more Californians safer from wildfire. While these resources will help protect our communities, Californians need to remain vigilant for what could be an intense wildfire season this year.”
Other states frequently threatened by wildfires are also making moves to embrace AI to help monitor for smoke and heat, including Washington state announcing in May it will deploy 21 camera stations. Colorado is also installing AI-powered cameras in San Miguel County to help monitor for fires.