DENVER (AP) — A year after the most destructive wildfire in state history burned nearly 1,100 homes, Colorado lawmakers are considering joining other western states in using artificial intelligence in hopes of detecting blazes before they do to get out of control.
A Colorado Senate committee on Thursday voted unanimously to move forward with a bill to create a $2 million pilot program that would place cameras on mountain tops and use artificial intelligence to monitor footage and detect early signs of wildfire. The bill will next go to the State Senate Budget Committee.
“It can only detect a wisp of smoke, and it’s that kind of situation in remote areas that could save forests and homes and land and lives,” said Democratic State Senator Joann Ginal, one of the sponsors of the bill, in the hearing.
The use of AI is part of an ongoing effort by firefighters to use new technologies to smarter prepare and better position their resources. Fire lookout towers once manned by humans have largely been replaced in remote areas by cameras, many of which are in high definition and equipped with artificial intelligence to distinguish a plume of smoke from morning fog.
There are hundreds of such cameras scattered across California, Nevada, Oregon and a handful already in Colorado, allowing even the casual viewer to watch from afar.
Vaughn Jones, chief of wildfire management at the Colorado Fire Department, said the technology “allows us to intervene very aggressively early on and keep the impact low…and not wait until the end of the day to start catching up.”
A historic drought and recent heatwaves linked to climate change have made fighting wildfires in the American West more difficult, and scientists say warming weather will continue to make the fires more frequent and more destructive.
Record-breaking storms that have drenched California with more than 11 inches of rain in recent weeks and large dumps of snow in other states have improved conditions in the short term, but drought is lingering in many western states, according to a Tuesday report by the National Oceanic and Atmospheric Administration.
The Colorado program would support 40 fixed camera stations and six other mobile stations that can be moved to monitor ongoing fires, Ben Miller, director of the center of excellence that researches firefighting technologies, said at Thursday’s hearing.
The AI algorithm behind the camera would attempt to detect a plume of smoke and alert first responders early, said Miller, pointing to a building fire captured by AI technology near the town of Boulder in December as an example.
Boulder County had partnered with an AI wildfire detection company called Pano AI, and the software had alerted authorities to the fire around the time the first emergency call came in, Miller said. One home was destroyed and another damaged before the fire could be contained – a far better result than a year earlier when the Marshal Fire, also near Boulder, burned down over 1,000 buildings.
“The more you train the model, the better it gets,” said Miller, who added that his agency is very interested in the technology, but it’s still nascent and a pilot program is a good place to start.
Pano AI began working with cities including ski resort Aspen, Colorado and has expanded to cities, counties and even Pacific Gas & Electric in six states. Kathryn Williams, Pano AI’s director of government development, who testified at the hearing, said, “AI machine learning is new, it’s exciting, it’s glamorous, but it’s not perfect,” adding that the company uses people to review alerts from the AI.
Their stations include two cameras mounted at a high vantage point, rotating 360 degrees with a 10-mile radius (about 16 kilometers) and linked to the company’s AI software. Each station costs about $50,000 annually. It is not known if the company would be hired for the pilot if the bill goes through.
Arvind Satyam, chief commercial officer at Pano AI, said in an interview that the artificial intelligence uses a dataset of over 300 million images that teaches it what smoke rising from a fire is and isn’t.
Once a camera signals there might be a fire, the photos and information are passed through the company’s intelligence center for human verification — the algorithm may have mistaken a tractor’s cloud of dust for smoke — before being passed on to the fire department, he said. Satyam added that the benefits go beyond detection, allowing firefighters to pinpoint the location of a fire and monitor a live feed of the burn.
AI has been known to invade a range of areas – from creating propaganda and disinformation to writing essays or cover letters about anything the user desires.
David Blankinship, senior technology advisor for the Western Fire Chiefs Association, said in an interview that fire departments rely on this type of detection technology, particularly in California where the programs have become more widely deployed.
However, Blankinship noted that “these cameras, even with AI, are just one component of the actual solution that works.”
When a vote was called to introduce the bill, Republican Senator Rod Pelton’s committee member was enthusiastic.
“I don’t want to be the bucket of water on this bill, so I’m going to say a fiery ‘yes,'” he said.
___
Jesse Bedayn is a corps member for the Associated Press/Report for America Statehouse News Initiative. Report for America is a nonprofit national service program that brings journalists into local newsrooms to cover undercover topics.
Copyright 2023 The Associated Press. All rights reserved. This material may not be published, broadcast, transcribed or redistributed without permission.