Colorado wants to use AI to detect wildfires
DENVER –
A year after the deadliest wildfire in state history burned nearly 1,100 homes, Colorado lawmakers are considering joining other Western states by applying artificial intelligence in hopes of spotting out fires before they burn out of control.
A Colorado Senate committee on Thursday unanimously voted to pass a bill creating a $2 million pilot program that would place cameras on top of mountains and use artificial intelligence to monitor scenes. record and help detect early signs of forest fires. Next, the bill will go to the state Senate Appropriations Committee.
Democratic State Senator Joann Ginal, one of the bill’s sponsors, said: “It can detect just a puff of smoke and that’s the situation in remote areas that can save forests, homes. , property and life”.
The deployment of AI is part of firefighters’ ongoing efforts to use new technology to become smarter about how they prepare and better position their resources. Fire watchtowers once manned by humans have largely been replaced by cameras in remote areas, many of which are high-resolution and equipped with artificial intelligence to distinguish plumes of smoke from haze.
There are hundreds of such cameras scattered throughout California, Nevada, Oregon and a few already in Colorado allowing even casual viewers to view from a distance.
Vaughn Jones, head of wildfire management for the Colorado Fire Department, said the technology “allows us to take very aggressive action in the first place and minimize the impact… no have to wait until the end of the day to start playing catch.”
Historic droughts and recent heatwaves linked to climate change have made wildfires in the western United States more difficult to treat, and scientists say warming weather will continue to make fires worse. fires occur more frequently and are more destructive.
Record storms have lashed California with more than 11 inches (27.94 cm) of rain in recent weeks and heavy snowfalls in other states have improved conditions in the short term, but the drought continues. performed in many western states, according to a report Tuesday. report from the National Oceanic and Atmospheric Administration.
The Colorado program will support 40 fixed camera stations and an additional 6 portable mobile stations to monitor ongoing fires, said Ben Miller, director at the Center of Excellence, which researches firefighting technology, said at a hearing on Thursday.
The AI algorithm behind the camera will try to detect a cloud of smoke and give early warning to first responders, said Miller, who pointed to an AI-caught construction fire near Boulder. in December as an example.
Miller said Boulder County partnered with an AI wildfire detection company called Pano AI, and the software alerted authorities to the fire around the time the first 911 call arrived, Miller said. speak. One home was destroyed and another damaged before the fire was brought under control — a much better result than a year ago when the Marshal Fire, also near Boulder, destroyed more than 1,000 structures. architecture.
“The more you train the model, the better it gets,” says Miller. He also added that his company is very interested in the technology but it is still growing and a pilot program is a good place to start.
Pano AI started working with cities, including the ski resort town of 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 “Machine learning AI is new, it’s exciting, it’s captivating but it’s not perfect,” adding that the company use staff to check for alerts from AI.
Their stations consist of two cameras mounted on a high vantage point, rotated 360 degrees with a 10-mile radius, and connected to the company’s AI software. Each station costs about $50,000 per year. It is not known if the company will be hired to do the pilot if the bill passes.
Arvind Satyam, commercial director of Pano AI, said in an interview that the artificial intelligence uses a dataset of more than 300 million images to teach it what is smoke coming from a fire and what is not. .
After the camera signals a possible fire, photos and information are passed through the company’s intelligence center to check on people — the algorithm may have confused the tractor’s dust cloud with smoke — before being sent to the fire authorities, he said. Satyam added that the benefits go beyond detection, allowing fire agencies to pinpoint the exact location of a fire and monitor a live feed of burns.
AI has gained notoriety for breaking into a number of areas – from creating propaganda and misinformation to writing essays or cover letters about anything a user asks.
David Blankinship, senior technology adviser for the Western Association of Fire Directors, said in an interview that fire agencies have relied on this type of detection technology, particularly in California, where firemen program has become more widely used.
However, Blankinship notes that “these cameras, even with AI, are only one component of the actual solution at work.”
When a vote was called to pass the bill, Republican state committee member Senator Rod Pelton was enthusiastic.
“I don’t want to be the bucket of water on this bill so I’ll say ‘Yes’,” he said.
——
Jesse Bedayn is a member of the Associated Press/Report for the America Statehouse News Initiative. Report for America is a nonprofit national service program that places journalists in local newsrooms to cover confidential issues.