CO Bill That Proposes Using Artificial Intelligence to Detect Wildfires Moves in the Legislative Assembly

A year after the most devastating wildfire in state history destroyed nearly 1,100 homes, Colorado lawmakers are considering joining other western states in implementing artificial intelligence in the hope of detecting fires before they get out of control.

A Colorado Senate committee on Thursday voted unanimously to move a bill to create a $2 million pilot program that would place cameras on mountaintops and use artificial intelligence to track footage and help spot early signs of a wildfire. The bill will then go to the State Senate Appropriations Committee.

“It can only detect a puff of smoke, and it is this situation in remote areas that can save forests, homes, property and lives,” Democratic Senator Joan Jinal, one of the bill’s sponsors, said at the hearing.

CO LEGISLATORS USE ARTIFICIAL INTELLIGENCE FOR EARLY FIRE DETECTION

The introduction of artificial intelligence is part of an ongoing effort by firefighters to use new technologies to become smarter about how they prepare and better allocate their resources. Fire watchtowers, once manned, have largely been replaced by cameras in remote areas, many of which are high-resolution and equipped with artificial intelligence to distinguish between a plume of smoke and morning mist.

There are hundreds of these cameras scattered across California, Nevada, Oregon and several already in Colorado that allow even casual viewers to remotely watch what is happening.

Vaughn Jones, who heads wildfire management at the Colorado fire prevention agency, said the technology “allows us to take very aggressive action early on and contain the impact … without waiting until the end of the day to start playing catch-up.”

Historic drought and recent heatwaves associated with climate change have made it harder to fight wildfires in the American West, and scientists say warmer temperatures will continue to make fires more frequent and destructive.

Flames rise from mountain ranges as a wildfire burns near a farm on October 22, 2020 near Granby, Colorado.
(AP Photo/David Zalubowski, file)

Record-breaking hurricanes hitting California in recent weeks with more than 11 inches of rain and large snow dumps elsewhere have improved conditions in the short term, but drought persists in many western states, according to a National Oceanic and Atmospheric Administration report released Tuesday.

The Colorado program will support 40 fixed cameras and another six mobile stations that can be moved to monitor ongoing fires, Ben Miller, director of the Center of Excellence, which researches firefighting technologies, said at a hearing Thursday.

The AI ​​algorithm behind the camera will try to detect the smoke plume and alert first responders in advance, Miller said, pointing to a building fire detected by AI technology near the city of Boulder in December as an example.

Boulder County worked with wildfire detection company Pano AI, Miller said, and the software alerted authorities to the fire around the time the first 911 call came in. One house was destroyed and another damaged before the fire was contained – a much better result than the year before, when the Marshall Fire, also near Boulder, burned more than 1,000 structures.

REPUBLIC SENATOR INTRODUCES BILLS RELATED TO BIDEN CLIMATE AGENDA: “ENERGY IS THE BASIS OF OUR ECONOMY”

“The more you train a model, the better and better it gets,” Miller said, adding that his agency is very interested in the technology but that it is still evolving and that the pilot program is a good place to start.

Pano AI started with cities, including the ski resort of Aspen, Colorado, and has expanded to cities, counties, and even Pacific Gas & Electric in six states. Katherine Williams, director of state development for Pano AI, who testified at the hearing, said “AI machine learning is new, exciting, glamorous, but not perfect,” adding that the company is using employees to validate AI alerts.

Their stations include two cameras mounted at a high vantage point, rotating 360 degrees with a 10-mile range and connected to the company’s artificial intelligence software. Each station costs approximately $50,000 per year. It is not known if the company will be hired for the pilot if the bill passes.

Arvind Satyam, commercial director of Pano AI, said in an interview that the AI ​​uses a dataset of more than 300 million images that teach it what is and isn’t smoke rising from a fire.

CLICK HERE TO GET THE FOX NEWS APP

As soon as the camera signals a possible fire, the photos and information pass through the company’s intelligence center to check people – the algorithm could have mistaken a dust cloud from a tractor for smoke – before they are sent to the fire departments, he said. Sathyam added that the benefits go beyond detection, allowing fire departments to pinpoint the location of a fire and monitor the live feed of the fire.

AI has gained notoriety for infiltrating a number of areas, from creating propaganda and misinformation to writing essays or cover letters about what the user is requesting.

David Blankinship, senior technology adviser for the Western Association of Fire Chiefs, said in an interview that fire departments have come to rely on this type of detection technology, especially in California, where programs have become more widespread.

However, Blankinship noted that “these cameras, even with artificial intelligence, are only one component of a real working solution.”

When a vote was called to send the bill forward, Republican state committee member Senator Rod Pelton was enthusiastic.

“I don’t want to be the bucket of water on this bill, so I’m going to be a fiery ‘Yes’,” he said.

Content Source

Dallas Press News – Latest News:
Dallas Local News || Fort Worth Local News | Texas State News || Crime and Safety News || National news || Business News || Health News

texasstandard.news contributed to this report.

Related Articles

Back to top button