Skip to Content

California firefighters use AI to snuff out wildfires before they explode

RIVERSIDE COUNTY, Calif. (CNN, KYMA/KECY) - Experts say the best way to stop a wildfire is to catch it before it spreads.

Now, California Fire (Cal Fire) officials say they've got a new tool to help them do that: Artificial intelligence (AI).

Cal Fire and the University of California (UC) San Diego have teamed up using a massive network of cameras across the state and AI to spot those fires early, and it seems to be working.

In California, where wildfires are a constant threat, firefighters want every advantage they can get on a blaze before it becomes an inferno.

A leg up

"While I was asleep in bed, my phone dinged," said Scott Slumpff, Batallion Chief of Cal Fire's Intel Program.

Slumpff got that leg up while testing new technology in July. He got a text message with a link to a video of a fire that started in the middle of the night, deep in the California wilderness.

"The dispatch center there was not aware of the fire," Stumpff added.

But something else was: AI.

New tech to recognize fires early

Cal Fire, in partnership with UC San Diego’s ALERTCalifornia Program and its network of more than 1,000 cameras across the state, is using the technology to recognize a fire early on.

"The next morning, that fire would have been a fire of significance," said Phillip SeLegue, Staff Chief for Cal Fire's Fire Intelligence.

Instead, firefighters were dispatched immediately, knocking the blaze down before it did major damage.

"the fires that you don't hear about in the news is the greatest success of this," SeLegue shared.

New eyes

These cameras are the new eyes for firefighters. These two positioned more than 5000 feet above sea level can see across the massive Southern California valley, and they're really adding precision to the spotting of wildfires compared to more traditional ways like a lookout station.

With this new AI technology, they can often spot wildfires more quickly than the human eye can.

Here’s how it works: If someone looked at an image, could they spot a fire? Probably not. However, if someone were to notice a red box on the right side, that’s where AI has detected a faint column of smoke.

"There's nothing on that horizon. Then, something appears on that horizon that wasn't there before that could be smoke, the camera will pick that up and go, 'That does not look normal,'" said Brian Norton of ALERTCalifornia.

"We have multiple successes of fires at night that had gone undetected that we were able to suppress before a 911 call had even come into the command centers," SeLegue added.

Tech won't replace people

The pilot program worked so well that Cal Fire recently expanded it to all 21 of its dispatch centers, where an official will validate the imagery to make sure it is not just dust or clouds.

"Our goal as an agency is to keep 95% of our fires at 10 acres or less. So, this tool increases our ability to ensure that we’re keeping those fires small," SeLegue explained.

And the AI is constantly learning each time a human confirms or corrects what it detects, the technology adapts.

This technology won’t replace people, Cal Fire says, but can help first responders stop fires before they explode.

"Nothing can take the place of the boots on the ground...We absolutely are able to, in my opinion, save lives and property," Slumpff expressed.

Article Topic Follows: California News

Jump to comments ↓

CNN Newsource

Author Profile Photo

Dillon Fuhrman

If you have any story ideas, reach out to him at dillon.fuhrman@kecytv.com.

Author Profile Photo

Karina Bazarte

Karina Bazarte joined the KYMA team as a reporter in September 2022.
Reach out to Karina with story ideas and tips at: karina.bazarte@kecytv.com

BE PART OF THE CONVERSATION

KYMA KECY is committed to providing a forum for civil and constructive conversation.

Please keep your comments respectful and relevant. You can review our Community Guidelines by clicking here

If you would like to share a story idea, please submit it here.

Skip to content