© 2024 Hawaiʻi Public Radio
Play Live Radio
Next Up:
0:00
0:00
0:00 0:00
Available On Air Stations
To our HPR-1 listeners on Kaua‘i (KIPL): Our transmitter will be powered down for tower maintenance on Friday 10/4, 10am-3pm. Mahalo for your understanding.

Firefighters and researchers are turning to AI to help fight fires

LEILA FADEL, HOST:

California is trying to adapt to a new reality, the spread of wildfires. And this isn't just a matter of a few bad fire seasons. A study finds that, on average, fires in northern and central California burn five times more land each summer than they did 50 years ago.

STEVE INSKEEP, HOST:

Climate change. Firefighters and researchers hope to spot fires more quickly and cut response times using artificial intelligence. Zachary Wells is a deputy chief with the Kern County Fire Department in California's Central Valley.

ZACHARY WELLS: The more time we give firefighters, the better chance that we have of containing these incidents before they become large, complex fires that take hundreds, if not thousands of firefighters to help mitigate.

INSKEEP: Oh, Kern County needs this. I've been there - a lot of beautiful, mountainous but dry land where wildfires have been devastating.

FADEL: The program uses a statewide network of cameras and sensors to monitor for wildfires and other potential disasters. ALERTCalifornia has now teamed up with Cal Fire, the state's fire department, to test an AI tool that can differentiate between smoke and other particles in the air.

NEAL DRISCOLL: We're pumping data into the AI. So we characterize the conditions prior to natural hazards, during natural hazards and after. So we want to prepare and manage.

INSKEEP: Neal Driscoll is ALERTCalifornia's principal investigator and helped design the program.

DRISCOLL: The data are open source. I give the data we collect to competitors, other AI companies, other universities, other scholars. This problem of extreme climate is bigger than any of us. We need to work together.

FADEL: Wells says he sees AI transforming firefighting. A decade ago, firefighters relied heavily on the 911 system. With the help of AI, they can now spot some fires before the first 911 call comes in. The data collected can also be used to predict fire behavior and provide real-time information to firefighters on the ground.

WELLS: We only have so many firefighters. We only have so many engines. And so when we have a report of wildfire, it's important to send an effective response force.

INSKEEP: ALERTCalifornia also helps researchers learn about other kinds of natural disasters, such as post-fire debris flows and floods and erosion. You can check out the program's live camera feeds at alertcalifornia.org.

(SOUNDBITE OF JAPANESE BREAKFAST'S "CAMPFIRES") Transcript provided by NPR, Copyright NPR.

NPR transcripts are created on a rush deadline by an NPR contractor. This text may not be in its final form and may be updated or revised in the future. Accuracy and availability may vary. The authoritative record of NPR’s programming is the audio record.

Leila Fadel is a national correspondent for NPR based in Los Angeles, covering issues of culture, diversity, and race.
Steve Inskeep is a host of NPR's Morning Edition, as well as NPR's morning news podcast Up First.
More from Hawai‘i Public Radio