PG&E is adopting artificial intelligence and machine learning software to use in a network of high-definition cameras for a better wildfire watching system.
The cameras have been installed throughout Northern and Central California in high-risk areas, according to PG&E. Of the 138 new HD cameras installed this year, 46 of them have the new AI testing program.
"In August, (the cameras) detected smoke in Placer County, one full minute before the fire dispatched, and that smoke ended up being the River Fire," PG&E Spokesperson Deanna Contreras told KCBS Radio.
"What the artificial intelligence does is, it detects smoke for us," she said. "And it does that by ruling out any false positives, it rules out haze or fog or dust, or anything that could be misconstrued as smoke."
"And when it determines that it is smoke, it sends PG&E a text or an email alerting that there’s smoke," she added.
This allows for a faster response, and faster allocation of the necessary resources in the necessary areas.
The camera and artificial intelligence system was created in partnership with Alchera and ALERTWildfire. The utility started putting up cameras in 2018 and as of October 31, there were 487 cameras.
"Even with the two significant rainstorms in October and November, we are still in a historic drought and California, along with other western states, continue to experience an increase in wildfire risk and a longer wildfire season," said PG&E Chief Risk Officer Sumeet Singh. "We are using every new tool and technology at our disposal to improve situational awareness and intelligence to help mitigate and prevent wildfires, including this new AI capability."
Related
