Unsplash

PG&E Testing WildFire Cameras with AI to Enhance Fire-Watch

Pacific Gas and Electric Company (PG&E) is testing artificial intelligence (AI) and machine learning capabilities of high-definition cameras across Northern and Central California to understand how it can enhance fire-watch and response capabilities. This testing will help them differentiate wildfire smoke and fog during extremely dry, hot, and windy weather. 

This year PG&E in collaboration with ALERTWIldfire, installed 138 new HD cameras across districts with a high-fire threat. In partnership with ALERTWildfire and Alchera, 46 of these cameras are included in the new AI testing program. There are seven AI pilot cameras in Yuba County, three in Plumas County, and two in Butte County.

The software analyzes video feeds for smoke and sends a notification via email or text. It then pinpoints the location and what kind of fire it is. The software also helps filter false positives like dust, fog, or haze. The pilot program also includes PG&E determining how to deliver the correct information to the right people quickly and effectively. 

The cameras give a 360-degree view with tilt, zoom, and pan capabilities and can be viewed by anyone through the ALERTWildfire Network. By the end of 2022, PG&E plans to have around 600 cameras installed, enabling them to see more than 90% of the high-fire risk areas in real-time.

The pilot program demonstrated its AI potential during the River Fire in Placer County when it identified the smoke a minute before the actual fire dispatch. Experts, first responders, and other agencies use fire-watch cameras to detect, monitor, and assess threats.

Source: