AI Startup Aims to Extinguish Wildfires

Based on the last two wildfire seasons, including 2018 when an entire California town was destroyed, utilities blamed for recent wildfires need all the help they can get maintaining aging grids. AI technologies may provide new monitoring tools.

Paradise, Calif., population of about 27,000, was destroyed by the Camp Fire. The 2018 inferno claimed at least 84 victims. In June, Pacific Gas & Electric (PG&E) was ordered to pay a $3.5 million fine for causing the Camp Fire.

As the wildfire season rolls around, a Silicon Valley AI startup is promoting a machine vision platform that could help utilities better monitor transmission lines and towers. Buzz Solutions said this week its platform can be used to analyze millions of power line images to detect grid flaws—and do it much faster.

The Palo Alto startup also announced a $1.2 million seed funding round to be used to perform image analysis. The platform is touted as producing in hours or days the reports that field engineers would produce in six to eight months. The image analyzer is also promoted as delivering potential savings in utility monitoring of up to 70 percent.

Buzz Solutions, a tech startup nurtured by Stanford University’s StartX accelerator, said Thursday (July 23) the seed round was led by Blackhorn Ventures along with a syndicate that included Advisors.fund, Ulu Ventures and Vodia Ventures.

The startup’s ML-based predictive analytics tools are used to monitor utility transmission lines that have been cited as a source of California’s worsening wildfires. The approach is promoted as accurate and timely, outperforming traditional field surveys.

Investors said the AI platform is being used in pilot projects by unidentified utilities in California, New York and a “large Midwest utility.”

Demand for automated monitoring systems is expected to grow as utility infrastructure ages and climate change adds fuel to the fire. Previously, utilities used drones, helicopters and fixed-wing aircraft to gather images of power lines, towers and surrounding vegetation. Image processing and mapping of the resulting data can take up to eight months.

The AI startup’s “predictive asset management” platform crunches historic, asset and fault data along with meteorological records. The output is a report on likely utility faults and high-risk areas.

“The utility industry is ready to use a far better approach to keep their equipment in good working order and keep people and property safe,” said Kaitlyn Albertoli, the startup’s co-founder and CEO.

“There is no doubt that utilities across the country are looking to inspect power lines in faster and more effective ways,” added Vikhyat Chaudhry, Buzz Solutions’ co-founder, CTO and COO.

Indeed, the pressure on California utilities to improve grid monitoring is growing. The startup notes California’s Department of Forestry and Fire Protection concluded that PG&E’s transmission lines also were at fault in last year’s Kincaid Fire which burned 78,000 acres, prompting the evacuation of 200,000 residents of Sonoma County.

Recent items:

IBM, Microsoft, and Nvidia Pit AI Against Wildfires

Seeing the Forest for the Trees With Analytics