Wildfire detection tech firm launches pilots in Napa, Sonoma, Lake counties
Detecting an industry ablaze with potential and government funding, San Francisco-based Pano has launched a pilot program with mountaintop camera stations that started to spot wildfires in the North Bay late last year.
With a focus on the wildfire-prone West, Pano installed the stations with high-definition cameras using artificial intelligence and computing hardware to gain distinct, 360-degree views at 10 miles out at seven locations in Sonoma, Napa and Lake counties.
Four are lined up along the Alexander Valley south to Windsor, with two in the Napa Valley. One is situated on the east side of Clear Lake. Other locations include Aspen, Portland and Big Sky in other western states, among other areas in the South Bay.
“I’ve always had an interest in public safety and climate change in the last decade,” said Sonia Kastner, CEO and founder of Pano. Kastner teamed up with Arvind Satyam, the chief commercial officer who, since he’s from Australia, also became interested in helping the cause when the bush fires broke out in his homeland last year.
The tech company was formed in July 2020 at a time when Kastner noted “the sky in San Francisco turned red.”
The North Bay pilot locations were set up five months later to test the computer algorithms on control burns during the rainy, winter months. The actual onboarding of the camera technology was launched last August.
List of North Bay sites with Pano tech (PDF)
The Silicon Valley tech executive joined forces with innovation professionals from Apple, Tesla, Cisco and Nest to come up with a solution to detecting wildfires at their infancy. The technology, which uses AI, circular cameras and satellite imagery, became known as Pano Rapid Detect.
“Their detection is 90% accurate,” Kastner said.
Early, precise detection that may distinguish between smoke, fog and dust is key to getting a quick jump on devastating fires that behave much differently than they did a decade ago.
“With wildfire conditions now, every minute counts,” she said, adding the data marked by a full rotation each minute is reviewed by a “central intelligence center manned by experts among Pano’s 20-person workforce. Consequently, the verified data feeds into 911 dispatch centers.
“The problem is when bystanders call 911, there are bad calls and the whole process can take hours,” she said.
Pano’s business model is based on subscription sales, with prospects ranging from fire agencies and local governments to property owners seeking a long-distance lay of the land and utility companies.
The goal is to have more than 5,000 stations in high-fire-risk areas across the United States. Kastner has considered using the stations to gather meteorological data such as wind speed.
The privately held company operates with venture funding. Financial information and subscription prices were not disclosed.
Pano currently partners with Portland General and Pacific Gas & Electric for its western stations made at its 3,000-plus-square-foot factory in San Francisco.
Granted, wildfire detection cameras are not a new thing. But the technology has helped the devices evolve into more of a useful tool to fire agencies and utilities tasked with monitoring flames near power equipment.
PG&E, which now uses 487 cameras in the ALERT Wildfire system, is taking part in a separate pilot program with Pano using AI technology. Another test pilot with 46 of its cameras is with Alchera Technologies.
“During extreme hot weather, being able to differentiate smoke from fog is very important,” PG&E spokeswoman Deanna Contreras said.
“The software analyzes the video feed, and if it thinks it sees smoke, we receive an alert via email and text, telling us it just detected smoke. Our analysts then pinpoint where the smoke is coming from and determine if it’s a car fire, dumpster fire or even a vegetation fire. Based on the location, we can assess for threat to the public or PG&E facilities,” said Eric Sutphin, PG&E supervisor in charge of the camera installations. “The AI filters out a significant number of false positives, for example, ruling out dust, fog or haze.”
Wildfire is never out of view of utility and fire officials.
“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. 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,” said Sumeet Singh, PG&E Chief Risk Officer. “Every bit of data and intelligence that comes to us could potentially save a life.”