If you recall the past summer, one of the images that you may have thought about was the wildfires. Perhaps you read about them; perhaps you were in an area where smoke was in the air; perhaps you saw the fires on a news feed or perhaps you or someone you know was in the area affected by wildfires. If you own stock in an insurance company, you are wondering what the losses are? The wildfires are seemingly become larger and they seem to be more of them. What is the solution?

In an article by Kelvin Chan of the Associated Press, there maybe some good news on the horizon which includes some form of early detection and sending resources to find small fires.

Firefighters and startups are using AI-enabled cameras to scan the horizon for signs of smoke. A German company is building a constellation of satellites to detect fire from space. And Microsoft is using AI models to predict where the next blaze could be sparked.

California’s main fireighting agency this summer started testing an AI system that looks for smoke from more than 1,000 mountaintop camera feeds and is now expanding it statewide. The system is designed to find abnormalities and alert emergency command centers, where staffers will confirm whether its indeed smoke or something else in the air.

The cameras provide billions of bytes of data for the AI system to digest. While humans will need to confirm any smoke sightings, the system will reduce fatigue among staffers typically monitoring multiple screens and cameras, alerting them only when there is possible smoke or fire, according to Phillip SeLegue, staff chief of intelligence for the California Department of Forestry and Fire Protection.

It has worked, a battalion chief received a smoke alert in the middle of the night, confirmed it on his cellphone and called a command centre to scramble first responders to the remote area. The small fire was put out and it did not become a large fire.

San Francisco startup Pano AI takes a similar approach, mounting cameras on cell towers that scan for smoke and alert customers including fire departments, utility companies and ski resorts. The cameras use computer vision machine learning, a type of AI. The images are combined with feeds from government weather satellites that scan for hot spots and other data sources such as social media posts.

For fighting forest fires, technology is becoming essential said Larry Bekkedahl, senior vice president of energy delivery of Portland General Electric, Oregon’s largest utility and a Pano AI customer. PGE has 26 Pano AI cameras.

Using AI to detect smoke from fires is relatively easy said Juan Lavista Ferres, chief data scientist at Microsoft. The hard part is having enough cameras in remote places. Microsoft is developing AI models to predict where fires are likely to start. They fed the models with areas that have burned previously along with climate and geospatial data.

German startup OroraTech analyzes satellite images with AI. The company has launched mini-satellites about the size of a shoebox into low orbit, about 1,000 miles about the Earth’s surface. It hopes to send up 8 more next year and have 100 satellites in space.

CEO Thomas Grubler said because we know exactly where the fires are, we can see how the fires will propagate. What fire will become larger and which ones should stop on their own.

Linking to dividend paying stocks, over the past few years fire have caused billions of dollars in damages and when they approach towns and cities, insurance companies have to pay claims. Using AI will limit those claims which is why there is a ready market for the data the companies are collecting and projecting. In the insurance world, there is a need to pay claims, the less they pay the more money the companies make giving the risks they insure. As a dividend investor some of the most consistent companies are utility companies, one question you might ask them is what AI systems they are using to limit their losses due to fires. If you remember PG & E in California and possibly Hawaiian Electric might have to pay fines for fires.

There are more questions than answers, till the next time – to raising questions.