Google to Invest in AI and Satellites to Improve Wildfire Detection

Google has stated that it will invest $13 million to enhance satellite photography in order to assist track and detect wildfires, beginning as early as next year, after a recent spate of wildfires in California.

The media behemoth revealed on Monday that FireSat, a constellation of more than 50 satellites, will be able to identify wildfires as tiny as a classroom, or roughly 16 by 16 feet. The first satellite is scheduled to launch in early 2025. Currently, wildfires are only detected by firefighting officials when they grow to be larger than an acre, or roughly the size of a football field, using satellite imaging.

In a video statement, Google Research Climate & Energy group leader and Earth Fire Alliance chairman Christopher Van Arsdale said, "We realized that if we can pair satellites with machine learning and artificial intelligence, it was the perfect platform to generate real-time operational intelligence on fires."

With support from Google and the Gordon and Betty Moore Foundation, the Earth Fire Alliance, a nonprofit organization founded in May to compile wildfire databases and build FireSat, is spearheading the effort.

According to Van Arsdale, satellite imagery may currently misidentify smokestacks or clouds for fires. Google engineers tested their machine learning-optimized camera over controlled-burn regions to see how well it detected fires.

The satellite constellation will be able to give firefighters up-to-date satellite imagery every 20 minutes, assisting them in putting out flames before they grow huge and catastrophic. That's not all, though.

The company stated, "FireSat's data will be used to create a global historical record of fire spread, helping Google and scientists to better model and understand wildfire behavior and spread, in addition to supporting emergency response efforts." The project, according to Google, is a component of the company's efforts to assist communities in mitigating the effects of climate change.

To better track wildfires, Californian officials have already begun utilizing artificial intelligence. In order to monitor smoke and other anomalies and notify CAL FIRE, the California Department of Forestry and Fire Protection (CAL FIRE) collaborated with UC San Diego to create a new AI pilot that will be installed on towers and mountain summits around the state.

According to U.S. Forest Service research mechanical engineer Jason Forthhofer, data from the FireSat project will also be used to better teach firefighters on how to deal with wildfires and comprehend how they are impacted by shifting conditions.

“We’ll be able to teach firefighters what dryness does to a fire, or wind, or a change in fuel type, because we have seen so many firefighters die on fires when they don’t anticipate what the fire’s going to do,” he said.

This wildfire season is particularly active in Southern California; three swift fires have burned over 100,000 acres, driven thousands of people to flee, and destroyed numerous buildings.