Google is investing in satellites and artificial intelligence to better detect forest fires


In the wake of the recent wildfires in California, Google has announced it will spend $13 million starting next year to improve satellite imagery to track and detect wildfires.

FireSat, a constellation of more than 50 satellites, can detect wildfires the size of a classroom — about 16 by 16 feet — and the first satellite is set to launch in early 2025. The media giant announced on MondayCurrently, firefighters rely on satellite imagery to detect wildfires, but only when they grow to the size of a football field or more than an acre.

“We realized that if we combined satellites with machine learning and artificial intelligence, it was the perfect platform to generate real-time, actionable intelligence about fires,” said Christopher Van Arsdale, head of Google’s Climate and Energy Research group and president of Fire Alert Earth, according to a video announcement.

An initiative of Earth Fire Alliance, a nonprofit that launched in May to create FireSat and develop wildfire datasets, with funding from Google and Gordon and Betty Moore Foundation.

Currently, satellite images can mistake clouds or smoke for fires, Van Arsdale said. Using machine learning, a team at Google built a camera that optimized the technology for fire detection, and the team tested it in controlled burn areas.

The satellite tower can provide firefighters with updated satellite images every 20 minutes to help them put out fires before they become large and destructive.

“In addition to supporting emergency response efforts, FireSat data will be used to create a global historical record of fire spread, helping Google and scientists better model and understand fire behavior and spread,” the company said. Google said the project is part of the company’s efforts to help communities deal with the effects of climate change.

California officials have already taken steps to use AI to better track wildfires. The California Department of Forestry and Fire Protection has partnered with UC San Diego to develop a new AI pilot project that will maintain 1,039 high-resolution cameras on towers and mountaintops across the state to monitor smoke and other anomalies and Cal Fire alarms.

Jason Forthhofer, a research mechanical engineer with the U.S. Forest Service, said the FireSat project will also help collect data to better train firefighters on how to deal with wildfires and understand how they are affected by changing conditions.

“We can teach firefighters how drought affects a fire, or wind, or a change in fuel type, because we have seen many firefighters die in fires when they did not predict what the fire was going to cause,” he said.

Southern California has endured a brutal wildfire season, with three fast-moving fires burning more than 100,000 acres and forcing thousands of people to flee dozens of structures.

Leave a Comment