Google’s new AI tech may know when your house will burn down
The satellite uses infrared sensors to detect heat signatures of wildfires and alerts authorities to respond quickly. FireSat aims to provide real-time information to help firefighters contain wildfires before they grow out of control. The project is a collaboration between the University of California, Berkeley and other partners. FireSat is expected to improve wildfire management and reduce the impact of wildfires on communities and the environment.
The project aims to detect a fire the size of a classroom within 20 minutes. Wildfires are becoming an increasingly common threat worldwide. Record-breaking burns from Australia to the Amazon to the United States are devastating the environment. The deadly wildfires that raged across Los Angeles in January were estimated to have caused more than $250 billion in damages.
Current satellite imagery is often low resolution, infrequently updated and unable to detect small fires. But what if there was a way to spot wildfires earlier and more accurately before they become raging infernos? Enter FireSat, a new satellite project designed to detect and track wildfires early. How early? The project aims to detect a fire that's merely 270 square feet – about the size of a classroom – within 20 minutes. It's also able to detect fires two to three acres in size, roughly the size of two football fields.
FireSat satellite (FireSat)
The FireSat constellation will consist of more than 50 satellites when it goes live. The satellites are fitted with custom six-band, multispectral infrared cameras designed to capture imagery suitable for machine learning algorithms to accurately identify wildfires, differentiating them from misleading objects like smokestacks.
Illustration of FireSat constellation (FireSat)
Using artificial intelligence, FireSat rapidly compares a spot, wherever it is in the world, with previous imagery of that location, considering factors like nearby infrastructure and local weather to determine if there’s a fire. "Differentiating between real fires and random 'noise' in the environment was a challenge," says Chris Van Arsdale, who works on climate and energy projects at Google. The team even loaded a plane with sensors to experiment with their progress. "The first time we used the plane, one of our team members lit a barbecue and a fire pit in his backyard so we could fly the plane over and test it," says Erica Brand, one of the project managers for FireSat. "And the sensors were able to pick it up."
Illustration of FireSat constellation images (FireSat)
The first FireSat satellite has already been launched. The entire constellation should be in orbit by 2030. The satellite data will contribute to a global historical record of fire spread so that scientists can better model and understand wildfire behavior.
FireSat stats (FireSat)
The team behind FireSat includes Google Research and satellite manufacturer Muon Space as founding partners in the Earth Fire Alliance, the nonprofit home for FireSat. Funding for the constellation’s first satellite comes in part from AI Collaboratives: Wildfires, an initiative created by Google.org that convenes leading nonprofits, academic institutions, government agencies, and companies around the joint goal of using AI to prevent the devastating impact of wildfires.
FireSat satellite (Earth Fire Alliance)
So, what does this all mean? It means a future where wildfires are detected faster, contained quicker and cause less devastation. FireSat represents a major advance in wildfire management. This ambitious project has the potential to protect lives, homes, and the environment we all cherish.