At an AI-focused press event today in New York, Google announced it is bringing its AI-powered wildfire detection system to the United States, Canada, Mexico and in parts of Australia. It’s one of several “AI for good” efforts the company detailed this morning, which also included Google’s efforts to expand flood forecasting to more parts of the world.
The previously announced system uses machine learning models trained on satellite data to track fires in real time and predict their spread. The feature is initially intended to help first responders determine the best way to control the fire.
“Our machine learning models trained using satellite imagery allow us to identify and track wildfires in real time and predict their spread, allowing us to support firefighters and other first responders” , said Katherine Chou, senior director of Google Research, on stage.
Around this time last year, Google announced the technology was being added as a layer in Google Maps. The company noted at the time:
[W]We are now gathering all of the forest fire information from Google and launching it around the world with a new layer on Google Maps. With the Wildfire layer, you can get up-to-date details on multiple fires at once, allowing you to make quick and informed decisions in an emergency. Simply tap on a fire to see available links to local government resources, such as emergency websites, phone numbers for help and information, and evacuation details. When available, you can also see important details about the fire, such as its containment, number of acres burned, and when all of this information was last reported.
The feature joins a similar ML-based flood forecasting feature announced in 2018. The former is now expanding to 18 additional countries with the global launch of the new FloodHub, Google’s platform that displays flood forecasts and shows when and where flooding may occur. . The countries are: Brazil, Colombia, Sri Lanka, Burkina Faso, Cameroon, Chad, Democratic Republic of Congo, Ivory Coast, Ghana, Guinea, Malawi, Nigeria, Sierra Leone, Angola, South Sudan, Namibia, Liberia and Africa from South.
Google also noted, as previously reported in a Wired article, that it uses machine learning models to identify damaged buildings after natural disasters such as hurricanes. By analyzing the same satellite imagery as its wildfire detection tools, the models provide crisis responders with information about the hardest-hit areas in the first phase of a response effort, Google says.
Google first applied the technology in partnership with the nonprofit organization GiveDirectly to identify and channel donations to low-income households affected by Hurricane Ian. More recently, the company has applied the models to support government relief efforts during the recent floods in Pakistan, Chou says.
“We hope to continue to empower organizations to deliver help faster to those in need,” she added.
#Googles #wildfire #detection #United #States #Mexico #Canada #parts #Australia