Wildfire boundary tracking

Using AI to map the boundaries of large wildfires and provide accurate wildfire information to affected communities and fire authorities

Blog '20 Blog '23 Blog '24

Wildfire boundary tracking

During wildfires people often turn to Google to find helpful information that can keep them and their communities safe. Our team at Google Research uses AI to detect wildfires, identifying their boundaries and making this information available through Google Search and Maps, including during driving direction related searches — complementing existing on-the-ground efforts to help people access information during a crisis. In addition, the boundary tracking system sends push notifications with the wildfire information to nearby users and communities.

This wildfire boundary tracker was just recently expanded and is now available in over 27 countries.

Watch the film

Link to Youtube Video

In February 2024, a series of devastating wildfires broke out across Chile, resulting in massive damage and significant loss of life. This chain of events shows how our wildfire boundary tracker provides helpful information during a crisis.

How it works

Satellite imagery is gathered using geostationary lower Earth orbit satellites and other data sources that provide continual coverage for a portion of the Earth. Satellites include GOES-16 and GOES-18 for North and South America; Himawari-9 and GK2A for Australia; and Suomi NPP and NOAA-20 satellites with VIIRS imagery in other locations.
An ML-powered system analyzes the continent-scale images using geostationary data sources. This works by receiving a sequence of the three most recent images to compensate for temporary obstructions and inputs from two satellites.
An ML system detects wildfire boundaries using geostationary data sources and a neural network to identify the total burnt area of the fire.

Read the Research Blog post to learn more.