Google AI venture to help military with disaster response

Google's Bellwether team, which is part of its X innovation hub, is partnering with the National Guard on using AI to quickly map disaster-affected areas to speed response times.

An artificial intelligence (AI) venture backed by Google is partnering with the military to use AI in responding to natural disasters.

Bellwether, a team that's part of Google parent Alphabet's X innovation hub, announced Wednesday that it's working with the National Guard and the Defense Innovation Unit (DIU) to address inefficiencies in the Guard's disaster response processes. The DIU is tasked with helping the Department of Defense integrate early stage commercial technologies into its operations.

Bellwether worked with the National Guard to develop a system that uses AI and machine learning (ML) to quickly analyze aerial imagery of disaster scenes to identify damage to critical infrastructure. That can then inform National Guard teams coordinating the disaster response as they look to deploy resources most effectively after conducting damage assessments.

The National Guard currently conducts damage assessments manually as humans look over aerial images of a disaster-struck area to compare them against corresponding pictures of those locations to note infrastructure changes caused by the disaster. That process continues as the disaster progresses, and the initial response can be delayed due to the time required to review those details.

AIR FORCE CONFIRMS FIRST SUCCESSFUL AI DOGFIGHT

"Right now, our analysts have to spend time sorting through images to find the ones that cover the areas most affected by natural disasters," Col. Brian McGarry – who leads the National Guard's operations, plans and training division – said in a statement.

"They then have to correlate those images to surrounding infrastructure, label all the relevant features, and only then can highlight the significant damage and send it forward to first responder teams."

"Using AI and ML to do the routine tasks of georectification, identification, and labeling will greatly speed up how quickly we can get important information to the folks that need it most," McGarry wrote. "It's all about saving lives in our communities."

GOOGLE CONSOLIDATES AI-FOCUSED DEEPMIND, RESEARCH TEAMS

The Bellwether team said they spent nine months building a prototype that uses AI and machine learning to analyze aerial imagery of an area hit by a disaster in mere seconds, using Google's geospatial assets as a reference to compare what the area looked like before the disaster.

After the images of the disaster scene are analyzed, the Bellwether tool produces a labeled map of affected areas that allows the National Guard to quickly determine how to deploy its resources in response to conditions in the disaster-affected area.

"There is so much information from so many sources about the Earth out there," Sarah Russell, who leads Project Bellwether at X, said in a release. "Our moonshot is to systematize that information so that disaster response organizations and other entities can use it to make better decisions and plan for the future."

WHAT IS ARTIFICIAL INTELLIGENCE (AI)?

"The DIU supports our mission to build the most effective tools possible as natural disasters continue to occur with worsening severity," Russell added. "In five years, nobody should have to wait to understand the extent of extreme weather damage and the community's most urgent needs. It should be seen as reasonable and expected that we immediately know the state of the most important infrastructure across a landscape, and what to do next."

Google said Bellwether's results are so encouraging to the DIU that it's partnering with the team on future disaster response efforts.

GET FOX BUSINESS ON THE GO BY CLICKING HERE

Google's X innovation hub also noted in a separate post that Bellwether is developing a wildfire prediction tool to calculate fire risk for landscapes and structures up to five years in the future.

The tool estimates the likelihood of wildfire in a location by analyzing historical data about the environment as well as risk drivers like tree species, wind qualities and the types of infrastructure in the area.