The First Five is a partnership with DOE, and Microsoft to improve disaster response, including wildfire prediction, search and rescue, flood control, damage assessments and natural disaster response.
“The First Five was formed to bring the best resources from industry, nonprofit and the public sector to use technology to address the need to mitigate the impact of natural disasters while protecting property and lives,” said Jermon Bafaty, a White House fellow with DOE, in a conference call.
“When you look at 2019, there were 14 disasters that were individually more than a billion [dollars] in damages each,” Bafaty said. “As a public-private partnership, we need to be able to pull together the best ideas and understandings to put together the right solutions that we think we’ll be able to scale to save lives.”
DOE is scaling a prototype that uses deep learning algorithms to produced data in near-real time that will improve the situational awareness and decision-making of the nation’s first responders.
“We were really excited six months ago to hear of the level of work that had been done and the prototype,” said Susie Adams, chief technology officer for Microsoft. “We’re really excited to take this to the next level and to scale this not only for the U.S. but for anybody in the humanitarian disaster response community.”
Microsoft has established a critical- infrastructure team that will help collect data for models that will be used to forecast impending disasters. The team will explore ways to use AI, confidential computing, modern communications, and distributed systems to improve disaster resilience.
As a frame of reference for the need of such tools, Phillip Selegue, deputy chief at CAL FIRE, noted the wildfires burning out of control in his state of California. “Lightning fires in the northern portion of the state have totaled 8,836, resulting in 356 fires,” he said.
Artificial intelligence tools would help with situational awareness, damage assessment and lend resiliency to communities at risk that rely on mapping to determine where the fire is, where it’s going and what impact it might have.
“First Five” references the first five minutes of a disaster when response is so critical. These are the areas the consortium will look to develop AI and deep learning methodologies:
1. Wildfire prediction and fire line containment;
2. Damage assessment – ingress and egress routes for impacted areas;
3. Search and rescue; and
4. Natural disasters including hurricanes and tornadoes.
“Understanding the first-responders’ needs, and delivering these AI-enabled technologies to first responders will save lives,” said Cheryl Ingstad, director of the Artificial Intelligence and Technology Office for DOE. “We are confident of that and looking forward to participating in this consortium.”
