Researchers use AI in hunt for improved battery life

The Army Research Office is funding research that uses artificial intelligence to identify materials that can transform energy storage, with possible ramifications for soldiers on the battlefield and everyday consumers.

Army-funded researchers at Cornell University are using AI to process possible configurations of elements to come up with combinations for possible alloys that scientists can test to see if they can contribute to more efficient energy storage.

Dr. Purush Iyer, the network sciences division chief at the Army Research Office, which is part of the Army Research Laboratory, told FCW via phone that, while the research is ongoing, it's already proven to be useful.

"Power is absolutely important in the Army. Soldiers walk from place to place carrying their gear. They have tons of equipment with them [and] tend to carry very expensive batteries. It can be a limiting factor," Iyer said.

"Portable, safe, fuel cells are definitely incredibly important," and has potential beyond defense, such as in the automotive industry and electric cars.

Iyer said the method will lead to more applications to address materials science challenges.

"The problem is not solved yet; it's not settled. And people are working on it from multiple angles," Iyer said. Research is limited by how quickly experiments materialize, data is analyzed, and results culminate from betting on the right combinations of materials that yield the right properties, he added.

The hope is that extended life battery fuel tech would be employable in the next five to ten years, Iyer said, but is hard to pinpoint a timeline for field delivery. But he drilled in on this point: DOD and society writ large needs to manage expectations around artificial intelligence.

"Machine learning is not a silver bullet, you have to apply it in a very, very refined way to get the kind of benefits that are necessary," Iyer said.