Microsoft announced Tuesday that a team of scientists used artificial intelligence and high-performance computing to plow through 32.6 million possible battery materials — many of which do not occur in nature — in 80 hours, a task the team previously estimated would take 20 years. have lasted. The results kick off an ambitious effort to create a new generation of batteries that are less dependent on toxic and environmentally harmful lithium.
The company shared some of the best candidates with the government’s Pacific Northwest National Laboratory in Richland, Washington, which examined the most promising and built a prototype battery using a brand new material.
Subscribe to The Post Most newsletter for the most important and interesting stories from The Washington Post.
While the dime-sized prototype isn’t yet ready for a primetime role powering today’s watches and car keys, it uses less lithium than commercially available options and has the ability to charge power. Furthermore, this achievement demonstrates the potential of new technologies to revolutionize the underappreciated but rapidly evolving field of materials science.
“It’s really not an exaggeration to say that almost every major problem we face as a society could be helped, at least in part, by having better materials,” said Christopher M. Wolverton, professor in the department of materials science and engineering at the Northwestern University. . Wolverton, who was not involved in Microsoft’s battery project but has worked on similar projects, called the company’s claim that it screened 32.6 million materials in 80 hours “mind-boggling.”
“Thirty-two million people immediately tell me they haven’t screened [just] known materials,” he added. “They screened hypothetical new materials they hoped to discover.”
Like other outside experts interviewed, he was able to view press releases from Microsoft and Pacific Northwest National Laboratory, but was unable to see the scientific paper describing the work before it was released. The paper, which has yet to be peer-reviewed, was posted on the scientific preprint site arXiv on Tuesday.
– – –
Powerful mixing and matching
Although estimates vary, experts generally believe there are about 200,000 known materials in the world, and materials scientists continue to search for new materials that could hold the key to solving some of the planet’s serious challenges.
To combat climate change, scientists must find the best materials to capture and store carbon dioxide in the atmosphere. To reduce the massive build-ups of plastic litter on beaches, clogging landfills and threatening human health, scientists must find safe ways to break it down into fuel and raw materials. To quickly respond to new pathogens that could cause future pandemics, scientists must design effective drugs that use proteins to attack viruses and bacteria or to boost the body’s defenses.
They all depend on discovering the right materials, a process that has been slowed by hypothesis-driven trial-and-error approaches.
Thanks to high-performance computing and artificial intelligence, scientists can now quickly use the elements in the periodic table as a painter would use a color palette, mixing them and creating new configurations.
“This is a new way to do science,” said Nathan Baker, author of the paper and senior director of partnerships for chemistry and materials at Microsoft. The project used the company’s Azure Quantum Elements platform, which was unveiled in June with the aim of using advanced computing power to accelerate the discovery process.
Starting with all known materials, Baker said, “we can basically go through the periodic table and drop new atoms in [various] locations through a process of replacement.”
Azure Quantum Elements quickly removed materials that are poor conductors, too unstable, too reactive or too expensive to use for batteries. The high-performance computers used by Microsoft essentially harnessed the power of about 5,000 typical laptops. Baker emphasized that once Microsoft had initial results, they consulted materials experts at the government lab, believing that, “Okay, a computer gave us the answer… Let’s go prove it.”
Officials from Microsoft and the national laboratory said they will pursue the battery project as part of a three-year collaboration aimed at accelerating the pace of innovation and discovery.
“This is not just a stunt announcement, a headline-grabbing announcement. This is the nature of things to come,” said Chirag Dekate, vice president and analyst at Stamford, Connecticut-based research and consulting firm Gartner. was not part of the research team.
– – –
The hunt for a better battery
The need for better battery technology has emerged as a major challenge for scientists.
“Many of today’s battery technologies are very inefficient,” says Dekate. “If you look at one of the reasons why the promise of a green future has eluded us until now, despite advances in solar and wind energy [power]If you look at the underlying reason, it’s really the challenges associated with battery technologies.”
Lithium-ion batteries now power most electric cars, as well as most of the electric scooters and electric bicycles that have become ubiquitous in modern cities around the world. In 2022, the global lithium-ion battery market size was estimated at $46.2 billion, and the industry is expected to reach $189.4 billion by 2032.
But current batteries are unable to charge quickly or hold their charge for long periods of time. Moreover, some of them have proven volatile.
In 2023, the New York Fire Department reported that 18 people died in fires related to electric vehicle batteries.
Microsoft looked for materials to build a so-called solid-state electrolyte battery; these have a greater energy density than liquid ion batteries and pose no fire or leakage risk. The material used for the prototype contained some lithium, but up to 70 percent less than the amount found in existing batteries.
Microsoft’s work on the battery project “began in earnest about nine months ago,” Baker said.
The team trained its artificial intelligence system by showing it examples of different materials, helping it learn their crystal structures and energetic properties. “As we go through different compositions, it starts to learn how the structure and composition relate to the energies,” Baker said.
The Microsoft team then used AI to function as a funnel. A large number of possibilities were entered at the top of the funnel and then passed through various filters that narrowed the list of candidates. The best came from the bottom of the funnel.
Since the material of a battery must be stable, the artificial intelligence started filtering the number of candidates to just under 590,000, which would remain in the shape necessary to perform in a battery. From there, the AI essentially asked each candidate: is he going to respond to oxygen? Will it do something strange if an electric current is applied to it? How do you get lithium atoms to move through the material, a necessary process for a functioning battery?
Ultimately, Microsoft contacted the Pacific Northwest National Laboratory, which has extensive experience in battery research.
“They asked themselves: What are the properties you normally need from a material to make a better battery?” said Vijay Murugesan, a paper co-author and head of the laboratory’s materials science group in the Department of Physical Sciences. He called developing a solid material that allows only lithium ions to move from one side of the battery to the other a huge challenge.
When he looked at a list of the top 120 to 130 candidates, Murugesan said his reactions ranged from “Why? What? Really?” for some of the most surprising candidates: “I see this being an obvious next step of what we do.”
Scientists said they were encouraged by the fact that some of the materials recommended by AI had already been identified as promising by experts.
The lab’s team analyzed the top candidates and created a handful of the hypothetical materials dreamed up by computers. The new material chosen for the prototype contains a little lithium in addition to sodium, chloride and yttrium. The laboratory continues to work on the material used for the prototype and is preparing to investigate at least two more candidate materials.
Aron Walsh, a professor and chair in materials design at Imperial College London, responded to preliminary information from Microsoft by email, saying: “AI offers a new generation of approximate yet practical tools, allowing us to tackle problems previously seemed impossible, such as the rapid exploration of large chemical spaces reported here.”
related content
Violent political threats are increasing as 2024 begins and haunting American democracy
New battery material that uses less lithium found in AI-powered search
Josh Harris just took a smart step away from the Commanders’ sad past