7 days ago
AI discovers new material that could transform batteries
Artificial intelligence has helped discover new materials that could transform batteries, scientists claim.
Battery technology could be key to moving towards a more sustainable world. Researchers hope that batteries could provide a key way of allowing for better electric vehicles as well as transforming smaller technology such as phones.
At the same time, however, our existing battery technology is flawed. The lithium-ion batteries that power much of our devices are relatively low density, lose energy over time and are vulnerable to heat and other changes.
One way that researchers hope to address those problems is through what they call multivalent batteries. Those use more easily available elements in comparison with lithium-ion batteries, and so could be cheaper, easier and cleaner to make.
What's more, the technology that powers them means that they could be more efficient and able to store more energy than existing batteries.
However, the larger size and greater electrical charge of the multivalent ions that are used in the battery mean they can be difficult to incorporate into a battery.
Now researchers have used generative artificial intelligence – a similar technology used in systems such as ChatGPT – to find new materials that could help resolve that problem.
'One of the biggest hurdles wasn't a lack of promising battery chemistries — it was the sheer impossibility of testing millions of material combinations,' said Dibakar Datta from the New Jersey Institute of Technology. 'We turned to generative AI as a fast, systematic way to sift through that vast landscape and spot the few structures that could truly make multivalent batteries practical.
'This approach allows us to quickly explore thousands of potential candidates, dramatically speeding up the search for more efficient and sustainable alternatives to lithium-ion technology.'
Researchers were able to use an AI system to pick through different possible materials and examine whether they would be helpful in such batteries.
'Our AI tools dramatically accelerated the discovery process, which uncovered five entirely new porous transition metal oxide structures that show remarkable promise,' said Professor Datta. 'These materials have large, open channels ideal for moving these bulky multivalent ions quickly and safely, a critical breakthrough for next-generation batteries.'
After finding the materials using AI, researchers checked them using more traditional simulations to ensure they could be used in real-world applications.
The work is reported in a new paper, 'Generative AI for discovering porous oxide materials for next-generation energy storage', published in the journal Cell Reports.
