Researchers have designed a machine learning method that can predict battery health with 10x higher accuracy than current industry standard, which could aid in the development of safer and more reliable batteries for electric vehicles and consumer electronics.

A technique based on the principles of MRI and NMR has allowed researchers to observe not only how next-generation batteries for large-scale energy storage work, but also how they fail, which will assist in the development of strategies to extend battery lifetimes in support of the transition to a zero-carbon future.