Peering at Particles "Pixel by Pixel" with Computer Vision Could Boost Future Lithium Batteries

Researchers from the Massachusetts Institute of Technology, Stanford University, the Toyota Research Institute, and the SLAC National Accelerator Laboratory have observed the inner workings of lithium-based batteries like never before — by using a machine learning system to peer at X-ray videos "pixel by pixel."

"What we learned from this study is that it's the interfaces that really control the dynamics of the battery, especially in today’s modern batteries made from nanoparticles of the active material. That means that our focus should really be on engineering that interface," says Martin Bazant, professor of chemical engineering and mathematics at MIT and senior author of the study. "What I find most exciting about this work is the ability to take images of a system that's undergoing the formation of some pattern, and learning the principles that govern that."

"Until now, we could make these beautiful X-ray movies of battery nanoparticles at work, but the movies were so information-rich that understanding the subtle details of how the particles function was a real challenge," adds co-lead William Chueh, associate professor at Stanford and director of the SLAC-Stanford Battery Center. "By applying image learning to these nanoscale movies, we can extract insights that were not previously possible. This is the kind of fundamental, science-based information that our partners in industry need to develop better batteries faster."

The project saw the team taking detailed scanning tunnelling X-ray microscopy videos of lithium iron phosphate particles during charging and discharging, observing how the lithium ions move in both cases. Beyond the ability of the human eye to see, the changes were tracked using a computer vision model — comparing its findings to earlier theoretical models. By monitoring where the lithium ion flow was at its highest, the researchers discovered a correlation with the thickness of the carbon coating on each particle — revealing a path to the optimization of future lithium ion phosphate battery systems.

"Lithium iron phosphate is an important battery material due to low cost, a good safety record and its use of abundant elements," adds Brian Storey, senior director of Energy and Materials at the Toyota Research Institute. "We are seeing an increased use of LFP in the electric vehicle market, so the timing of this study could not be better."

The team's work has been published under open-access terms in the journal Nature.