The Battery Revolution

less than 1 minute read

Published:

Fires in phones, laptops, and even a jumbo jet share a common cause: the flammable liquid electrolyte inside conventional lithium-ion batteries. Alongside their fire risk, these batteries also fall short on charging speed and energy density — driving researchers to look for a safer, better alternative.

Professor Yifei Mo’s group uses supercomputers paired with machine learning to model battery materials atom by atom, predicting how they conduct lithium ions and speeding up the search for viable solid-state battery materials.

“What we’re after is ultimate safety, energy density, life cycle, and charging time.” — Yifei Mo

Fast lithium-ion diffusion in solids is rare, and only a handful of materials achieve it at room temperature. By training machine learning models on existing materials data, Mo’s lab — among the first to apply ML to this problem — has helped uncover promising new candidates, filing multiple patents and working with industry partners to bring the technology toward commercialization.

Read the full story at the UMD MSE news page.