"The electrodes have to satisfy very different properties at the same time. They always conflict with each other," said Ritesh Kumar, an Eric and Wendy Schimdt AI in Science Postdoctoral Fellow at the University of Chicago.
In April 2025, researchers at the University of Chicago Pritzker School of Molecular Engineering (UChicago PME) unveiled a new AI framework to accelerate the discovery of battery electrolytes. This framework balances ionic conductivity, oxidative stability, and Coulombic efficiency to identify promising molecules.
The AI, trained on a dataset of 250 research papers, assigns an "eScore" to molecules, predicting their suitability as electrolytes. The AI has already identified a molecule performing as well as top electrolytes, marking a significant advancement in battery technology. This reduces reliance on trial-and-error, saving time and resources.
The AI can sift through billions of potential molecules, a task impossible for humans. Researchers aim to develop an AI that can design entirely new molecules with desired properties. This could revolutionize battery design for electric vehicles, phones, and grid-scale energy storage.
Jeffrey Lopez from Northwestern University emphasizes that data-driven frameworks are crucial for accelerating battery material development. The team is now working on improving the AI's ability to identify unfamiliar materials, further enhancing its design capabilities.