Lithium-ion batteries have become the quiet workhorses of the energy transition, but the way they are designed and tested has long been slow, expensive, and heavily empirical. Machine learning is now ...

Machine learning models trained on molecular quadrupole moments predict electrostatic potentials rapidly, enabling faster ...

An agentic AI tool for battery researchers harnesses data from previous battery designs to predict the cycle life of new battery concepts. With information from just 50 cycles, the tool—developed at ...

Something to look forward to: A new tool could dramatically accelerate how scientists design and test batteries. Researchers at the University of Michigan have developed a machine-learning system that ...

Alfred University’s Inamori School of Engineering recently hosted a short course on battery machine learning, which was attended by a group of students and representatives of a Binghamton-area company ...

illustrating the comprehensive zero-shot benchmark of 19 universal machine learning interatomic potentials and the dominant impact of training data composition for surface energy prediction. A ...