In this paper he and the co-authors develop CHargeNet, which is a universal machine-learned potential to model materials much faster than with typical first-principles methods. The need to quickly discover new materials and to understand their underlying physics in the presence of complex electron interactions calls for advanced simulation tools. Deng et al. propose CHGNet, a graph-neural-network-based machine learning interatomic potential that incorporates charge information. Pretrained on over 1.5 million inorganic crystal structures from Materials Project, CHGNet opens new opportunities for insights into ionic systems with charge interactions."

You can read the article here: