Through new improvements to existing AI models, researchers in China have created a framework that can methodically identify useful new forms of solid carbon. With their approach, Zhibin Gao and ...

SPaDe-CSP first predicts most probable space groups and crystal densities using machine learning and then employs an efficient neural network potential for structure refinement. Prediction of crystal ...

The new method can determine crystal structures underlying experimental data thus far difficult to analyze. A joint research team led by Yuuki Kubo and Shiji Tsuneyuki of the University of Tokyo has ...