原子间势
图形
计算机科学
卷积神经网络
理论计算机科学
计算科学
统计物理学
分子动力学
人工智能
物理
量子力学
作者
So Takamoto,Daisuke Okanohara,Qing‐Jie Li,Ju Li
标识
DOI:10.1016/j.jmat.2022.12.007
摘要
• Universal interatomic potential for modeling chemically and structurally complex systems. • Tensorial message passing in equivariant graph convolutional network. • Iterative construction of a diverse and broad training dataset. • User-friendly atomistic simulation platform Matlantis™ powered by universal interatomic potential for 72 elements.
科研通智能强力驱动
Strongly Powered by AbleSci AI