Towards universal neural network interatomic potential
So Takamoto, Daisuke Okanohara, Qing-Jie Li, Ju Li
•Universal interatomic potential for modeling chemically and structurally complex systems.<br/> •Tensorial message passing in equivariant graph convolutional network.<br/> •Iterative construction of a diverse and broad training dataset.<br/> •User-friendly atomistic simulation platform Matlantis™ powered by universal interatomic potential for 72 elements.<br/>
キーワード
PFP