Deep learning inter-atomic potential model for accurate irradiation damage simulations

We propose a hybrid scheme that smoothly interpolates the Ziegler-Biersack-Littmark (ZBL) screened nuclear repulsion potential with a deep learning potential energy model. The resulting deep potential-ZBL model can not only provide overall good performance on the predictions of near-equilibrium mate...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Applied physics letters 2019-06, Vol.114 (24)
Hauptverfasser:	Wang, Hao, Guo, Xun, Zhang, Linfeng, Wang, Han, Xue, Jianming
Format:	Artikel
Sprache:	eng
Schlagworte:	Aluminum Applied physics Cascades Computer simulation Deep learning Embedded atom method Free energy Heat of formation Machine learning Material properties Point defects Potential energy Radiation damage
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!