Phase transitions of zirconia: Machine-learned force fields beyond density functional theory

doi:10.1103/PhysRevB.105.L060102

CORC > 金属研究所 > 中国科学院金属研究所

	Phase transitions of zirconia: Machine-learned force fields beyond density functional theory
	Liu, Peitao 1,2,3,4; Verdi, Carla 2,3; Karsai, Ferenc 1; Kresse, Georg 1,2,3
刊名	PHYSICAL REVIEW B
	2022-02-16
卷号	105 期号:6 页码:6
ISSN号	2469-9950
DOI	10.1103/PhysRevB.105.L060102
通讯作者	Liu, Peitao(peitao.liu@univie.ac.at)
英文摘要	Machine-learned force fields (MLFFs) are increasingly used to accelerate first-principles simulations of many materials properties. However, MLFFs are generally trained from density functional theory (DFT) data and thus suffer from the same limitations as DFT. To achieve more predictive accuracy, MLFFs based on higher levels of theory are required, but the training becomes exceptionally arduous. Here, we present an approach to generate MLFFs with beyond DFT accuracy which combines an efficient on-the-fly active learning method and Delta-machine learning. Using this approach, we generate an MLFF for zirconia based on the random phase approximation (RPA). Specifically, an MLFF trained on the fly during DFT-based molecular dynamics simulations is corrected by another MLFF that is trained on the differences between RPA and DFT calculated energies, forces, and stress tensors. We show that owing to the relatively smooth nature of these differences, the expensive RPA calculations can be performed only on a small number of representative structures of small unit cells selected by rank compression of the kernel matrix. This dramatically reduces the computational cost and allows one to generate an MLFF fully capable of reproducing high-level quantum-mechanical calculations beyond DFT. We carefully validate our approach and demonstrate its success in studying the phase transitions of zirconia. These results open the way to many-body calculations of finite-temperature properties of materials.
资助项目	Advanced Materials Simulation Engineering Tool (AMSET) project - US Naval Nuclear Laboratory (NNL) ; Austrian Science Fund (FWF) within the SFB TACO[F 81-N]
WOS研究方向	Materials Science ; Physics
语种	英语
出版者	AMER PHYSICAL SOC
WOS记录号	WOS:000761166700002
资助机构	Advanced Materials Simulation Engineering Tool (AMSET) project - US Naval Nuclear Laboratory (NNL) ; Austrian Science Fund (FWF) within the SFB TACO
内容类型	期刊论文
源URL	[http://ir.imr.ac.cn/handle/321006/173228]
专题	金属研究所_中国科学院金属研究所
通讯作者	Liu, Peitao
作者单位	1.VASP Software GmbH, Sensengasse 8, A-1090 Vienna, Austria 2.Univ Vienna, Fac Phys, Kolingasse 14-16, A-1090 Vienna, Austria 3.Univ Vienna, Ctr Computat Mat Sci, Kolingasse 14-16, A-1090 Vienna, Austria 4.Chinese Acad Sci, Inst Met Res, Shenyang Natl Lab Mat Sci, Shenyang, Peoples R China
推荐引用方式 GB/T 7714	Liu, Peitao,Verdi, Carla,Karsai, Ferenc,et al. Phase transitions of zirconia: Machine-learned force fields beyond density functional theory[J]. PHYSICAL REVIEW B,2022,105(6):6.
APA	Liu, Peitao,Verdi, Carla,Karsai, Ferenc,&Kresse, Georg.(2022).Phase transitions of zirconia: Machine-learned force fields beyond density functional theory.PHYSICAL REVIEW B,105(6),6.
MLA	Liu, Peitao,et al."Phase transitions of zirconia: Machine-learned force fields beyond density functional theory".PHYSICAL REVIEW B 105.6(2022):6.