Development and Application of Atomic Simulation Software Based on Machine Learning Potentials

被引：0
|
作者：
Shang C. [1 ]
Kang P. [1 ]
Liu Z. [1 ]
机构：
[1] Department of Chemistry, Fudan University, Shanghai
来源：
Kuei Suan Jen Hsueh Pao/Journal of the Chinese Ceramic Society | 2023年 / 51卷 / 02期
关键词：
atomic simulation software; global potential energy surface; machine learning; potential;
D O I：
10.14062/j.issn.0454-5648.20220824
中图分类号：
学科分类号：
摘要：
Recent development of large-scale atomic simulation techniques based on machine learning has brought a great promise in chemistry. These simulations are featured by both high speed and high accuracy. This review outlined recent development on three key aspects of atomic simulation based on machine learning potential, i.e., machine learning models and structure descriptors, generation of global potential energy surface training sets, and automatic training of potential functions based on active learning. It is indicated that the designed structure descriptor and feedforward neural network model are suitable for generating a highly complex global potential energy surface. In addition, the applications of LASP software in material and reaction simulations were also selected to illustrate how ML-based atomic simulation could assist the discovery of novel materials and reactions. © 2023 Chinese Ceramic Society. All rights reserved.
引用
收藏
页码：476 / 487
页数：11
相关论文
共 103 条
  • [1] HOHENBERG P, KOHN W J P r., Inhomogeneous electron gas, Phys Rev, 136, 3B, pp. B864-B871, (1964)
  • [2] CAR R, PARRINELLO M., Unified approach for molecular dynamics and density-functional theory, Phys Rev Lett, 55, 22, pp. 2471-2474, (1985)
  • [3] ZHAO Y, TRUHLAR D G., Density Functionals with Broad Applicability in Chemistry, Account Chem Res, 41, 2, pp. 157-167, (2008)
  • [4] ROUSSEA A, SELLONI A., Theoretical insights into the surface physics and chemistry of redox-active oxides, Nat Rev Mater, 5, 6, pp. 460-475, (2020)
  • [5] JORDAN M I, MITCHELL T M., Machine learning: Trends, perspectives, and prospects, Science, 349, 6245, pp. 255-260, (2015)
  • [6] BLANK T B, BROWN S D, CALHOUN A W, Et al., Neural-Network Models of Potential-Energy Surfaces, J Chem Phys, 103, 10, pp. 4129-4137, (1995)
  • [7] LIU T, FU B, ZHANG D H., Six-dimensional quantum dynamics study for the dissociative adsorption of HCl on Au(111) surface, J Chem Phys, 139, 18, (2013)
  • [8] BEHLER J, PARRINELLO M., Generalized neural-network representation of high-dimensional potential-energy surfaces, Phys Rev Lett, 98, 14, (2007)
  • [9] BEHLER J., Atom-centered symmetry functions for constructing high-dimensional neural network potentials, J Chem Phys, 134, 7, (2011)
  • [10] SOSSO G C, MICELI G, CARAVATI S, Et al., Neural network interatomic potential for the phase change material GeTe, Phys Rev B, 85, 17, (2012)
12345678910