用于评估金纳米颗粒性质的机器学习原子间势

Evaluation of Machine Learning Interatomic Potentials for the Properties of Gold Nanoparticles.

作者信息

Fronzi Marco, Amos Roger D, Kobayashi Rika, Matsumura Naoki, Watanabe Kenta, Morizawa Rafael K

机构信息

University of Technology Sydney, Ultimo, NSW 2007, Australia.

Australian National University, Canberra, ACT 2601, Australia.

出版信息

Nanomaterials (Basel). 2022 Nov 3;12(21):3891. doi: 10.3390/nano12213891.

DOI:10.3390/nano12213891

PMID:36364667

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC9655512/

Abstract

We have investigated Machine Learning Interatomic Potentials in application to the properties of gold nanoparticles through the DeePMD package, using data generated with the VASP program. Benchmarking was carried out on Au20 nanoclusters against molecular dynamics simulations and show we can achieve similar accuracy with the machine learned potential at far reduced cost using LAMMPS. We have been able to reproduce structures and heat capacities of several isomeric forms. Comparison of our workflow with similar ML-IP studies is discussed and has identified areas for future improvement.

摘要

我们通过DeePMD软件包，利用VASP程序生成的数据，研究了机器学习原子间势在金纳米颗粒性质方面的应用。针对Au20纳米团簇，与分子动力学模拟进行了基准测试，结果表明，使用LAMMPS时，我们能够以低得多的成本，通过机器学习势实现相似的精度。我们已经能够重现几种异构体形式的结构和热容量。讨论了我们的工作流程与类似的机器学习原子间势研究的比较，并确定了未来改进的方向。