期刊
INTERNATIONAL JOURNAL OF QUANTUM CHEMISTRY
卷 116, 期 13, 页码 979-987出版社
WILEY
DOI: 10.1002/qua.25115
关键词
Kohn-Sham density functional theory; neural networks; reactive force fields; potential energy surfaces; machine learning
类别
资金
- National Science Foundation [CBET-1506770]
- R.K. Mellon Foundation
- Department of Chemical and Petroleum Engineering, University of Pittsburgh
- Div Of Chem, Bioeng, Env, & Transp Sys
- Directorate For Engineering [1506770] Funding Source: National Science Foundation
We have studied how ReaxFF and Behler-Parrinello neural network (BPNN) atomistic potentials should be trained to be accurate and tractable across multiple structural regimes of Au as a representative example of a single-component material. We trained these potentials using subsets of 9,972 Kohn-Sham density functional theory calculations and then validated their predictions against the untrained data. Our best ReaxFF potential was trained from 848 data points and could reliably predict surface and bulk data; however, it was substantially less accurate for molecular clusters of 126 atoms or fewer. Training the ReaxFF potential to more data also resulted in overfitting and lower accuracy. In contrast, BPNN could be fit to 9,734 calculations, and this potential performed comparably or better than ReaxFF across all regimes. However, the BPNN potential in this implementation brings significantly higher computational cost. (C) 2016 Wiley Periodicals, Inc.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据