期刊
JOURNAL OF CHEMICAL THEORY AND COMPUTATION
卷 14, 期 1, 页码 216-224出版社
AMER CHEMICAL SOC
DOI: 10.1021/acs.jctc.7b01157
关键词
-
资金
- EPSRC [EP/K005472]
- Brazilian government's FAPESP [2014/21241-9, 2015/22247-3]
- EPSRC [EP/K005472/1] Funding Source: UKRI
- Fundacao de Amparo a Pesquisa do Estado de Sao Paulo (FAPESP) [15/22247-3] Funding Source: FAPESP
We present an innovative method for predicting the dynamic electron correlation energy of an atom or a bond in a molecule utilizing topological atoms. Our approach uses the machine learning method Kriging (Gaussian Process Regression with a non-zero mean function) to predict these dynamic electron correlation energy contributions. The true energy values are calculated by partitioning the MP2 two-particle density-matrix via the Interacting Quantum Atoms (IQA) procedure. To our knowledge, this is the first time such energies have been predicted by a machine learning technique. We present here three important proof-of-concept cases: the water monomer, the water dimer, and the van der Waals complex H-2 center dot center dot center dot He. These cases represent the final step toward the design of a full IQA potential for molecular simulation. This final piece will enable us to consider situations in which dispersion is the dominant intermolecular interaction. The results from these examples suggest a new method by which dispersion potentials for molecular simulation can be generated.
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