当前位置: X-MOL 学术J. Chem. Phys. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Machine-learned electron correlation model based on frozen core approximation
The Journal of Chemical Physics ( IF 3.1 ) Pub Date : 2020-11-11 , DOI: 10.1063/5.0021281
Yasuhiro Ikabata 1 , Ryo Fujisawa 2 , Junji Seino 1, 3 , Takeshi Yoshikawa 1, 4 , Hiromi Nakai 1, 2, 5
Affiliation  

The machine-learned electron correlation (ML-EC) model is a regression model in the form of a density functional that reproduces the correlation energy density based on wavefunction theory. In a previous study [T. Nudejima et al., J. Chem. Phys. 151, 024104 (2019)], the ML-EC model was constructed using the correlation energy density from all-electron calculations with basis sets including core polarization functions. In this study, we applied the frozen core approximation (FCA) to the correlation energy density to reduce the computational cost of the response variable used in machine learning. The coupled cluster singles, doubles, and perturbative triples [CCSD(T)] correlation energy density obtained from a grid-based energy density analysis was analyzed within FCA and correlation-consistent basis sets without core polarization functions. The complete basis set (CBS) limit of the correlation energy density was obtained using the extrapolation and composite schemes. The CCSD(T)/CBS correlation energy densities based on these schemes showed reasonable behavior, indicating its appropriateness as a response variable. As expected, the computational time was significantly reduced, especially for systems containing elements with a large number of inner-shell electrons. Based on the density-to-density relationship, a large number of data (5 662 500 points), which were accumulated from 30 molecules, were sufficient to construct the ML-EC model. The valence-electron correlation energies and reaction energies calculated using the constructed model were in good agreement with the reference values, the latter of which were superior in accuracy to density functional calculations using 71 exchange–correlation functionals. The numerical results indicate that the FCA is useful for constructing a versatile model.

中文翻译:

基于冻结核逼近的机器学习电子相关模型

机器学习的电子相关(ML-EC)模型是密度函数形式的回归模型,该模型基于波函数理论再现相关能量密度。在先前的研究中[T. Nudejima等。J.Chem。物理 151,024024(2019)],使用全电子计算中的相关能量密度和包括核极化函数的基本集构建了ML-EC模型。在这项研究中,我们将冻结核心近似(FCA)应用于相关能量密度,以减少机器学习中使用的响应变量的计算成本。从基于网格的能量密度分析获得的耦合簇单,双和微扰三元组[CCSD(T)]相关能量密度在FCA和无核心极化函数的相关一致基集中进行了分析。使用外推和复合方案获得了相关能量密度的完整基集(CBS)极限。基于这些方案的CCSD(T)/ CBS相关能量密度显示出合理的行为,指示其是否适合作为响应变量。正如预期的那样,计算时间显着减少,尤其是对于包含具有大量内壳电子的元素的系统而言。基于密度与密度的关系,从30个分子中积累的大量数据(566.25万个点)足以构建ML-EC模型。使用所构建的模型计算出的价电子相关能和反应能与参考值吻合良好,后者的精确度优于使用71种交换相关函数的密度函数计算。数值结果表明,FCA可用于构建通用模型。特别是对于包含具有大量内壳电子的元素的系统。基于密度与密度的关系,从30个分子中积累的大量数据(566.25万个点)足以构建ML-EC模型。使用所构建的模型计算出的价电子相关能和反应能与参考值吻合良好,后者的精确度优于使用71种交换相关函数的密度函数计算。数值结果表明,FCA可用于构建通用模型。特别是对于包含具有大量内壳电子的元素的系统。基于密度与密度的关系,从30个分子中积累的大量数据(566.25万个点)足以构建ML-EC模型。使用所构建的模型计算出的价电子相关能和反应能与参考值吻合良好,后者的精确度优于使用71种交换相关函数的密度函数计算。数值结果表明,FCA可用于构建通用模型。足以构建ML-EC模型。使用所构建的模型计算出的价电子相关能和反应能与参考值吻合良好,后者的精确度优于使用71种交换相关函数的密度函数计算。数值结果表明,FCA可用于构建通用模型。足以构建ML-EC模型。使用所构建的模型计算的价电子相关能和反应能与参考值吻合良好,后者的准确度优于使用71个交换相关函数的密度泛函计算。数值结果表明,FCA可用于构建通用模型。
更新日期:2020-11-13
down
wechat
bug