TY - JOUR

T1 - Machine-learned electron correlation model based on frozen core approximation

AU - Ikabata, Yasuhiro

AU - Fujisawa, Ryo

AU - Seino, Junji

AU - Yoshikawa, Takeshi

AU - Nakai, Hiromi

N1 - Funding Information:
Some of the calculations were performed at the Research Center for Computational Science (RCCS), Okazaki Research Facilities, National Institutes of Natural Sciences (NINS). This study was supported, in part, by the “Elements Strategy Initiative for Catalysts and Batteries (ESICB)” project (Grant No. JPMXP0112101003) by the Ministry of Education, Culture, Sports, Science, and Technology (MEXT), Japan. Y.I. received support from the Grants-in-Aid for Scientific Research (“KAKENHI”) (Grant No. JP18K14184) by the Japan Society for the Promotion of Science (JSPS). J.S. received support from the PRESTO program, “Advanced Materials Informatics through Comprehensive Integration among Theoretical, Experimental, Computational, and Data-Centric Sciences,” sponsored by the Japan Science and Technology Agency (JST).
Publisher Copyright:
© 2020 Author(s).

PY - 2020/11/14

Y1 - 2020/11/14

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85096153402&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85096153402&partnerID=8YFLogxK

U2 - 10.1063/5.0021281

DO - 10.1063/5.0021281

M3 - Article

C2 - 33187434

AN - SCOPUS:85096153402

VL - 153

JO - Journal of Chemical Physics

JF - Journal of Chemical Physics

SN - 0021-9606

IS - 18

M1 - 184108

ER -