Header

UZH-Logo

Maintenance Infos

A Machine Learning Approach for MP2 Correlation Energies and Its Application to Organic Compounds


Han, Ruocheng; Rodríguez-Mayorga, Mauricio; Luber, Sandra (2021). A Machine Learning Approach for MP2 Correlation Energies and Its Application to Organic Compounds. Journal of Chemical Theory and Computation, 17(2):777-790.

Abstract

A proper treatment of electron correlation effects is indispensable for accurate simulation of compounds. Various post-Hartree–Fock methods have been adopted to calculate correlation energies of chemical systems, but time complexity usually prevents their usage in a large scale. Here, we propose a density functional approximation, based on machine learning using neural networks, which can be readily employed to produce results comparable to second-order Møller–Plesset perturbation (MP2) ones for organic compounds with reduced computational cost. Various systems have been tested and the transferability across basis sets, structures, and nuclear configurations has been evaluated. Only a small number of molecules at the equilibrium structure has been needed for the training, and generally less than 5% relative error has been achieved for structures outside the training domain and systems containing about 140 atoms. In addition, this approach has been applied to make predictions on correlation energies of nuclear configurations extracted from density functional theory-based molecular dynamics trajectories with only one or two structures as training data.

Abstract

A proper treatment of electron correlation effects is indispensable for accurate simulation of compounds. Various post-Hartree–Fock methods have been adopted to calculate correlation energies of chemical systems, but time complexity usually prevents their usage in a large scale. Here, we propose a density functional approximation, based on machine learning using neural networks, which can be readily employed to produce results comparable to second-order Møller–Plesset perturbation (MP2) ones for organic compounds with reduced computational cost. Various systems have been tested and the transferability across basis sets, structures, and nuclear configurations has been evaluated. Only a small number of molecules at the equilibrium structure has been needed for the training, and generally less than 5% relative error has been achieved for structures outside the training domain and systems containing about 140 atoms. In addition, this approach has been applied to make predictions on correlation energies of nuclear configurations extracted from density functional theory-based molecular dynamics trajectories with only one or two structures as training data.

Statistics

Citations

Dimensions.ai Metrics

Altmetrics

Downloads

3 downloads since deposited on 11 Oct 2021
3 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:07 Faculty of Science > Department of Chemistry
Dewey Decimal Classification:540 Chemistry
Scopus Subject Areas:Physical Sciences > Computer Science Applications
Physical Sciences > Physical and Theoretical Chemistry
Uncontrolled Keywords:Physical and Theoretical Chemistry, Computer Science Applications
Language:English
Date:9 February 2021
Deposited On:11 Oct 2021 14:17
Last Modified:12 Oct 2021 20:00
Publisher:American Chemical Society (ACS)
ISSN:1549-9618
OA Status:Green
Publisher DOI:https://doi.org/10.1021/acs.jctc.0c00898
Project Information:
  • : FunderSNSF
  • : Grant IDPP00P2_170667
  • : Project TitleIn Silico Investigation and Design of Bio-inspired Catalysts for Water Splitting

Download

Green Open Access

Download PDF  'A Machine Learning Approach for MP2 Correlation Energies and Its Application to Organic Compounds'.
Preview
Content: Accepted Version
Filetype: PDF
Size: 3MB
View at publisher