Development of Machine Learning Models to Reproduce Coupled-Cluster Molecular Energies

Key Points

Prediction accuracy for coupled-cluster molecular energies matches that of density functional theory, showing effectiveness.
Machine learning models constructed to predict atomic environment energies demonstrate high accuracy levels.
Energy density analysis was used to extract atomic energies from quantum chemical calculations effectively.
Implications suggest that these machine learning models could enhance computational efficiency in quantum chemistry.

Abstract

We attempted to reproduce molecular energies at the coupled-cluster level from molecular structures by constructing machine learning models that reproduce atomic environment energies, defined as the difference between the atomic energy in a molecule and that of the corresponding isolated atom. To obtain atomic energies from quantum chemical calculations, we adopted energy density analysis. Our results showed that the prediction accuracy of coupled-cluster molecular energies was comparable to that for density functional theory.

Bookmark

View Full Paper

Bookmark

View Full Paper

Development of Machine Learning Models to Reproduce Coupled-Cluster Molecular Energies

Key Points

Abstract

Cite This Study