Accurate molecular polarizabilities with coupled-cluster theory and machine learning

TL;DR

This paper combines high-level quantum mechanical calculations with machine learning to accurately predict molecular polarizabilities efficiently, surpassing traditional density functional theory in diverse organic molecules.

Contribution

It introduces a robust machine-learning model trained on LR-CCSD data to predict molecular polarizabilities with high accuracy and low computational cost.

Findings

Machine learning predicts polarizabilities with LR-CCSD accuracy.

Model outperforms hybrid DFT in diverse molecules.

Atom-centered decomposition offers insights into DFT shortcomings.

Abstract

The molecular polarizability describes the tendency of a molecule to deform or polarize in response to an applied electric field. As such, this quantity governs key intra- and inter-molecular interactions such as induction and dispersion, plays a key role in determining the spectroscopic signatures of molecules, and is an essential ingredient in polarizable force fields and other empirical models for collective interactions. Compared to other ground-state properties, an accurate and reliable prediction of the molecular polarizability is considerably more difficult as this response quantity is quite sensitive to the description of the underlying molecular electronic structure. In this work, we present state-of-the-art quantum mechanical calculations of the static dipole polarizability tensors of 7,211 small organic molecules computed using linear-response coupled-cluster singles and doubles theory (LR-CCSD). Using a symmetry-adapted machine-learning based approach, we demonstrate that it is possible to predict the molecular polarizability with LR-CCSD accuracy at a negligible computational cost. The employed model is quite robust and transferable, yielding molecular polarizabilities for a diverse set of 52 larger molecules (which includes challenging conjugated systems, carbohydrates, small drugs, amino acids, nucleobases, and hydrocarbon isomers) at an accuracy that exceeds that of hybrid density functional theory (DFT). The atom-centered decomposition implicit in our machine-learning approach offers some insight into the shortcomings of DFT in the prediction of this fundamental quantity of interest.