Accurate helium–benzene potential: From CCSD(T) to Gaussian process regression

Abstract

The accurate modeling of non-covalent interactions between helium and graphitic materials is important for understanding quantum phenomena in reduced dimensions, with the helium–benzene complex serving as the fundamental prototype. However, creating a quantitatively reliable potential energy surface (PES) for this weakly bound system remains a significant computational challenge. In this study, we present a comprehensive, multi-level investigation of the He–benzene interaction, establishing benchmark energies using high-level coupled-cluster singles-and-doubles with perturbative triples [CCSD(T)] methods extrapolated to the complete basis set limit and assessing higher-order contributions. We use symmetry-adapted perturbation theory to benchmark it against CCSD(T) and to decompose the interaction into its physical components—confirming it is dominated by a balance between dispersion and exchange-repulsion. A continuous, three-dimensional PES is constructed from discrete ab initio points using multifidelity Gaussian process regression that combines density functional theory results with sparse coupled-cluster energies. The result is a highly accurate PES with sub-cm−1 accuracy that obeys physical laws. This new PES is applied to path integral Monte Carlo (PIMC) simulations to study the solvation of 4He atoms on benzene at low temperatures. Our PIMC results reveal qualitatively different solvation behavior, particularly in the filling of adsorption layers, when compared to simulations using commonly employed empirical Lennard-Jones potentials. This study provides a benchmark PES essential for accurate many-body simulations of helium on larger polycyclic aromatic hydrocarbons toward graphene.