Machine-learning based interatomic potential for amorphous carbon

TL;DR

This paper presents a machine-learning interatomic potential for amorphous carbon that achieves near-DFT accuracy at lower computational cost, enabling detailed simulations of liquid and amorphous phases.

Contribution

A novel Gaussian approximation potential for amorphous carbon using hierarchical structural descriptors, achieving high accuracy across diverse carbon structures.

Findings

Accurately models energetic and structural properties of carbon across densities

Captures liquid phase structures better than existing empirical potentials

Enables simulations of surface reconstructions and amorphous surface energies

Abstract

We introduce a Gaussian approximation potential (GAP) for atomistic simulations of liquid and amorphous elemental carbon. Based on a machine-learning representation of the density-functional theory (DFT) potential-energy surface, such interatomic potentials enable materials simulations with close-to DFT accuracy but at much lower computational cost. We first determine the maximum accuracy that any finite-range potential can achieve in carbon structures; then, using a novel hierarchical set of two-, three-, and many-body structural descriptors, we construct a GAP model that can indeed reach the target accuracy. The potential yields accurate energetic and structural properties over a wide range of densities; it also correctly captures the structure of the liquid phases, at variance with state-of-the-art empirical potentials. Exemplary applications of the GAP model to surfaces of "diamond-like" tetrahedral amorphous carbon (ta-C) are presented, including an estimate of the amorphous material's surface energy, and simulations of high-temperature surface reconstructions ("graphitization"). The new interatomic potential appears to be promising for realistic and accurate simulations of nanoscale amorphous carbon structures.