Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons

TL;DR

This paper presents a machine learning approach to create interatomic potentials that replicate quantum mechanical accuracy without explicitly modeling electrons, enabling efficient and precise simulations of materials.

Contribution

The authors introduce a flexible, data-driven interatomic potential model that is systematically improvable and capable of capturing complex quantum mechanical energy landscapes.

Findings

Accurately models properties of bulk carbon, silicon, and germanium.

Achieves significant computational savings in molecular dynamics simulations.

Demonstrates systematic improvement with additional data.

Abstract

We introduce a class of interatomic potential models that can be automatically generated from data consisting of the energies and forces experienced by atoms, derived from quantum mechanical calculations. The resulting model does not have a fixed functional form and hence is capable of modeling complex potential energy landscapes. It is systematically improvable with more data. We apply the method to bulk carbon, silicon and germanium and test it by calculating properties of the crystals at high temperatures. Using the interatomic potential to generate the long molecular dynamics trajectories required for such calculations saves orders of magnitude in computational cost.