Accelerating structure search using atomistic graph-based classifiers

TL;DR

This paper presents an atomistic graph-based classifier that leverages spectral graph theory and Voronoi tessellation to efficiently distinguish atomic structures, enhancing global optimization algorithms for complex potential energy landscapes.

Contribution

The paper introduces a novel atomistic classifier integrated into the GOFEE algorithm, improving structure filtering and reducing stagnation in global optimization of atomic systems.

Findings

Successfully optimized structures of pyroxene, olivine, Au12, LJ55, and LJ75 nanoparticles.

Demonstrated classifier's effectiveness in filtering structures and avoiding stagnation.

Enhanced global optimization performance with the new classifier.

Abstract

We introduce an atomistic classifier based on a combination of spectral graph theory and a Voronoi tessellation method. This classifier allows for the discrimination between structures from different minima of a potential energy surface, making it a useful tool for sorting through large datasets of atomic systems. We incorporate the classifier as a filtering method in the Global Optimization with First-principles Energy Expressions (GOFEE) algorithm. Here it is used to filter out structures from exploited regions of the potential energy landscape, whereby the risk of stagnation during the searches is lowered. We demonstrate the usefulness of the classifier by solving the global optimization problem of 2-dimensional pyroxene, 3-dimensional olivine, Au12, and Lennard-Jones LJ55 and LJ75 nanoparticles.