# Efficient global structure optimization with a machine learned surrogate model

## TL;DR

This paper introduces GOFEE, a global optimization method that combines machine-learned surrogate models with first-principles calculations to efficiently explore atomistic structures, significantly outperforming traditional algorithms.

## Contribution

The paper presents a novel scheme integrating Gaussian Process-based surrogate modeling with active learning for efficient global structure optimization using first-principles energy calculations.

## Key findings

- Outperforms traditional evolutionary algorithms by two orders of magnitude.
- Successfully identifies surface reconstructions and initial oxidation stages.
- Demonstrates efficiency in exploring complex atomistic potential energy landscapes.

## Abstract

We propose a scheme for global optimization with first-principles energy expressions (GOFEE) of atomistic structure. While unfolding its search, the method actively learns a surrogate model of the potential energy landscape on which it performs a number of local relaxations (exploitation) and further structural searches (exploration). Assuming Gaussian Processes, an acquisition function is used to decide on which of the resulting structures is the more promising. Subsequently, a single point first-principles energy calculation is conducted for that structure. The method is demonstrated to outperform by two orders of magnitude a well established first-principles based evolutionary algorithm in finding surface reconstructions. Finally, GOFEE is utilized to identify initial stages of the edge oxidation and oxygen intercalation of graphene sheets on the Ir(111) surface.