Accelerating crystal structure prediction by machine-learning interatomic potentials with active learning

TL;DR

This paper introduces a machine-learning based method combined with an evolutionary algorithm to accelerate crystal structure prediction, significantly reducing computational costs while maintaining accuracy, demonstrated on various elemental systems.

Contribution

The authors develop an active learning approach for interatomic potentials integrated with USPEX, enabling rapid and accurate crystal structure predictions from scratch.

Findings

Successfully predicted known allotropes of carbon, sodium, and boron.

Discovered a new 54-atom boron structure.

Achieved several orders of magnitude speedup over traditional DFT methods.

Abstract

In this letter we propose a new methodology for crystal structure prediction, which is based on the evolutionary algorithm USPEX and the machine-learning interatomic potentials actively learning on-the-fly. Our methodology allows for an automated construction of an interatomic interaction model from scratch replacing the expensive DFT with a speedup of several orders of magnitude. Predicted low-energy structures are then tested on DFT, ensuring that our machine-learning model does not introduce any prediction error. We tested our methodology on a problem of prediction of carbon allotropes, dense sodium structures and boron allotropes including those which have more than 100 atoms in the primitive cell. All the the main allotropes have been reproduced and a new 54-atom structure of boron have been found at very modest computational efforts.