A Symmetry-orientated Divide-and-Conquer Method for Crystal Structure Prediction

TL;DR

This paper introduces a symmetry-oriented divide-and-conquer approach for crystal structure prediction, leveraging AI to efficiently explore symmetry-dependent subspaces and accurately predict complex crystal structures.

Contribution

The novel method decomposes the search space into symmetry-based subspaces and uses AI for selecting promising regions, improving prediction efficiency for complex structures.

Findings

Successfully predicted structures of binary Lennard-Jones mixtures

Predicted high-pressure phase of ice with over 100 atoms

Reduced exploration of complex subspaces in structure prediction

Abstract

Crystal structure prediction has been a subject of topical interest, but remains a substantial challenge, especially for complex structures as it deals with the global minimization of the extremely rugged high-dimensional potential energy surface. In this manuscript, a symmetry-orientated divide-and-conquer scheme was proposed to construct a symmetry tree graph, where the entire search space is decomposed into a finite number of symmetry-dependent subspaces. An artificial intelligence-based symmetry selection strategy was subsequently devised to select the low-lying subspaces with high symmetries for global exploration and in-depth exploitation. Our approach can significantly simplify the problem of crystal structure prediction by avoiding exploration of the most complex P1 subspace on the entire search space and have the advantage of preserving the crystal symmetry during structure evolution, making it well suitable for predicting the complex crystal structures. The effectiveness of the method has been validated by successful prediction of the candidate structures of binary Lennard-Jones mixtures and high-pressure phase of ice, containing more than one hundred atoms in the simulation cell. The work, therefore, opens up an opportunity towards achieving the long-sought goal for crystal structure prediction of complex systems.