Global optimization in the discrete and variable-dimension conformational space: The case of crystal with the strongest atomic cohesion

TL;DR

This paper presents a novel computational approach combining crystal graph neural networks and Bayesian optimization to efficiently identify crystal structures with maximum atomic cohesion, advancing inverse materials design.

Contribution

It introduces a new method that optimizes crystal structures considering composition, stoichiometry, and structure, enabling discovery of highly cohesive crystals with practical stability.

Findings

Identified new high-cohesion crystal structures confirmed by DFT.

Effectively optimized structures across full configuration space.

Demonstrated practical application in inverse materials design.

Abstract

We introduce a computational method to optimize target physical properties in the full configuration space regarding atomic composition, chemical stoichiometry, and crystal structure. The approach combines the universal potential of the crystal graph neural network and Bayesian optimization. The proposed approach effectively obtains the crystal structure with the strongest atomic cohesion from all possible crystals. Several new crystals with high atomic cohesion are identified and confirmed by density functional theory for thermodynamic and dynamic stability. Our method introduces a novel approach to inverse materials design with additional functional properties for practical applications.