Systematic global structure search of bismuth-based binary systems under pressure using machine learning potentials

TL;DR

This study employs machine learning potentials to efficiently explore and predict novel bismuth-based binary crystal structures under pressure, revealing new compounds and confirming known ones, thus advancing materials discovery.

Contribution

It introduces polynomial machine learning potentials tailored for bismuth systems, enabling comprehensive global structure searches under pressure with high accuracy and efficiency.

Findings

Discovered numerous new bismuth-based compounds.

Successfully identified all known compounds within the explored space.

Demonstrated robustness of ML potentials for crystal structure prediction.

Abstract

Machine learning potentials (MLPs) have significantly advanced global crystal structure prediction by enabling efficient and accurate property evaluations. In this study, global structure searches are performed for 11 bismuth-based binary systems, including Na-Bi, Ca-Bi, and Eu-Bi, under pressures ranging from 0 to 20 GPa, employing polynomial MLPs developed specifically for these systems. The searches reveal numerous compounds not previously reported in the literature and identify all experimentally known compounds that are representable within the explored configurational space. These results highlight the robustness and reliability of the current MLP-based structure search. The study provides valuable insights into the discovery and design of novel bismuth-based materials under both ambient and high-pressure conditions.