Discovering Superhard B-N-O Compounds by Iterative Machine Learning and Evolutionary Structure Predictions

TL;DR

This study employs an iterative machine learning and evolutionary algorithm approach to identify new superhard B-N-O compounds, revealing potential superhard insulators with wide bandgaps and thermodynamic stability.

Contribution

The paper introduces a novel iterative ML method combined with ab initio calculations to discover superhard B-N-O compounds, focusing on specific compositions with high stability and hardness.

Findings

Identified B$_{x+2}$N$_{x}$O$_{3}$ compounds as potentially superhard.

Discovered these compounds are wide bandgap insulators ($ extgreater 4.4$ eV).

Demonstrated the effectiveness of iterative ML and ab initio methods for material discovery.

Abstract

We search for new superhard B-N-O compounds with an iterative machine learning (ML) procedure, where ML models are trained using sample crystal structures from evolutionary algorithm. We first use cohesive energy to evaluate the thermodynamic stability of varying B$_x$N$_y$O$_z$ compositions, and then gradually focus on compositional regions with high cohesive energy and high hardness. The results converge quickly after a few iterations. Our resulting ML models show that B$_{x+2}$N$_{x}$O$_{3}$ compounds with $x \geq 3$ (like B$_5$N$_3$O$_3$, B$_6$N$_4$O$_3$, etc.) are potentially superhard and thermodynamically favorable. Our meta-GGA density functional theory calculations indicate that these materials are also wide bandgap ($\ge 4.4$ eV) insulators, with the valence band maximum related to the $p$-orbitals of nitrogen atoms near vacant sites. This study demonstrates that an iterative method combining ML and ab initio simulations provides a powerful tool for discovering novel materials.