Machine Learning and Evolutionary Prediction of Superhard B-C-N Compounds

TL;DR

This study employs machine learning models trained on extensive data to predict elastic and hardness properties of B-C-N compounds, identifying potential new superhard materials validated by computational methods.

Contribution

It introduces a random forest approach using chemical formulas to predict superhard B-C-N compounds, validated by evolutionary algorithms and density functional theory.

Findings

Identified new superhard B-C-N compounds with hardness >40 GPa.

Developed models predicting elastic properties from chemical formulas.

Validated predictions with computational methods, suggesting feasible synthesis routes.

Abstract

We build random forests models to predict elastic properties and mechanical hardness of a compound, using only its chemical formula as input. The model training uses over 10,000 target compounds and 60 features based on stoichiometric attributes, elemental properties, orbital occupations, and ionic bonding levels. Using the models, we construct triangular graphs for B-C-N compounds to map out their bulk and shear moduli, as well as hardness values. The graphs indicate that a 1:1 B-N ratio can lead to various superhard compositions. We also validate the machine learning results by evolutionary structure prediction and density functional theory. Our study shows that BC$_{10}$N, B$_4$C$_5$N$_3$, and B$_2$C$_3$N exhibit dynamically stable phases with hardness values $>40$GPa, which are potentially new superhard materials that could be synthesized by low-temperature plasma methods.