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

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.

References in corpus (13)

• Scikit-learn: Machine Learning in Python
• Necessary and Sufficient Elastic Stability Conditions in Various Crystal Systems
• Intrinsic Correlation between Hardness and Elasticity in Polycrystalline Materials and Bulk Metallic Glasses
• A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials
• AFLOW: An automatic framework for high-throughput materials discovery
• Data-driven materials science: status, challenges and perspectives
• Universal Fragment Descriptors for Predicting Electronic Properties of Inorganic Crystals
• Simple and accurate model of fracture toughness of solids
• Evolutionary search for novel superhard materials: Methodology and applications to forms of carbon and TiO2
• Superhard Phases of Simple Substances and Binary Compounds of the B-C-N-O System: from Diamond to the Latest Results (a Review)
• High-pressure synthesis of superhard and ultrahard materials
• Predicted phase diagram of B-C-N
• Structure, non-stoichiometry, and geometrical frustration of alpha-tetragonal boron

Cited by in corpus (9)

• Mutual modulation via charge transfer and unpaired electrons of catalyt-ic site for superior intrinsic activity of N2 reduction: from high-throughput computations assisted with machine learning perspective
• Machine learning the relationship between Debye temperature and superconducting transition temperature
• Global optimization in the discrete and variable-dimension conformational space: The case of crystal with the strongest atomic cohesion
• Machine Learning and First-Principles Predictions of Materials with Low Lattice Thermal Conductivity
• Discovering Superhard B-N-O Compounds by Iterative Machine Learning and Evolutionary Structure Predictions
• Fused borophenes: a new family of superhard materials
• Polar Encoding: A Simple Baseline Approach for Classification with Missing Values
• Load-dependent Hardness Prediction for Materials using Machine Learning
• First-Principles Calculation of Superconducting $T_c$ in Superhard B-C-N Metals