Accelerating the Discovery of Transition Metal Borides by Machine Learning on Small Data Sets

Accurate and efficient prediction of the stability and structure-stability relationship is important to discover materials; however, it requires tremendous efforts via traditional trial-and-error schemes. Here, we presented a small-data set machine learning (ML) method to accelerate the discovery of promising ternary transition metal boride (MAB) candidates. Based on data sets obtained by ab initio calculations, we developed three robust neural networks to predict the decomposition energy (ΔH_d) and assess the thermodynamic stability of 212-typed MABs (M₂AB₂). The quantitative relation between ΔH_d and stability was unraveled by several composition-and-structure descriptors. Three hexagonal M₂AB₂, i.e., Nb₂PB₂, Nb₂AsB₂, and Zr₂SB₂, were discovered to be stable with negative ΔH_d, and 75 metastable MABs were identified with ΔH_d less than 70 meV/atom. Finally, the dynamical stability and mechanical properties of MABs were investigated by ab initio calculations, whose results further verified the reliability of our ML models. This work provided a ML approach on small data sets to accelerate the discovery of compounds and expanded the MAB phase family to V_A and VI_A groups.