Machine learning modeling of lattice constants for half-Heusler alloys

The Gaussian process regression model is developed as a machine learning tool to find statistical correlations among lattice constants, a0, of half-Heusler compounds, ionic radii, and Pauling electronegativity of their alloying elements. Nearly 140 half-Heusler samples, containing alloying elements of Cr, Mn, Fe, Co, Ni, Rh, Ti, V, Al, Ga, In, Si, Ge, Sn, P, As, and Sb, are explored for this purpose. The modeling approach demonstrates a high degree of accuracy and stability, contributing to efficient and low-cost estimations of lattice constants of half-Heusler compounds.