Machine learning lattice constants of zircon-group minerals MXO4

Abstract

For tetragonal zircon-type structures, the stoichiometry, ionic radii, and electronegativities of alloying elements affect lattice constants, a and c. Lattice distortions have significant impacts on the stability, electronic structure, ionic conductivity, and thus materials performance. Here, we develop the Gaussian process regression (GPR) model to elucidate statistical relationships among ionic radii, electronegativities, and lattice constants for zircon-group minerals MXO4 compounds with 100 samples. The modeling approach shows a high degree of accuracy and stability, contributing to efficient and low-cost estimations of lattice constants, which can be employed in further computational studies on materials behavior.