Machine learning lattice constants for cubic perovskite A22+BB′O6 compounds

Abstract

Double perovskite oxides have attracted great attention in the past decade due to their unique and versatile material properties. The lattice constant, a, as the only variable parameter among the six parameters in the cubic structure, has a significant impact on the structural stability, electronic structure, magnetic ordering, and thus material performance. In this work, a Gaussian process regression (GPR) model is developed to elucidate the statistical relationship among ionic radii, electronegativities, oxidation states, and lattice constants for cubic perovskite A₂²⁺BB′O₆ compounds. A total of 147 samples with lattice constants ranging from 7.700 Å to 8.890 Å are explored. The modeling approach demonstrates a high degree of accuracy and stability, contributing to efficient and low-cost estimations of lattice constants.