Machine learning enabled accurate prediction of structural and magnetic properties of cobalt ferrite

Abstract

A machine learning enabled computational approach has been developed to accurately predict the equilibrium degree of inversion in spinel lattice and some magnetic properties of cobalt ferrite (CoFe₂O₄) crystal. The computational approach is composed of construction of a database from density functional theory calculations, training of machine learning models, and atomistic simulations. Support vector regression was employed to derive the relation between system energy and atomic structures of CoFe₂O₄. Using this trained machine learning model, atomistic Monte Carlo simulations predicted the equilibrium degree of inversion of CoFe₂O₄ to be 0.755 at 1237 K. The strength of twenty-three types of superexchange interactions were determined using the linear regression model and further applied in magnetic Monte Carlo simulations to predict the Curie temperature of CoFe₂O₄ to be 914 K. The predictions from the presented computational approach are well validated by the results from neutron diffraction measurement on CoFe₂O₄.