Abstract Scope |
It has been found that both cation chemistry and degree of inversion play an important role in technically relevant properties of spinel oxides. In this study, we have developed and applied a machine learning based atomistic simulation approach to predict the equilibrium cation distribution in multi-cation spinel oxides. The database was constructed to contain the density functional theory calculated energies of the spinel oxides with various cation distribution. We applied the machine learning techniques (i.e., neural network and support vector machine) to find the relation between the system energy and structural features of the spinel oxides from the database, and further performed the atomistic Monte Carlo simulations to predict the equilibrium cation distribution in AB2O4 spinel as function of its composition and synthesis temperature. Our predicted cation distributions for material systems of single spinel CoFe2O4, NiFe2O4, MgAl2O4, MgFe2O4, and double spinel MgAl2-xFexO4 are well validated by available experimental results. |