Semi-supervised generative approach to point-defect formation in chemically disordered compounds: application to uranium-plutonium mixed oxides

Abstract

Machine-learning methods are nowadays of common use in the field of material science. For example, they can aid in optimizing the physicochemical properties of new materials, or help in the characterization of highly complex chemical compounds. An especially challenging problem arises in the modeling of chemically disordered solid solutions, for which some properties depend on the distribution of chemical species in the crystal lattice. This is the case of defect properties of uranium-plutonium mixed oxides nuclear fuels. The number of possible configurations is so high that the problem becomes intractable if treated with direct sampling. We thus propose a machine learning approach, based on generative modeling, to optimize the exploration of this large configuration space. A probabilistic, semi-supervised approach using Mixture Density Network is applied to estimate the concentration of thermal defects in (U, Pu)O2. We show that this method, based on the prediction of the density of states of formation energy of a defect, is computationally much more cost-efficient compared to other approaches available in the literature.