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

TL;DR

This paper introduces a semi-supervised generative machine learning method using Mixture Density Networks to efficiently predict defect formation energies in chemically disordered uranium-plutonium oxides, reducing computational costs.

Contribution

It presents a novel semi-supervised generative modeling approach for exploring defect properties in complex disordered materials, specifically applied to nuclear fuel oxides.

Findings

The method accurately predicts defect formation energies.

It significantly reduces computational effort compared to existing methods.

The approach effectively handles large configuration spaces.

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.