Compositional Search of Stable Crystalline Structures in Multi-Component Alloys Using Generative Diffusion Models

TL;DR

This paper introduces an enhanced generative diffusion model, CDVAE, for efficiently exploring and designing stable multi-component alloy structures, significantly improving reconstruction accuracy and enabling inverse design with MD simulations.

Contribution

The paper develops novel extensions to the CDVAE model, improving its reconstruction capabilities and applying it to generate and optimize stable alloy configurations across phase space.

Findings

30% improvement in configuration reconstruction accuracy

High agreement with first principles data in identifying stable structures

Efficient inverse design framework using MD simulations

Abstract

Exploring the vast composition space of multi-component alloys presents a challenging task for both \textit{ab initio} (first principles) and experimental methods due to the time-consuming procedures involved. This ultimately impedes the discovery of novel, stable materials that may display exceptional properties. Here, the Crystal Diffusion Variational Autoencoder (CDVAE) model is adapted to characterize the stable compositions of a well studied multi-component alloy, NiFeCr, with two distinct crystalline phases known to be stable across its compositional space. To this end, novel extensions to CDVAE were proposed, enhancing the model's ability to reconstruct configurations from their latent space within the test set by approximately 30\% . A fact that increases a model's probability of discovering new materials when dealing with various crystalline structures. Afterwards, the new model is applied for materials generation, demonstrating excellent agreement in identifying stable configurations within the ternary phase space when compared to first principles data. Finally, a computationally efficient framework for inverse design is proposed, employing Molecular Dynamics (MD) simulations of multi-component alloys with reliable interatomic potentials, enabling the optimization of materials property across the phase space.