Virp: neural network-accelerated prediction of physical properties in site-disordered materials

TL;DR

This paper introduces Virp, a neural network-accelerated pipeline that efficiently predicts properties of site-disordered materials, overcoming limitations of traditional simulation methods.

Contribution

The authors develop a novel pipeline combining virtual cell generation, sampling, and post-processing to enable feasible analysis of complex disordered materials.

Findings

400 virtual cells suffice for adequate sampling of configurational space

The pipeline significantly reduces computational costs compared to traditional methods

Effective prediction of properties in site-disordered materials achieved

Abstract

Among metallic alloys, ceramics, and even common compounds such as water ice, it is usual to find materials in which crystalline order is expressed as a probability. In such cases, one or more sites within a crystal can be occupied by multiple elements or vacancies, according to a set of probabilities. These crystal structures remain inaccessible to common first-principles materials simulation methodologies, which assumes perfect crystal order. Workaround strategies to this limitation include quasirandom structures and cluster expansion. These methods are system-specific and computationally expensive as they rely on large scale Monte Carlo simulations of enlarged unit cells. To address these limitations, we propose a pipeline combining a permutation-based virtual cell generation algorithm, sampling regime, and thermodynamic post-processing which greatly improves the feasibility of computation analyses for site-disordered materials. We demonstrate that the massive configurational space can be adequately sampled with 400 virtual cells, as long as the supercell definition is sufficiently large.