Neural network based order parameter for phase transitions and its applications in high-entropy alloys

TL;DR

This paper introduces a novel 'VAE order parameter' derived from variational autoencoders' latent space to identify phase transitions, specifically in high-entropy alloys, enabling better materials design and understanding of chemical ordering.

Contribution

It proposes the Manhattan distance in VAE latent space as a universal order parameter for phase transitions, with applications to high-entropy alloys.

Findings

VAE order parameter effectively characterizes phase transitions.

Physical interpretation of the order parameter in alloy systems.

Facilitates alloy design by mimicking natural element mixing.

Abstract

Phase transition is one of the most important phenomena in nature and plays a central role in materials design. All phase transitions are characterized by suitable order parameters, including the order-disorder phase transition. However, finding a representative order parameter for complex systems is nontrivial, such as for high-entropy alloys. Given variational autoencoder's (VAE) strength of reducing high dimensional data into few principal components, here we coin a new concept of "VAE order parameter". We propose that the Manhattan distance in the VAE latent space can serve as a generic order parameter for order-disorder phase transitions. The physical properties of the order parameter are quantitatively interpreted and demonstrated by multiple refractory high-entropy alloys. Assisted by it, a generally applicable alloy design concept is proposed by mimicking the nature mixing of elements. Our physically interpretable "VAE order parameter" lays the foundation for the understanding of and alloy design by chemical ordering.