Dimensionality reduction of local structure in glassy binary mixtures

TL;DR

This paper explores how unsupervised learning methods, like PCA and neural autoencoders, can effectively reduce the complexity of structural descriptors in glassy binary mixtures, revealing key features linked to particle mobility.

Contribution

It demonstrates that simple collective variables can capture most structural fluctuations and compares PCA with neural autoencoders, highlighting interpretability and effectiveness in glassy systems.

Findings

Few collective variables explain bulk structural fluctuations.

Bond-orientational descriptors relate to particle mobility.

PCA and neural autoencoders yield similar results.

Abstract

We consider unsupervised learning methods for characterizing the disordered microscopic structure of supercooled liquids and glasses. Specifically, we perform dimensionality reduction of smooth structural descriptors that describe radial and bond-orientational correlations, and assess the ability of the method to grasp the essential structural features of glassy binary mixtures. In several cases, a few collective variables account for the bulk of the structural fluctuations within the first coordination shell and also display a clear connection with the fluctuations of particle mobility. Fine-grained descriptors that characterize the radial dependence of bond-orientational order better capture the structural fluctuations relevant for particle mobility, but are also more difficult to parametrize and to interpret. We also find that principal component analysis of bond-orientational order parameters provides identical results to neural network autoencoders, while having the advantage of being easily interpretable. Overall, our results indicate that glassy binary mixtures have a broad spectrum of structural features. In the temperature range we investigate, some mixtures display well-defined locally favored structures, which are reflected in bimodal distributions of the structural variables identified by dimensionality reduction.