A general classification scheme of detecting spatial and dynamical heterogeneities in super-cooled liquids

TL;DR

This paper introduces a machine learning-based classification scheme combining PCA and Gaussian Mixture clustering to identify and analyze nano-domain heterogeneities in supercooled liquids across structural and configurational spaces.

Contribution

The study develops a novel, general ML-driven method for detecting spatial and dynamical heterogeneities in supercooled liquids, applicable to various disordered systems.

Findings

Identification of nano-domains in supercooled liquids over long timescales

Consistent nano-domains observed across different system sizes

Method effectively links structural features to configurational space

Abstract

A computational approach via implementation of the Principle Component Analysis (PCA) and Gaussian Mixture (GM) clustering methods from Machine Learning (ML) algorithms to identify domain structures of supercooled liquids is developed. Raw features data are collected from the coordination numbers of particles smoothed using its radial distribution function and are used as an order-parameter of disordered structures for GM clustering after dimensionality reduction from the PCA. To transfer the knowledge from features(structural) space to configurational space, another GM clustering is performed using the Cartesian coordinates as an order-parameter with the particles' identity from GM in the feature space. Both GM clustering are performed iteratively until convergence. Results show the appearance of aggregated clusters of nano-domains over sufficient long timescale both in structural and configurational spaces with heterogeneous dynamics. More importantly, consistent nano-domains tilling up the whole space regardless of the system size are observed and our approach can be applied to any disordered systems.