Selecting Relevant Structural Features for Glassy Dynamics by Information Imbalance

TL;DR

This paper uses an information imbalance method to identify structural features that predict dynamical heterogeneity in glass-forming liquids, enhancing understanding of glassy slow dynamics.

Contribution

It introduces a novel feature selection approach combining supervised and unsupervised methods to predict glassy dynamics.

Findings

Selected features improve prediction accuracy of future dynamics.

The method identifies key structural descriptors influencing dynamics.

Potential to uncover mechanisms behind glassy slow dynamics.

Abstract

We investigate numerically the identification of relevant structural features that contribute to the dynamical heterogeneity in a model glass-forming liquid. By employing the recently proposed information imbalance technique, we select these features from a range of physically motivated descriptors. This selection process is performed in a supervised manner (using both dynamical and structural data) and an unsupervised manner (using only structural data). We then apply the selected features to predict future dynamics using a machine learning technique. Finally, we discuss the potential applications of this approach in identifying the dominant mechanisms governing the glassy slow dynamics.