Supervised and Unsupervised Machine Learning of Structural Phases of Polymers Adsorbed to Nanowires

TL;DR

This paper uses machine learning techniques to identify and characterize structural phases and transitions in polymer-nanowire composites, removing human bias and intuition from phase boundary detection.

Contribution

It demonstrates that neural networks and unsupervised methods can reliably recognize known phases and locate phase boundaries without prior assumptions.

Findings

Neural networks accurately identify all known configurational phases.

Unsupervised methods locate phase boundaries without human bias.

Machine learning approaches outperform traditional ad-hoc order parameters.

Abstract

We identify configurational phases and structural transitions in a polymer nanotube composite by means of machine learning. We employ various unsupervised dimensionality reduction methods, conventional neural networks, as well as the confusion method, an unsupervised neural-network-based approach. We find neural networks are able to reliably recognize all configurational phases that have been found previously in experiment and simulation. Furthermore, we locate the boundaries between configurational phases in a way that removes human intuition or bias. This could be done before only by relying on preconceived, ad-hoc order parameters.