Inferring the Isotropic-nematic Phase Transition with Generative Machine Learning

TL;DR

This paper demonstrates that score-based generative machine learning models can effectively learn and infer the critical behavior of the isotropic-nematic phase transition in liquid crystals from limited simulation data.

Contribution

It introduces the use of Thermodynamic Maps, a score-based modeling approach, to describe complex phase transitions in liquid crystalline systems.

Findings

Successfully infers critical behavior from limited data

Estimates nematic order parameter across phase transition

Learns physics of anisotropic liquid crystalline phase transition

Abstract

Contemporary work implies generative machine learning models are capable of learning the phase behavior in condensed matter systems such as the Ising model. In this Letter, we utilize a score-based modeling procedure called Thermodynamic Maps to describe the isotropic-nematic phase transition in a melt of $N=343$ calamitic Gay-Berne ellipsoids. When trained on samples generated by molecular dynamics simulation from a single temperature on either side of the phase transition, we demonstrate this generative machine learning approach infers information regarding the critical behavior and estimates effectively the nematic order parameter at sampled temperatures between the two training temperatures. These results demonstrate score-based models' ability to learn the physics of a non-trivial liquid crystalline phase transition driven by anisotropic interactions both entropic and energetic in nature.