Learning the bulk and interfacial physics of liquid-liquid phase separation with neural density functionals

TL;DR

This paper combines machine learning and classical density functional theory to accurately model phase coexistence and interfacial properties in binary liquid mixtures, providing insights into wetting behavior.

Contribution

It introduces a neural density functional approach that predicts phase diagrams and interfacial tensions with high accuracy for symmetrical Lennard-Jones mixtures.

Findings

Accurate liquid-liquid and vapor-liquid binodals predicted.

Interfacial tensions vary consistently across the phase diagram.

No wetting transition occurs in the symmetrical mixture.

Abstract

We use simulation-based supervised machine learning and classical density functional theory to investigate bulk and interfacial phenomena associated with phase coexistence in binary mixtures. For a prototypical symmetrical Lennard-Jones mixture our trained neural density functional yields accurate liquid-liquid and liquid-vapour binodals together with predictions for the variation of the associated interfacial tensions across the entire fluid phase diagram. From the latter we determine the contact angles at fluid-fluid interfaces along the line of triple-phase coexistence and confirm there can be no wetting transition in this symmetrical mixture.