Prediction of transport property via machine learning molecular movements

TL;DR

This paper introduces a simple supervised machine learning approach combined with unsupervised representation to predict material transport properties, specifically viscosity, from molecular dynamics data, revealing molecular mechanisms behind viscosity variations.

Contribution

The study presents a novel, simplified ML framework that reduces data requirements and enhances interpretability in predicting transport properties from MD simulations.

Findings

Successfully predicted viscosity of lubricant molecules

Identified two molecular mechanisms affecting viscosity

Simplified model enhances understanding of molecular dynamics

Abstract

Molecular dynamics (MD) simulations are increasingly being combined with machine learning (ML) to predict material properties. The molecular configurations obtained from MD are represented by multiple features, such as thermodynamic properties, and are used as the ML input. However, to accurately find the input--output patterns, ML requires a sufficiently sized dataset that depends on the complexity of the ML model. Generating such a large dataset from MD simulations is not ideal because of their high computation cost. In this study, we present a simple supervised ML method to predict the transport properties of materials. To simplify the model, an unsupervised ML method obtains an efficient representation of molecular movements. This method was applied to predict the viscosity of lubricant molecules in confinement with shear flow. Furthermore, simplicity facilitates the interpretation of the model to understand the molecular mechanics of viscosity. We revealed two types of molecular mechanisms that contribute to low viscosity.