Prediction of transport property via machine learning molecular movements
This work addresses the problem of expensive data generation for material property prediction, offering an incremental improvement for researchers in computational materials science.
The authors tackled the high computational cost of generating large molecular dynamics datasets for machine learning by developing a simple supervised method that uses an unsupervised representation of molecular movements to predict transport properties, specifically achieving predictions of lubricant viscosity in confinement with shear flow and identifying two molecular mechanisms for low viscosity.
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.