English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Molecular dynamics (MD) simulations are increasingly being combined withmachine learning (ML) to predict material properties. The molecularconfigurations obtained from MD are represented by multiple features, such asthermodynamic properties, and are used as the ML input. However, to accuratelyfind the input--output patterns, ML requires a sufficiently sized dataset thatdepends on the complexity of the ML model. Generating such a large dataset fromMD simulations is not ideal because of their high computation cost. In thisstudy, we present a simple supervised ML method to predict the transportproperties of materials. To simplify the model, an unsupervised ML methodobtains an efficient representation of molecular movements. This method wasapplied to predict the viscosity of lubricant molecules in confinement withshear flow. Furthermore, simplicity facilitates the interpretation of the modelto understand the molecular mechanics of viscosity. We revealed two types ofmolecular mechanisms that contribute to low viscosity.

Prediction of transport property via machine learning molecular movements