Machine learning of the architecture-property relationship in graft polymers.

Journal: Physical chemistry chemical physics : PCCP
Published Date: Jun 25, 2025

Abstract

Graft polymers are promising in energy and biomedical applications. However, the diverse architectures make it challenging to establish their structure-property relationships. We systematically investigate how backbone and side-chain architectures influence four key properties: glass transition temperature (), self-diffusion coefficient (), radius of gyration (), and packing density (). Using molecular dynamics simulations, we analyze a dataset of 500 graft polymers with randomly positioned side chains. and exhibit decoupled relationships due to the distinct topological effects. Furthermore, we develop dense neural networks (DNNs) and convolutional neural networks (CNNs) to pave the way to polymer design with desired properties.

Authors

  • Kevin V Bigting
    Department of Computer Science and Engineering, Louisiana State University, Baton Rouge, LA 70803, USA.
  • Jordan J Carden
    Department of Computer Science and Engineering, Louisiana State University, Baton Rouge, LA 70803, USA.
  • Shubhadeep Nag
    Department of Chemical Engineering, Louisiana State University, Baton Rouge, LA 70803, USA.
  • Jimmy Lawrence
    Department of Chemical Engineering, Louisiana State University, Baton Rouge, LA 70803, USA.
  • Yen-Fang Su
    Department of Civil and Environmental Engineering, Louisiana State University, Baton Rouge, LA 70803, USA.
  • Yaxin An
    Department of Chemical Engineering, Louisiana State University, Baton Rouge, LA 70803, USA.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals