Accelerated Discovery of Dielectric Polymer Materials Using Graph Convolutional Neural Networks

ORAL

Abstract

Polynorbornene (PNB) is an important amorphous polymer system, which has potential applications as a high energy density polymer due to its high breakdown strength with low dielectric loss and high thermal stability. Moreover, electrical properties of PNB can be significantly enhanced by incorporation of defects or synthesis with controlled crystallinity by hydrogenation reaction. However, this process is challenging since it involves experimental synthesis and characterization of combinatorial large number of polymer systems to identify potential candidates. Here, we propose a deep learning-based graph convolutional neural network (GNN) model that can identify polymer systems capable of exhibiting increased energy and power density. The GNN model is trained to predict dielectric constant for a polymer, where the training data for the high frequency dielectric constant of the PNB polymers are computed via ab-initio molecular dynamics simulation. Our model can significantly aid experimental synthesis of potentially new dielectric polymer materials which is otherwise difficult using simplistic statistical procedures.

*This work was supported by the Office of Naval Research through a Multi-University Research Initiative (MURI) under grant number (N00014-17-1-2656).

–

Presenters

  • Ankit Mishra

    • Mork Family Department of Chemical Engineering and Materials Science, University of Southern California

Authors

  • Ankit Mishra

    • Mork Family Department of Chemical Engineering and Materials Science, University of Southern California

  • Pankaj Rajak

    • Argonne National Lab
    • LCF, Argonne National Laboratory

  • Ekin Dogus Cubuk

    • Google
    • Google Inc.
    • Google Inc
    • Google Brain

  • Ken-ichi Nomura

    • Mork Family Department of Chemical Engineering and Materials Science, University of Southern California
    • University of Southern California
    • Univ of Southern California

  • Rajiv Kalia

    • Mork Family Department of Chemical Engineering and Materials Science, University of Southern California
    • Univ of Southern California
    • Collaboratory for Advanced Computing and Simulations, University of Southern California

  • Aiichiro Nakano

    • Mork Family Department of Chemical Engineering and Materials Science, University of Southern California
    • Univ of Southern California
    • Collaboratory for Advanced Computing and Simulations, University of Southern California

  • Ajinkya Deshmukh

    • Department of Chemistry, University of Connecticut, Storrs

  • Lihua Chen

    • Department of Material Science and Technology, Georgia Tech
    • Materials Science and Engineering, Georgia Institute of Technology

  • Greg Sotzing

    • Department of Chemistry, University of Connecticut, Storrs

  • Yang Cao

    • Department of Electrical Engineering, University of Connecticut, Storrs

  • Ramamurthy Ramprasad

    • Georgia Institute of Technology
    • School of Materials Science and Engineering, Georgia Institute of Technology
    • Department of Material Science and Technology, Georgia Tech
    • Materials Science and Engineering, Georgia Institute of Technology

  • Priya Vashishta

    • Mork Family Department of Chemical Engineering and Materials Science, University of Southern California
    • Univ of Southern California
    • University of Southern California
    • Collaboratory for Advanced Computing and Simulations, University of Southern California