Machine Learning Strategy for Accelerated Design of Polymer Dielectrics

TLDR

Designing advanced dielectric polymers is hindered by scarce, reliable data across polymer chemical spaces and the difficulty of generating such data within practical time and computational limits. The study seeks to accelerate polymer dielectric design by extracting machine‑learning models from accurate first‑principles calculations for polymers in a key chemical subspace. Polymers are represented by simple numerical fingerprints mapped to properties via machine learning, and a genetic algorithm evolves constituent blocks to produce polymers with desired target properties. The approach, demonstrated on polymer dielectrics, can be extended to other material classes.

Abstract

Abstract The ability to efficiently design new and advanced dielectric polymers is hampered by the lack of sufficient, reliable data on wide polymer chemical spaces and the difficulty of generating such data given time and computational/experimental constraints. Here, we address the issue of accelerating polymer dielectrics design by extracting learning models from data generated by accurate state-of-the-art first principles computations for polymers occupying an important part of the chemical subspace. The polymers are ‘fingerprinted’ as simple, easily attainable numerical representations, which are mapped to the properties of interest using a machine learning algorithm to develop an on-demand property prediction model. Further, a genetic algorithm is utilised to optimise polymer constituent blocks in an evolutionary manner, thus directly leading to the design of polymers with given target properties. While this philosophy of learning to make instant predictions and design is demonstrated here for the example of polymer dielectrics, it is equally applicable to other classes of materials as well.