Review of machine learning‐driven design of polymer‐based dielectrics

Abstract

Polymer-based dielectrics are extensively applied in various electrical and electronic devices such as capacitors, power transmission cables and microchips, in which a variety of distinct performances such as the dielectric and thermal properties are desired. To fulfil these properties, the emerging machine learning (ML) technique has been used to establish a surrogate model for the structure-property linkage analysis, which provides an effective tool for the rational design of the chemical and morphological structure of polymers/nanocomposites. In this article, the authors reviewed the recent progress in the ML algorithms and their applications in the rational design of polymer-based dielectrics. The main routes for collecting training data including online libraries, experiments and high-throughput computations are first summarized. The fingerprints charactering the microstructures of polymers/nanocomposites are presented, followed by the illustration of ML models to establish a mapping between the fingerprinted input and the target properties. Further, inverse design methods such as evolution searching strategies and generative models are described, which are exploited to accelerate the discovery of new polymer-based dielectrics. Moreover, structure-property linkage analysis techniques such as Pearson correlation calculation, decision-tree-based methods and interpretable neural networks are summarized to identify the key features affecting the target properties. The future development prospects of the ML-driven design method for polymer-based dielectrics are also presented in this review. K E Y W O R D S fingerprinting, inverse design, machine learning, polymer-based dielectrics, structure-property linkage analysisThis is an open access article under the terms of the Creative Commons Attribution-NonCommercial License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.

Inverse Design of Materials by Machine Learning

“…Several ML algorithms are commonly used in these calculations, such as linear regression, GPR, ANN, RF, deep neural network, etc. [ 60 ] Mannodi-Kanakkithodi et al [ 61 ] addressed the polymer dielectric design by ML-based genome approach for optimization of polymer constituent blocks, where they fingerprinted polymers into easily attainable numerical representations in prior. Their method accelerates the discovery of on-demand polymers with desired dielectric constant.…”

The Rise of Machine Learning in Polymer Discovery

“…A number of review papers have been published recently on this important area of study. [16][17][18][19][20][21][22][23][24][25][26][27] The focus of this article is to provide new insight on ML-assisted polymer discovery, including crosslinked polymer networks. The aim of this review is to provide an insight for researchers who are already in this field and for researchers who are stepping into this field.…”

“…A number of review papers have been published recently on this important area of study. [ 16–27 ] The focus of this article is to provide new insight on ML‐assisted polymer discovery, including crosslinked polymer networks.…”

nanoNET: machine learning platform for predicting nanoparticles distribution in a polymer matrix

“…Recently, machine learning has shown tremendous success in solving a wide range of materials problems, such as the identification of the local structure of metallic NPs on an oxide-support and defective graphene sheets; 25 the automated recognition of metal NPs deposited on pyrolytic graphite; 26 atomic structure classification and prediction; [27][28][29] nanostructure identification from X-ray, SEM (scanning electron microscopy), TEM (transmission electron microscopy), and SAS (small-angle scattering); [30][31][32][33][34] and classification and prediction of sequence-defined morphologies of copolymers. [35][36][37] Machine learning methods have also been used recently to predict the properties of PNCs, [38][39][40][41] such as their dielectric constant, rubbery modulus, and glassy modulus. However, developing a machine learning workflow that predicts the long-range spatial correlation of NPs based on the composition of a PNC remains elusive.…”

“…In machine learning literature, the encoding of data is commonly known as feature learning. 39,[42][43][44][45] In this process, unique characteristics are extracted from the data to represent it in a lower-dimension continuous space representation. In the context of materials design and structure-property modeling, several feature-learning techniques are used to represent the vast chemical space of molecules in machine-readable numerical form.…”