Machine-learning predictions of polymer properties with Polymer Genome

Summary Modern data-driven tools are transforming application-specific polymer development cycles. Surrogate models that can be trained to predict properties of polymers are becoming commonplace. Nevertheless, these models do not utilize the full breadth of the knowledge available in datasets, which are oftentimes sparse; inherent correlations between different property datasets are disregarded. Here, we demonstrate the potency of multi-task learning approaches that exploit such inherent correlations effectively. Data pertaining to 36 different properties of over 13,000 polymers are supplied to deep-learning multi-task architectures. Compared to conventional single-task learning models, the multi-task approach is accurate, efficient, scalable, and amenable to transfer learning as more data on the same or different properties become available. Moreover, these models are interpretable. Chemical rules, that explain how certain features control trends in property values, emerge from the present work, paving the way for the rational design of application specific polymers meeting desired property or performance objectives.

show abstract

“…The field of polymer science and engineering is thus poised for exciting informatics-based inquiry and discovery. 1 , 2 , 3 , 4 , 5 …”

Section: Introductionmentioning

confidence: 99%

Polymer informatics with multi-task learning

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…They fitted their datasets of 451–1,321 polymers with the Gaussian process regression model in the polymer genome platform. 38 , 45 , 46 , 47 , 48 When using 1,321 polymers for training, their ML model reported a root-mean-square error of 27 K and

of 0.92. 39 In addition to molecular descriptors as feature representation, ML models, such as convolutional neural networks (CNNs) with image-based input, have also been examined.…”

Section: Introductionmentioning

confidence: 99%

Machine learning discovery of high-temperature polymers

Tao

Chen

2021

Patterns

View full text Add to dashboard Cite

Summary To formulate a machine learning (ML) model to establish the polymer's structure-property correlation for glass transition temperature , we collect a diverse set of nearly 13,000 real homopolymers from the largest polymer database, PoLyInfo. We train the deep neural network (DNN) model with 6,923 experimental values using Morgan fingerprint representations of chemical structures for these polymers. Interestingly, the trained DNN model can reasonably predict the unknown values of polymers with distinct molecular structures, in comparison with molecular dynamics simulations and experimental results. With the validated transferability and generalization ability, the ML model is utilized for high-throughput screening of nearly one million hypothetical polymers. We identify more than 65,000 promising candidates with > 200°C, which is 30 times more than existing known high-temperature polymers (∼2,000 from PoLyInfo). The discovery of this large number of promising candidates will be of significant interest in the development and design of high-temperature polymers.

show abstract

“…The emerging machine learning (ML) technique trained on massive amounts of data establishes linkages between input fingerprints and output properties, which provides a powerful surrogate model for the structure-property linkage analysis [15][16][17][18][19]. Further, inverse design methods such as evolution searching (ES) strategies and generative models can be employed to explore the large space of potential materials, greatly accelerating the discovery and development of new polymers [20,21].…”

Section: Introductionmentioning

confidence: 99%

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

Zhu

Deng

Lei

et al. 2021

IET Nanodielectrics

View full text Add to dashboard Cite

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.

show abstract

Machine-learning predictions of polymer properties with Polymer Genome

Cited by 146 publications

References 59 publications

Polymer informatics with multi-task learning

Polymer informatics with multi-task learning

Machine learning discovery of high-temperature polymers

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

Contact Info

Product

Resources

About