Polymers for Extreme Conditions Designed Using Syntax-Directed Variational Autoencoders

The design/discovery of new materials is highly non-trivial owing to the near-infinite possibilities of material candidates, and multiple required property/performance objectives. Thus, machine learning tools are now commonly employed to virtually screen material candidates with desired properties by learning a theoretical mapping from material-to-property space, referred to as the \emph{forward} problem. However, this approach is inefficient, and severely constrained by the candidates that human imagination can conceive. Thus, in this work on polymers, we tackle the materials discovery challenge by solving the \emph{inverse} problem: directly generating candidates that satisfy desired property/performance objectives. We utilize syntax-directed variational autoencoders (VAE) in tandem with Gaussian process regression (GPR) models to discover polymers expected to be robust under three extreme conditions: (1) high temperatures, (2) high electric field, and (3) high temperature \emph{and} high electric field, useful for critical structural, electrical and energy storage applications. This approach to learn from (and augment) human ingenuity is general, and can be extended to discover polymers with other targeted properties and performance measures.

[1]  Pushmeet Kohli,et al.  Learning Continuous Semantic Representations of Symbolic Expressions , 2016, ICML.

[2]  Ola Engkvist,et al.  Direct steering of de novo molecular generation with descriptor conditional recurrent neural networks , 2020, Nature Machine Intelligence.

[3]  S. Greenbaum,et al.  Polymer Capacitor Dielectrics for High Temperature Applications. , 2018, ACS applied materials & interfaces.

[4]  Rampi Ramprasad,et al.  Machine learning models for the lattice thermal conductivity prediction of inorganic materials , 2019, Computational Materials Science.

[5]  Steven Skiena,et al.  Syntax-Directed Variational Autoencoder for Structured Data , 2018, ICLR.

[6]  Rampi Ramprasad,et al.  Flexible Temperature‐Invariant Polymer Dielectrics with Large Bandgap , 2020, Advanced materials.

[7]  Qi Liu,et al.  Constrained Graph Variational Autoencoders for Molecule Design , 2018, NeurIPS.

[8]  R. Batra,et al.  Physically informed artificial neural networks for atomistic modeling of materials , 2018, Nature Communications.

[9]  Michael F. Crowley,et al.  Message-passing neural networks for high-throughput polymer screening , 2018, The Journal of chemical physics.

[10]  Chiho Kim,et al.  From Organized High-Throughput Data to Phenomenological Theory using Machine Learning: The Example of Dielectric Breakdown , 2016 .

[11]  Rampi Ramprasad,et al.  Computable Bulk and Interfacial Electronic Structure Features as Proxies for Dielectric Breakdown of Polymers. , 2020, ACS applied materials & interfaces.

[12]  Lei Cheng,et al.  Accelerating Electrolyte Discovery for Energy Storage with High-Throughput Screening. , 2015, The journal of physical chemistry letters.

[13]  Anand Chandrasekaran,et al.  Solving the electronic structure problem with machine learning , 2019, npj Computational Materials.

[14]  Jure Leskovec,et al.  Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation , 2018, NeurIPS.

[15]  Lili Zhang,et al.  High-Temperature Capacitor Polymer Films , 2014, Journal of Electronic Materials.

[16]  Rampi Ramprasad,et al.  A universal strategy for the creation of machine learning-based atomistic force fields , 2017, npj Computational Materials.

[17]  Al Stevens,et al.  C programming , 1990 .

[18]  Jihan Kim,et al.  Inverse design of porous materials using artificial neural networks , 2020, Science Advances.

[19]  Bjarne Stroustrup,et al.  C++ Programming Language , 1986, IEEE Softw..

[20]  Chiho Kim,et al.  Electrochemical Stability Window of Polymeric Electrolytes , 2019, Chemistry of Materials.

[21]  Matt J. Kusner,et al.  Grammar Variational Autoencoder , 2017, ICML.

[22]  Nicola De Cao,et al.  MolGAN: An implicit generative model for small molecular graphs , 2018, ArXiv.

[23]  R. Batra,et al.  Polymer design using genetic algorithm and machine learning , 2021, Computational Materials Science.

[24]  Anand Chandrasekaran,et al.  Polymer Genome: A Data-Powered Polymer Informatics Platform for Property Predictions , 2018, The Journal of Physical Chemistry C.

[25]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[26]  Alán Aspuru-Guzik,et al.  Design Principles and Top Non-Fullerene Acceptor Candidates for Organic Photovoltaics , 2017 .

[27]  A. McCallum,et al.  Materials Synthesis Insights from Scientific Literature via Text Extraction and Machine Learning , 2017 .

[28]  Connor W. Coley,et al.  BigSMILES: A Structurally-Based Line Notation for Describing Macromolecules , 2019, ACS central science.

[29]  Feng Lin,et al.  Machine Learning Directed Search for Ultraincompressible, Superhard Materials. , 2018, Journal of the American Chemical Society.

[30]  Chiho Kim,et al.  Active-learning and materials design: the example of high glass transition temperature polymers , 2019, MRS Communications.

[31]  Mikkel N. Schmidt,et al.  Machine learning-based screening of complex molecules for polymer solar cells. , 2018, The Journal of chemical physics.

[32]  Chiho Kim,et al.  Iterative-Learning Strategy for the Development of Application-Specific Atomistic Force Fields , 2019, The Journal of Physical Chemistry C.

[33]  Regina Barzilay,et al.  Junction Tree Variational Autoencoder for Molecular Graph Generation , 2018, ICML.

[34]  Pascal Friederich,et al.  Self-referencing embedded strings (SELFIES): A 100% robust molecular string representation , 2019, Mach. Learn. Sci. Technol..

[35]  Alán Aspuru-Guzik,et al.  Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules , 2016, ACS central science.

[36]  B. Uberuaga,et al.  Physics-informed machine learning for inorganic scintillator discovery. , 2018, The Journal of chemical physics.

[37]  Nando de Freitas,et al.  Taking the Human Out of the Loop: A Review of Bayesian Optimization , 2016, Proceedings of the IEEE.

[38]  Alok Choudhary,et al.  Combinatorial screening for new materials in unconstrained composition space with machine learning , 2014 .

[39]  Li Li,et al.  Optimization of Molecules via Deep Reinforcement Learning , 2018, Scientific Reports.

[40]  Alán Aspuru-Guzik,et al.  Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models , 2017, ArXiv.

[41]  Aron Walsh,et al.  Inorganic materials: The quest for new functionality. , 2015, Nature chemistry.

[42]  Jeffrey D. Ullman,et al.  Introduction to Automata Theory, Languages and Computation , 1979 .

[43]  Christopher Wolverton,et al.  Accelerated discovery of metallic glasses through iteration of machine learning and high-throughput experiments , 2018, Science Advances.

[44]  James Theiler,et al.  Accelerated search for materials with targeted properties by adaptive design , 2016, Nature Communications.

[45]  Rong Zeng,et al.  A Scalable, High‐Throughput, and Environmentally Benign Approach to Polymer Dielectrics Exhibiting Significantly Improved Capacitive Performance at High Temperatures , 2018, Advanced materials.

[46]  Tong-Yi Zhang,et al.  Data-driven discovery of formulas by symbolic regression , 2019, MRS Bulletin.

[47]  Sergei V. Kalinin,et al.  Materials science in the artificial intelligence age: high-throughput library generation, machine learning, and a pathway from correlations to the underpinning physics , 2019, MRS communications.

[48]  G. Hutchison,et al.  Efficient Computational Screening of Organic Polymer Photovoltaics. , 2013, The journal of physical chemistry letters.

[49]  Regina Barzilay,et al.  Hierarchical Generation of Molecular Graphs using Structural Motifs , 2020, ICML.

[50]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[51]  Olga Kononova,et al.  Unsupervised word embeddings capture latent knowledge from materials science literature , 2019, Nature.

[52]  Ken E. Whelan,et al.  The Automation of Science , 2009, Science.

[53]  Corey Oses,et al.  Machine learning modeling of superconducting critical temperature , 2017, npj Computational Materials.

[54]  Arun Mannodi-Kanakkithodi,et al.  Scoping the polymer genome: A roadmap for rational polymer dielectrics design and beyond , 2017, Materials Today.