Application of deep learning to inverse design of phase separation structure in polymer alloy

Abstract In this study, using some machine learning methods, we develop a framework that deals with forward analysis to predict a property from a polymer alloy’s phase separation structure and inverse design to generate the structure from the property. We only consider Young’s modulus as the property in this study. The forward analysis is performed using a convolutional neural network (CNN) and the inverse design is realized by a random search toward a model combining a generative adversarial network (GAN) and a CNN. This framework is applicable to other properties at a low computational cost, and latent variables belonging to the GAN are useful for feature extraction.

[1]  Wei Chen,et al.  Microstructural Materials Design Via Deep Adversarial Learning Methodology , 2018, Journal of Mechanical Design.

[2]  Yanchao Wang,et al.  Crystal structure prediction via particle-swarm optimization , 2010 .

[3]  Feng Cheng,et al.  Probabilistic Representation and Inverse Design of Metamaterials Based on a Deep Generative Model with Semi‐Supervised Learning Strategy , 2019, Advanced materials.

[4]  K. Tsuda,et al.  Hunting for Organic Molecules with Artificial Intelligence: Molecules Optimized for Desired Excitation Energies , 2018, ACS central science.

[5]  L. Hollaway.  A review of the present and future utilisation of FRP composites in the civil infrastructure with reference to their important in-service properties , 2010 .

[6]  Siqi Shi,et al.  The onset temperature (Tg) of AsxSe1−x glasses transition prediction: A comparison of topological and regression analysis methods , 2017 .

[7]  Koray Aydin,et al.  Inverse design of an ultra-compact broadband optical diode based on asymmetric spatial mode conversion , 2016, Scientific Reports.

[8]  Kris T. Delaney,et al.  Broadly Accessible Self-Consistent Field Theory for Block Polymer Materials Discovery , 2016 .

[9]  Kyu-Tae Lee,et al.  A Generative Model for Inverse Design of Metamaterials , 2018, Nano letters.

[10]  Schick,et al.  Stable and unstable phases of a diblock copolymer melt. , 1994, Physical review letters.

[11]  Grace X. Gu,et al.  Machine learning for composite materials , 2019, MRS Communications.

[12]  M. Matsen.  Self‐Consistent Field Theory and Its Applications , 2007 .

[13]  Yue Liu,et al.  Materials discovery and design using machine learning , 2017 .

[14]  Fei Zhao,et al.  Multifunctional Nanostructured Conductive Polymer Gels: Synthesis, Properties, and Applications. , 2017, Accounts of chemical research.

[15]  R. Kondor,et al.  On representing chemical environments , 2012, 1209.3140.

[16]  G. Fredrickson,et al.  COMBINATORIAL SCREENING OF COMPLEX BLOCK COPOLYMER ASSEMBLY WITH SELF-CONSISTENT FIELD THEORY , 1999 .

[17]  Bong Hoon Kim,et al.  Bimodal phase separated block copolymer/homopolymer blends self-assembly for hierarchical porous metal nanomesh electrodes. , 2017, Nanoscale.

[18]  Yue Liu,et al.  Machine learning assisted materials design and discovery for rechargeable batteries , 2020, Energy Storage Materials.

[19]  N. Kikuchi,et al.  Simulation of the multi-scale convergence in computational homogenization approaches , 2000 .

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

[21]  Siqi Shi,et al.  Multi-scale computation methods: Their applications in lithium-ion battery research and development , 2016 .

[22]  Akinori Yamanaka,et al.  Deep neural network approach to estimate biaxial stress-strain curves of sheet metals , 2020 .

[23]  L. Tjeng,et al.  Long-range interactions in the effective low-energy Hamiltonian of Sr2IrO4: A core-to-core resonant inelastic x-ray scattering study , 2016, 1612.00074.

[24]  M. Baenitz,et al.  Singlet ground state in the alternating spin- 12 chain compound NaVOAsO4 , 2018, Physical Review B.

[25]  S. Tung,et al.  Microdomain control in block copolymer-based supramolecular thin films through varying the grafting density of additives , 2011 .

[26]  H. Yokoyama.  Fabrication of Nanoporous and Nanofoamed Materials using Microphase Separation of Block Copolymers , 2013 .

[27]  Yue Liu,et al.  Multi‐Layer Feature Selection Incorporating Weighted Score‐Based Expert Knowledge toward Modeling Materials with Targeted Properties , 2020, Advanced Theory and Simulations.

[28]  T. Soen,et al.  Thermodynamic interpretation of domain structure in solvent-cast films of A–B type block copolymers of styrene and isoprene† , 1969 .

[29]  L. Leibler,et al.  Block copolymers in tomorrow's plastics , 2005, Nature materials.

[30]  Jung Hoon Han,et al.  Application of machine learning to two-dimensional Dzyaloshinskii-Moriya ferromagnets , 2018, Physical Review B.

[31]  Yue Liu,et al.  Predicting the onset temperature (Tg) of GexSe1-x glass transition: a feature selection based two-stage support vector regression method. , 2019, Science bulletin.

[32]  A. Hotta,et al.  Stress-strain behavior, elastic recovery, fracture points, and time-temperature superposition of an oot-possessing triblock copolymer , 2011 .

[33]  D. Hui,et al.  A short review on basalt fiber reinforced polymer composites , 2015 .

[34]  Chiho Kim,et al.  Machine learning in materials informatics: recent applications and prospects , 2017, npj Computational Materials.

[35]  Jeff Z Y Chen,et al.  Identifying polymer states by machine learning. , 2017, Physical review. E.

[36]  Kenji Yasuoka,et al.  Multi-Step Time Series Generator for Molecular Dynamics , 2018, AAAI.

[37]  Keisuke Takahashi,et al.  Creating Machine Learning-Driven Material Recipes Based on Crystal Structure. , 2019, The journal of physical chemistry letters.

[38]  Gaurav Vats,et al.  Mutual Insight on Ferroelectrics and Hybrid Halide Perovskites: A Platform for Future Multifunctional Energy Conversion , 2019, Advanced materials.

[39]  Yi Yang,et al.  Nanophotonic particle simulation and inverse design using artificial neural networks , 2018, Science Advances.

[40]  J. E. Gubernatis,et al.  Machine learning in materials design and discovery: Examples from the present and suggestions for the future , 2018, Physical Review Materials.

[41]  Léon Bottou,et al.  Wasserstein Generative Adversarial Networks , 2017, ICML.

[42]  Kevin P. Murphy,et al.  Machine learning - a probabilistic perspective , 2012, Adaptive computation and machine learning series.

[43]  Alán Aspuru-Guzik,et al.  Inverse molecular design using machine learning: Generative models for matter engineering , 2018, Science.

[44]  Hirokazu Hasegawa,et al.  Bicontinuous microdomain morphology of block copolymers. 1. Tetrapod-network structure of polystyrene-polyisoprene diblock polymers , 1987 .

[45]  S. Shi,et al.  Rationalizing the interphase stability of Li|doped-Li7La3Zr2O12via automated reaction screening and machine learning , 2019, Journal of Materials Chemistry A.

[46]  K. Müller,et al.  Fast and accurate modeling of molecular atomization energies with machine learning. , 2011, Physical review letters.

[47]  César F. Lima,et al.  Impaired socio-emotional processing in a developmental music disorder , 2016, Scientific Reports.

[48]  K. Loos,et al.  Block copolymer template-directed synthesis of well-ordered metallic nanostructures , 2013 .

[49]  Daniel W. Davies,et al.  Machine learning for molecular and materials science , 2018, Nature.

[50]  Aden Forrow,et al.  Inverse design of discrete mechanical metamaterials , 2019, Physical Review Materials.

[51]  S. Sakurai,et al.  Effects of microdomain structures on the molecular orientation of poly(styrene-block-butadiene-block-styrene) triblock copolymer , 1993 .

[52]  Atsuto Seko,et al.  Representation of compounds for machine-learning prediction of physical properties , 2016, 1611.08645.

[53]  Raymond Y. K. Lau,et al.  Least Squares Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[54]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[55]  David Pfau,et al.  Unrolled Generative Adversarial Networks , 2016, ICLR.

[56]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[57]  Yuichi Yoshida,et al.  Spectral Normalization for Generative Adversarial Networks , 2018, ICLR.

[58]  A. Hexemer,et al.  Conjugated block copolymer photovoltaics with near 3% efficiency through microphase separation. , 2013, Nano letters.

[59]  O. A. V. Lilienfeld,et al.  First principles view on chemical compound space: Gaining rigorous atomistic control of molecular properties , 2012, 1209.5033.

[60]  Alessandro Corbetta,et al.  Fluctuations around mean walking behaviors in diluted pedestrian flows. , 2016, Physical review. E.

[61]  R. Mezzenga,et al.  Phase behavior and temperature-responsive molecular filters based on self-assembly of polystyrene-block-poly(N-isopropylacrylamide)-block-polystyrene , 2007 .

[62]  Mike Preuss,et al.  Planning chemical syntheses with deep neural networks and symbolic AI , 2017, Nature.

[63]  V. Kouznetsova,et al.  Multi‐scale constitutive modelling of heterogeneous materials with a gradient‐enhanced computational homogenization scheme , 2002 .