Inferring the Physics of Structural Evolution of Multicomponent Polymers <italic style="font-style: italic">via</italic> Machine-Learning-Accelerated Method

Kai-Hua Zhang; Ying Jiang; Liang-Shun Zhang

doi:10.1007/s10118-023-2891-9

Your Location：

Home >

Browse articles >

Inferring the Physics of Structural Evolution of Multicomponent Polymers via Machine-Learning-Accelerated Method

RESEARCH ARTICLE | Updated：2023-08-24

- Inferring the Physics of Structural Evolution of Multicomponent Polymers via Machine-Learning-Accelerated Method
- Chinese Journal of Polymer Science Vol. 41, Issue 9, Pages: 1377-1385(2023)
- Affiliations：
  
  a.School of Chemistry, Center of Soft Matter Physics and Its Applications, Beihang University, Beijing 100191, China
  b.Shanghai Key Laboratory of Advanced Polymeric Materials, School of Materials Science and Engineering, East China University of Science and Technology, Shanghai 200237, China
- Author bio：
  
  yjiang@buaa.edu.cn (Y.J.)
  zhangls@ecust.edu.cn (L.S.Z.)
- Funds：
- DOI：10.1007/s10118-023-2891-9
  CLC：
- Received：22 September 2022，
  
  Revised：2022-10-13，
  
  Accepted：20 October 2022，
  
  Online First：29 December 2022，
  
  Published：01 September 2023
- Accepted：
Scan QR Code
Zhang, K. H.; Jiang, Y.; Zhang, L. S. Inferring the physics of structural evolution of multicomponent polymers via machine-learning-accelerated method. Chinese J. Polym. Sci. 2023, 41, 1377–1385

Kai-Hua Zhang, Ying Jiang, Liang-Shun Zhang. Inferring the Physics of Structural Evolution of Multicomponent Polymers via Machine-Learning-Accelerated Method[J]. Chinese Journal of Polymer Science, 2023, 41(9): 1377-1385. DOI: 10.1007/s10118-023-2891-9.
Zhang, K. H.; Jiang, Y.; Zhang, L. S. Inferring the physics of structural evolution of multicomponent polymers via machine-learning-accelerated method. Chinese J. Polym. Sci. 2023, 41, 1377–1385 DOI： 10.1007/s10118-023-2891-9.

Kai-Hua Zhang, Ying Jiang, Liang-Shun Zhang. Inferring the Physics of Structural Evolution of Multicomponent Polymers via Machine-Learning-Accelerated Method[J]. Chinese Journal of Polymer Science, 2023, 41(9): 1377-1385. DOI: 10.1007/s10118-023-2891-9. DOI：

摘要

A machine-learning-based method is developed to accelerate the predictions of structural evolution of multicomponent polymers. Importantly

the data-driven method can also infer the latent growth laws of phase-separated microstructures of multicomponent polymers without the prior knowledge of the governing dynamics.

Abstract

Dynamic self-consistent field theory (DSCFT) is a fruitful approach for modeling the structural evolution and collective kinetics for a wide variety of multicomponent polymers. However

solving a set of DSCFT equations remains daunting because of high computational demand. Herein

a machine learning method

integrating low-dimensional representations of microstructures and long short-term memory neural networks

is used to accelerate the predictions of structural evolution of multicomponent polymers. It is definitively demonstrated that the neural-network-trained surrogate model has the capability to accurately forecast the structural evolution of homopolymer blends as well as diblock copolymers

without the requirement of “on-the-fly” solution of DSCFT equations. Importantly

the data-driven method can also infer the latent growth laws of phase-separated microstructures of multicomponent polymers through simply using a few of time sequences from their past

without the prior knowledge of the governing dynamics. Our study exemplifies how the machine-learning-accelerated method can be applied to understand and discover the physics of structural evolution in the complex polymer systems.

关键词

Keywords

references

Thurn-Albrecht,T.;Schotter,J.;Kastle,C.A.;Emley,N.;Shibauchi,T.;Krusin-Elbaum,L.;Guarini,K.;Black,C.T.;Tuominen,M.T.;Russell,T.P.Ultrahigh-densitynanowirearraysgrowninself-assembleddiblockcopolymertemplates. Science 2000 , 290 ,2126−2129..

Meuler,A.J.;Hillmyer,M.A.;Bates,F.S.Orderednetworkmesostructuresinblockpolymermaterials. Macromolecules 2009 , 42 ,7221−7250..

Müller,M.;Abetz,V.Nonequilibriumprocessesinpolymermembraneformation:theoryandexperiment. Chem. Rev. 2021 , 121 ,14189−14231..

Huang,C.H.;Zhu,Y.Y.;Man,X.K.Blockcopolymerthinfilms. Phys. Rep. 2021 , 932 ,1−36..

Fraaije,J.G.E.M.;vanVlimmeren,B.A.C.;Maurits,N.M.;Postma,M.;Evers,O.A.;Hoffmann,C.;Altevogt,P.;Goldbeck-Wood,G.Thedynamicmean-fielddensityfunctionalmethodanditsapplicationtothemesoscopicdynamicsofquenchedblockcopolymermelts. J. Chem. Phys. 1997 , 106 ,4260−4269..

Morita,H.;Kawakatsu,T.;Doi,M.Dynamicdensityfunctionalstudyonthestructureofthinpolymerblendfilmswithafreesurface. Macromolecules 2001 , 34 ,8777–8783..

Müller,M.;Schmid,F.Incorporatingfluctuationsanddynamicsinself-consistentfieldtheoriesforpolymerblends. Adv. Polym. Sci. 2005 , 185 ,1−58..

Wang,G.;Ren,Y.;Müller,M.Collectiveshort-timedynamicsinmulticomponentpolymermelts. Macromolecules 2019 , 52 ,7704−7720..

Sides,S.W.;Fredrickson,G.H.Parallelalgorithmfornumericalself-consistentfieldtheorysimulationsofblockcopolymerstructure. Polymer 2003 , 44 ,5859−5866..

Hall,D.M.;Lookman,T.;Fredrickson,G.H.;Banerjee,S.Hydrodynamicself-consistentfieldtheoryforinhomogeneouspolymermelts. Phys. Rev. Lett. 2006 , 97 ,114501..

Zhang,L.;Sevink,A.;Schmid,F.HybridlatticeBoltzmann/dynamicself-consistentfieldsimulationsofmicrophaseseparationandvesicleformationinblockcopolymersystems. Macromolecules 2011 , 44 ,9434−9447..

Arora,A.;Qin,J.;Morse,D.C.;Delaney,K.T.;Fredrickson,G.H.;Bates,F.S.;Dorfman,K.D.Broadlyaccessibleself-consistentfieldtheoryforblockpolymermaterialsdiscovery. Macromolecules 2016 , 49 ,4675−4690..

Mehta,P.;Wang,C.-H.;Day,A.G.R.;Richardson,C.;Bukov,M.;Fisher,C.K.;Schwab,D.J.Ahigh-bias,low-varianceintroductiontomachinelearningforphysicists. Phys. Rep. 2019 , 810 ,1−124..

Carleo,G.;Cirac,I.;Cranmer,K.;Daudet,L.;Schuld,M.;Tishby,N.;Vogt-Maranto,L.;Zdeborová,L.Machinelearningandthephysicalsciences. Rev. Mod. Phys. 2019 , 91 ,045002..

Brunton,S.L.;Noack,B.R.;Koumoutsakos,P.Machinelearningforfluidmechanics. Annu. Rev. Fluid Mech. 2020 , 52 ,477−508..

Keith,J.A.;Vassilev-Galindo,V.;Cheng,B.;Chmiela,S.;Gastegger,M.;Müller,K.R.;Tkatchenko,A.Combiningmachinelearningandcomputationalchemistryforpredictiveinsightsintochemicalsystems. Chem. Rev. 2021 , 121 ,9816−9872..

Colen,J.;Han,M.;Zhang,R.;Redford,S.A.;Lemma,L.M.;Morgan,L.;Ruijgrok,P.V.;Adkins,R.;Bryant,Z.;Dogic,Z.;Gardel,M.L.;dePablo,J.J.;Vitelli,V.Machinelearningactive-nematichydrodynamics. Proc. Natl. Acad. Sci. U. S. A. 2021 , 118 ,e2016708118..

Li,H.;Jin,Y.;Jiang,Y.;Chen,J.Z.Y.DeterminingthenonequilibriumcriticalityofaGardnertransition via ahybridstudyofmolecularsimulationsandmachinelearning. Proc. Natl. Acad. Sci. U. S. A. 2021 , 118 ,e2017392118..

LeCun,Y.;Bengio,Y.;Hinton,G.Deeplearning. Nature 2017 , 521 ,436−444..

Carrasquilla,J.;Melko,R.G.Machinelearningphasesofmatter. Nat. Phys. 2017 , 13 ,431−434..

Bapst,V.;Keck,T.;Grabska-Barwińska,A.;Donner,C.;Cubuk,E.D.;Schoenholz,S.S.;Obika,A.;Nelson,A.W.R.;Back,T.;Hassabis,D.;Kohli,P.Unveilingthepredictivepowerofstaticstructureinglassysystems. Nat. Phys. 2020 , 16 ,448−454..

Zhao,S.;Cai,T.;Zhang,L.;Li,W.;Lin,J.Autonomousconstructionofphasediagramsofblockcopolymersbytheory-assistedactivemachinelearning. ACS Macro Lett. 2021 , 10 ,598−602..

Coli,G.M.;Boattini,E.;Filion,L.;Dijkstra,M.Inversedesignofsoftmaterials via adeeplearning-basedevolutionarystrategy. Sci Adv. 2022 , 8 ,eabj6731..

Aoyagi,T.Deeplearningmodelforpredictingphasediagramsofblockcopolymers. Comput. Mater. Sci. 2021 , 188 ,110224..

Tu,K.;Huang,H.;Lee,S.;Lee,W.;Sun,Z.;Alexander-Katz,A.;Ross,C.A.Machinelearningpredictionsofblockcopolymerself-assembly. Adv. Mater. 2020 , 32 ,2005713..

Schneider,L.;dePablo,J.J.Combiningparticle-basedsimulationsandmachinelearningtounderstanddefectkineticsinthinfilmsofsymmetricdiblockcopolymers. Macromolecules 2021 , 54 ,10074−10085..

Pathak,J.;Hunt,B.;Girvan,M.;Lu,Z.;Ott,E.Model-freepredictionoflargespatiotemporallychaoticsystemsfromdata:areservoircomputingapproach. Phys. Rev. Lett. 2018 , 120 ,024102..

Raissi,M.;Perdikaris,P.;Karniadakis,G.E.Physics-informedneuralnetworks:adeeplearningframeworkforsolvingforwardandinverseproblemsinvolvingnonlinearpartialdifferentialequations. J. Comput. Phys. 2019 , 378 ,686−707..

Zhao,H.;Storey,B.D.;Braatz,R.D.;Bazant,M.Z.Learningthephysicsofpatternformationfromimages. Phys. Rev. Lett. 2020 , 124 ,060201..

Bar-Sinai,Y.;Hoyer,S.;Hickey,J.;Brenner,M.P.Learningdata-drivendiscretizationsforpartialdifferentialequations. Proc. Natl. Acad. Sci. U. S. A. 2019 , 116 ,15344−15348..

Kemeth,F.P.;Bertalan,T.;Thiem,T.;Dietrich,F.;Moon,S.J.;Laing,C.R.;Kevrekidis,I.G.Learningemergentpartialdifferentialequationsinalearnedemergentspace. Nat. Commun. 2022 , 13 ,3318..

Vlachas,P.R.;ByeonW.;Wan,Z.Y.;Sapsis,T.P.;Koumoutsakos,P.Data-drivenforecastingofhigh-dimensionalchaoticsystemswithlongshort-termmemorynetworks. Proc. R. Soc. A 2018 , 474 ,20170844..

Vlachas,P.R.;Arampatzis,G.;Uhler,C.;Koumoutsakos,P.Multiscalesimulationsofcomplexsystemsbylearningtheireffectivedynamics. Nat. Machine Intelligence 2022 , 4 ,359−366..

MontesdeOcaZapiain,D.,Stewart,J.A.;Dingreville,R.Acceleratingphase-field-basedmicrostructureevolutionpredictionsviasurrogatemodelstrainedbymachinelearningmethods. NPJ Comput. Mater. 2021 , 7 ,1−11..

Hu,C.;Martin,S.;Dingreville,R.Acceleratingphase-fieldpredictions via recurrentneuralnetworkslearningthemicrostructureevolutioninlatentspace. Comput. Methods Appl. Mech. Engrg. 2022 , 397 ,115128..

Qi,S.;Schmid,F.Dynamicdensityfunctionaltheoriesforinhomogeneouspolymersystemscomparedtobrowniandynamicssimulations. Macromolecules 2017 , 50 ,9831−9845..

Pearson,K.Onlinesandplanesofclosestfittosystemsofpointsinspace. Philos. Mag. 1901 , 2 ,559−572..

Jolliffe,I.T. Principal Component Analysis ;Wiley:Chichester,U.K., 2002 ..

Hochreiter,S.;Schmidhuber,J.Longshort-termmemory. Neural Comput. 1997 , 9 ,1735−1780..

Greff,K.;Srivastava,R.K.;Koutnik,J.;Steunebrink,B.R.;Schmidhuber,J.LSTM:asearchspaceodyssey. IEEE Trans. Neural Netw. Learn. Syst. 2017 , 28 ,2222−2232..

Cho,K.;VanMerriënboer,B.;Bahdanau,D.;Bengio,Y.Onthepropertiesofneuralmachinetranslation:encoder-decoderapproaches. 2014 ,arXivpreprintarXiv:1409.1259.

Cho,K.;VanMerriënboer,B.;Gulcehre,C.;Bahdanau,D.;Bougares,F.;Schwenk,H.;Bengio,Y.LearningphraserepresentationsusingRNNencoder-decoderforstatisticalmachinetranslation. 2014 ,arXivpreprintarXiv:1406.1078.

Bray,A.J.Theoryofphase-orderingkinetics. Adv. Phys. 1994 , 43 ,357−459..

Sung,L.;Karim,A.;Douglas,J.F.;Han,C.C.Dimensionalcrossoverinthephaseseparationkineticsofthinpolymerblendfilms. Phys. Rev. Lett. 1996 , 76 ,4368..

Siggia,E.D.Latestagesofspinodaldecompositioninbinarymixtures. Phys. Rev. A: At., Mol., Opt. Phys. 1979 , 20 ,595−602..

Shiwa,Y.;Taneike,T.;Yokojima,Y.Scalingbehaviorofblockcopolymersinspontaneousgrowthoflamellardomains. Phys. Rev. Lett. 1996 , 77 ,4378..

Bahiana,M.;Oono,Y.Celldynamicalsystemapproachtoblockcopolymers. Phys. Rev. A: At., Mol., Opt. Phys. 1990 , 41 ,6763..

Yokojima,Y.;Shiwa,Y.Orderingprocessinquenchedblockcopolymersatlowtemperatures. Phys. Rev. E: Stat. Phys., Plasmas, Fluids, Relat. Interdiscip. Top. 2000 , 62 ,6838..

Singh,M.;Wu,W.;Nuka,V.;Strzalka,J.;Douglas,J.F.;Karim,A.Latestagedomaincoarseningdynamicsoflamellarblockcopolymers. ACS Macro Lett. 2021 , 10 ,727−731..

Views

143

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

Long-Range Ordered Nanostructures of Assembling Macromolecules via Rational Design of Kinetic Pathways: A Computational Perspective

Block Copolymer Aided Controllable Design of Colloidal Molecules by DNA-programmable Assembly

Topology-regulated Co-assembly of Single Chain Polymer Nanoparticles and Block Copolymers into Hierarchical Micelle@Vesicle Composite Structures

Molecular Segregation and Melt Memory in Dilute Polycaprolactone with Reduced Entanglements

From Molecular Defect to Macroscopic Performance: Manipulating Dichroism and Mechanics in Iodine-doped Poly(vinyl alcohol) via Ethylene Incorporation

Related Author

Xian-Deng Qiu

Hao Tang

Rong Wang

Bai-Xue Deng

Hong-Zhu Lai

Li Jiang

Lin Yu

Lin Cheng

Related Institution

Department of Polymer Science and Engineering, State Key Laboratory of Coordination Chemistry, Key Laboratory of High Performance Polymer Materials and Technology of Ministry of Education, School of Chemistry and Chemical Engineering, Nanjing University

State Key Laboratory of Molecular Engineering of Polymers, Department of Macromolecular Science, Fudan University

School of Chemistry and Materials Science, Anhui Normal University

College of chemical engineering and materials, Shandong University of Aeronautics

School of Materials Science and Engineering, Nanchang Hangkong University

⁰

Inferring the Physics of Structural Evolution of Multicomponent Polymers via Machine-Learning-Accelerated Method

DOI：10.1007/s10118-023-2891-9

摘要

Abstract

关键词

Keywords

references