[en] Polymer particle size constitutes a crucial characteristic of product quality in polymerization. Raman spectroscopy is an established and reliable process analytical technology for in-line concentration monitoring. Recent approaches and some theoretical considerations show a correlation between Raman signals and particle sizes but do not determine polymer size from Raman spectroscopic measurements accurately and reliably. With this in mind, we propose three alternative machine learning workflows to perform this task, all involving diffusion maps, a nonlinear manifold learning technique for dimensionality reduction: (i) directly from diffusion maps, (ii) alternating diffusion maps, and (iii) conformal autoencoder neural networks. We apply the workflows to a data set of Raman spectra with associated size measured via dynamic light scattering of 47 microgel (cross-linked polymer) samples in a diameter range of 208–483 nm. The conformal autoencoders substantially outperform state-of-the-art methods and results for the first time in a promising prediction of polymer size from Raman spectra.
Disciplines :
Engineering, computing & technology: Multidisciplinary, general & others
Author, co-author :
KORONAKI, Eleni ; University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Engineering (DoE)
Kaven, Luise F.; Process Systems Engineering (AVT.SVT), RWTH Aachen University, Aachen, Germany
Faust, Johannes M. M.; Process Systems Engineering (AVT.SVT), RWTH Aachen University, Aachen, Germany
Kevrekidis, Ioannis G.; Department of Chemical and Biomolecular Engineering and Department of Applied Mathematics and Statistics, Whiting School of Engineering, Johns Hopkins University, Baltimore, United States
Mitsos, Alexander ; Process Systems Engineering (AVT.SVT), RWTH Aachen University, Aachen, Germany ; JARA-CSD, Aachen, Germany ; Institute of Energy and Climate Research, Energy Systems Engineering (IEK-10), Forschungszentrum Jülich GmbH, Jülich, Germany
External co-authors :
yes
Language :
English
Title :
Nonlinear manifold learning determines microgel size from Raman spectroscopy
Air Force Office of Scientific Research Deutsche Forschungsgemeinschaft Horizon 2020 Framework Programme
Funding text :
This work was performed as a part of project B4 of the CRC\u00A0985 \u201CFunctional Microgels and Microgel Systems\u201D funded by Deutsche Forschungsgemeinschaft (DFG). EDK was funded by the Luxembourg National Research Fund (FNR), grant reference 16758846. For the purpose of open access, the authors have applied a Creative Commons Attribution 4.0 International (CC BY 4.0) license to any Author Accepted Manuscript version arising from this submission. The work of YGK was partially supported by the US Air Force Office of Scientific Research. The authors thank J\u00F6rn Viell for scientific discussions and feedback on the manuscript and Andrij Pich for useful discussions on future tasks and impact of this work. Open Access funding enabled and organized by Projekt DEAL.This work was performed as a part of project B4 of the CRC 985 \u201CFunctional Microgels and Microgel Systems\u201D funded by Deutsche Forschungsgemeinschaft (DFG). EDK was funded by the Luxembourg National Research Fund (FNR), grant reference 16758846. For the purpose of open access, the authors have applied a Creative Commons Attribution 4.0 International (CC BY 4.0) license to any Author Accepted Manuscript version arising from this submission. The work of YGK was partially supported by the US Air Force Office of Scientific Research. The authors thank J\u00F6rn Viell for scientific discussions and feedback on the manuscript and Andrij Pich for useful discussions on future tasks and impact of this work. Open Access funding enabled and organized by Projekt DEAL.
Chew W, Sharratt P. Trends in process analytical technology. Anal Methods. 2010;2(10):1412.
Beer T, Burggraeve A, Fonteyne M, Saerens L, Remon J, Vervaet C. Near infrared and Raman spectroscopy for the in-process monitoring of pharmaceutical production processes. Int J Pharm. 2011;417(1-2):32-47.
Pomerantsev A, Rodionova O. Process analytical technology: a critical view of the chemometricians. J Chemometr. 2012;26(6):299-310.
Simon L, Pataki H, Marosi G, et al. Assessment of recent process analytical technology (PAT) trends: a multiauthor review. Organ Process Res Dev. 2015;19(1):3-62.
Beer A. Bestimmung der absorption des rothen Lichts in farbigen Flüssigkeiten. Annal Phys Chem. 1852;162(5):78-88.
Marini F, Bucci R, Magrì A, Magrì A. Artificial neural networks in chemometrics: history, examples and perspectives. Microchem J. 2008;88(2):178-185.
Garrido M, Rius F, Larrechi M. Multivariate curve resolution-alternating least squares (MCR-ALS) applied to spectroscopic data from monitoring chemical reactions processes. Anal Bioanal Chem. 2008;390(8):2059-2066.
Alsmeyer F, Koß HJ, Marquardt W. Indirect spectral hard modeling for the analysis of reactive and interacting mixtures. Appl Spectrosc. 2004;58(8):975-985.
Keidel R, Ghavami A, Lugo D, et al. Time-resolved structural evolution during the collapse of responsive hydrogels: the microgel-to-particle transition. Sci Adv. 2018;4(4):eaao7086.
Bohren CF, Huffman DR. Absorption and Scattering of Light by Small Particles. Wiley; 1998.
Reis M, Araújo P, Sayer C, Giudici R. Evidences of correlation between polymer particle size and Raman scattering. Polymer. 2003;44(20):6123-6128.
van den Brink M, Pepers M, van Herk A. Raman spectroscopy of polymer latexes. J Raman Spectrosc. 2002;33(4):264-272.
Ito K, Kato T, Ona T. Non-destructive method for the quantification of the average particle diameter of latex as water-based emulsions by near-infrared Fourier transform Raman spectroscopy. J Raman Spectrosc. 2002;33(6):466-470.
Houben C, Nurumbetov G, Haddleton D, Lapkin A. Feasibility of the simultaneous determination of monomer concentrations and particle size in emulsion polymerization using in situ Raman spectroscopy. Ind Eng Chem Res. 2015;54(51):12867-12876.
Ambrogi P, Colmán M, Giudici R. Miniemulsion polymerization monitoring using off-line Raman spectroscopy and in-line NIR spectroscopy. Macromol React Eng. 2017;11(4):1600013.
Meyer-Kirschner J, Mitsos A, Viell J. Polymer particle sizing from Raman spectra by regression of hard model parameters. J Raman Spectrosc. 2018;49(8):1402-1411.
Nadler B, Lafon S, Coifman R, Kevrekidis I. Diffusion maps, spectral clustering and reaction coordinates of dynamical systems. Appl Comput Harmonic Anal. 2006;21(1):113-127.
Coifman R, Kevrekidis I, Lafon S, Maggioni M, Nadler B. Diffusion maps, reduction coordinates, and low dimensional representation of stochastic systems. Multiscale Model Simul. 2008;7(2):842-864.
Lederman R, Talmon R. Learning the geometry of common latent variables using alternating-diffusion. Appl Comput Harmonic Anal. 2018;44(3):509-536.
Katz O, Talmon R, Lo YL, Wu HT. Alternating diffusion maps for multimodal data fusion. Inform Fusion. 2019;45:346-360.
Dietrich F, Yair O, Mulayoff R, Talmon R, Kevrekidis I. Spectral discovery of jointly smooth features for multimodal data. SIAM J Math Data Sci. 2022;4(1):410-430.
Evangelou N, Wichrowski N, Kevrekidis G, et al. On the parameter combinations that matter and on those that do not: data-driven studies of parameter (non)identifiability. PNAS Nexus. 2022;1:154.
Chiavazzo E, Gear C, Dsilva C, Rabin N, Kevrekidis I. Reduced models in chemical kinetics via nonlinear data-mining. Processes. 2014;2(1):112-140.
Koronaki E, Evangelou N, Psarellis Y, Boudouvis A, Kevrekidis I. From partial data to out-of-sample parameter and observation estimation with diffusion maps and geometric harmonics. Comput Chem Eng. 2023;178:108357.
Nyström E. Über Die Praktische Auflösung von Linearen Integralgleichungen Mit Anwendungen Auf Randwertaufgaben der Potentialtheorie. Akademische Buchhandlung; 1929.
Fowlkes C, Belongie S, Malik J. Efficient spatiotemporal grouping using the Nystrom method. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001. Vol 1. IEEE; 2001:I-II.
Evangelou N, Dietrich F, Chiavazzo E, Lehmberg D, Meila M, Kevrekidis I. Double diffusion maps and their latent harmonics for scientific computations in latent space. arXiv preprint arXiv:2204.12536. 2022.
Kaven L, Schweidtmann A, Keil J, Israel J, Wolter N, Mitsos A. Data-driven product-process optimization of n-isopropylacrylamide microgel synthesis in flow. arXiv preprint arXiv:2308.16724. 2023.
Kaven L, Wolff H, Wille L, Wessling M, Mitsos A, Viell J. In-line monitoring of microgel synthesis: flow versus batch reactor. Organ Process Res Dev. 2021;25(9):2039-2051.
Kather M, Ritter F, Pich A. Surfactant-free synthesis of extremely small stimuli-responsive colloidal gels using a confined impinging jet reactor. Chem Eng J. 2018;344:375-379.
Wolff H, Kather M, Breisig H, Richtering W, Pich A, Wessling M. From batch to continuous precipitation polymerization of thermoresponsive microgels. ACS Appl Mater Interfaces. 2018;10(29):24799-24806.
Janssen F, Kather M, Ksiazkiewicz A, Pich A, Mitsos A. Synthesis of poly(N-vinylcaprolactam)-based microgels by precipitation polymerization: pseudo-bulk model for particle growth and size distribution. ACS Omega. 2019;4(9):13795-13807.
Kaven L, Mitsos A. Dataset to: nonlinear manifold learning determines microgel size from Raman spectroscopy. 2023. doi:10.18154/RWTH-2023-05604
Kaven L, Wolff H, Wille L, Wessling M, Mitsos A, Viell J. Dataset to: in-line monitoring of microgel synthesis: flow versus batch reactor. 2021. doi:10.18154/RWTH-2021-09666
Psarellis Y, Lee S, Bhattacharjee T, Datta S, Bello-Rivas J, Kevrekidis I. Data-driven discovery of chemotactic migration of bacteria via machine learning. arXiv preprint arXiv:2208.11853. 2022.
Coifman RR, Lafon S. Geometric harmonics: a novel tool for multiscale out-of-sample extension of empirical functions. Appl Comput Harmonic Anal. 2006;21(1):31-52.
Dsilva C, Talmon R, Coifman R, Kevrekidis I. Parsimonious representation of nonlinear dynamical systems through manifold learning: a chemotaxis case study. Appl Comput Harmonic Anal. 2018;44(3):759-773.
Talmon R, Wu HT. Latent common manifold learning with alternating diffusion: analysis and applications. Appl Comput Harmonic Anal. 2019;47(3):848-892.
Koronaki E, Kaven L, Faust J, Kevrekidis I, Mitsos A. Code to: nonlinear manifold learning determines microgel size from Raman spectroscopy. 2023 https://gitlab.com/eleni.koronaki/mlforpolymersizeraman.git
MI Ltd. Zetasizer nano technical note MRK728-01 - the accuracy and precision expected from dynamic light scattering measurements. 2006 https://kdsi.ru/upload/iblock/357/be4ecfa4fcce215f870e4acb8eb229d6.pdf
