{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T04:47:15Z","timestamp":1785646035437,"version":"3.56.0"},"reference-count":33,"publisher":"MDPI AG","issue":"15","license":[{"start":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T00:00:00Z","timestamp":1785456000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Polymers"],"abstract":"<jats:p>Rapid estimation of the melt flow index (MFI) is essential for the timely control of industrial polypropylene polymerization because conventional plastometer measurements require offline sampling and introduce analytical delays. This work investigates the physicochemical limits of MFI model transferability using 425 reactor-grade polypropylene production runs spanning homopolymer, random copolymer, and impact copolymer architectures. Principal component analysis (PCA), partial least squares (PLS), PCR-Ridge, Random Forest, Extra Trees, and Gradient Boosting were evaluated using within-pool, repeated five-fold, and product group validation. The latent structure, predictive performance, and dominant process descriptors were strongly architecture-dependent. Hydrogen-related variables remained central to molecular weight control, whereas comonomer descriptors, catalyst and donor variables, hydrodynamic conditions, and second reactor variables gained importance as compositional and morphological complexity increased. Nonlinear ensembles improved prediction within heterogeneous pools, but product group validation still revealed transferability losses when models crossed architecture-dependent process\u2013structure\u2013property domains. Repeated cross-validation and preprocessing sensitivity analyses confirmed that the principal model rankings and architecture-dependent conclusions were stable under resampling and correlation filtering. These results show that the polymer architecture defines a practical applicability boundary for industrial MFI soft sensors and supports architecture-specific or architecture-routed calibration when universal models fail cross-family validation.<\/jats:p>","DOI":"10.3390\/polym18151880","type":"journal-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T08:20:18Z","timestamp":1785486018000},"page":"1880","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Reactor-Grade Non-Additive Polypropylene Architecture Defines the Physicochemical Limits of Melt Flow Index Model Transferability: An Industrial Chemometric and Machine Learning Study"],"prefix":"10.3390","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2330-8580","authenticated-orcid":false,"given":"Joaqu\u00edn","family":"Hern\u00e1ndez-Fern\u00e1ndez","sequence":"first","affiliation":[{"name":"Chemistry Program, Department of Natural and Exact Sciences, University of Cartagena, San Pablo Campus, Cartagena de Indias 130015, Colombia"},{"name":"Department of Natural and Exact Sciences, Universidad de la Costa, Barranquilla 080002, Colombia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6904-2282","authenticated-orcid":false,"given":"Juan","family":"Lopez-Martinez","sequence":"additional","affiliation":[{"name":"Institute of Materials Technology (ITM), Universitat Politecnica de Valencia (UPV), Plaza Ferrandiz and Carbonell s\/n, 03801 Alcoy, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,31]]},"reference":[{"key":"ref_1","unstructured":"(2022). Plastics\u2014Determination of the Melt Mass-Flow Rate (MFR) and Melt Volume-Flow Rate (MVR) of Thermoplastics\u2014Part 1: Standard Method (Standard No. ISO 1133-1:2022)."},{"key":"ref_2","unstructured":"(2023). Standard Test Method for Melt Flow Rates of Thermoplastics by Extrusion Plastometer (Standard No. ASTM D1238-23)."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1073","DOI":"10.1002\/app.21308","article-title":"Propylene\u2013ethylene random copolymers: Comonomer effects on crystallinity and application properties","volume":"95","author":"Gahleitner","year":"2005","journal-title":"J. Appl. Polym. Sci."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1083","DOI":"10.1007\/s00397-007-0200-0","article-title":"Melt viscosity effects in ethylene\u2013propylene copolymers","volume":"46","author":"Grein","year":"2007","journal-title":"Rheol. Acta"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"693","DOI":"10.1007\/s10973-009-0532-3","article-title":"Flow-induced crystallization of propylene\/ethylene random copolymers","volume":"98","author":"Housmans","year":"2009","journal-title":"J. Therm. Anal. Calorim."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"6396","DOI":"10.1021\/acs.macromol.7b01228","article-title":"Effect of random ethylene comonomer on relaxation of flow-induced precursors in isotactic polypropylene","volume":"50","author":"Dargent","year":"2017","journal-title":"Macromolecules"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"532","DOI":"10.1080\/10601325.2015.1039325","article-title":"The influence of copolymerization condition on rheology, morphology and thermal behavior of polypropylene heterophasic copolymers","volume":"52","author":"Jahani","year":"2015","journal-title":"J. Macromol. Sci. Part A Pure Appl. Chem."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1021\/ie049803b","article-title":"Clustering-based hybrid soft sensor for an industrial polypropylene process with grade changeover operation","volume":"44","author":"Kim","year":"2005","journal-title":"Ind. Eng. Chem. Res."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1105","DOI":"10.1002\/aic.690440509","article-title":"Product design through multivariate statistical analysis of process data","volume":"44","author":"Jaeckle","year":"1998","journal-title":"AIChE J."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"6372","DOI":"10.1016\/j.ces.2006.05.046","article-title":"Inferential sensors for estimation of polymer quality parameters: Industrial application of a PLS-based soft sensor for a LDPE plant","volume":"61","author":"Sharmin","year":"2006","journal-title":"Chem. Eng. Sci."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Tian, H., Tian, X., and Deng, X. (2010). Soft sensor for polypropylene melt index based on improved orthogonal least squares. Proceedings of the 8th World Congress on Intelligent Control and Automation, Jinan, China, 7\u20139 July 2010, IEEE.","DOI":"10.1109\/WCICA.2010.5554539"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"324","DOI":"10.1002\/cem.2795","article-title":"A real-time model based on optimized least squares support vector machine for industrial polypropylene melt index prediction","volume":"30","author":"Zhang","year":"2016","journal-title":"J. Chemom."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1007\/s11633-019-1203-x","article-title":"Developing soft sensors for polymer melt index in an industrial polymerization process using deep belief networks","volume":"17","author":"Zhu","year":"2020","journal-title":"Int. J. Autom. Comput."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"857","DOI":"10.1016\/j.ifacol.2022.07.552","article-title":"Soft sensor for melt index prediction based on long short-term memory network","volume":"55","author":"Song","year":"2022","journal-title":"IFAC-PapersOnLine"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"5037","DOI":"10.1021\/ie504185j","article-title":"Auto-switch Gaussian process regression-based probabilistic soft sensors for industrial multigrade processes with transitions","volume":"54","author":"Liu","year":"2015","journal-title":"Ind. Eng. Chem. Res."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Seifert, L., Leuchtenberger-Engel, L., and Hopmann, C. (2024). Enhancing the quality of polypropylene recyclates: Predictive modelling of the melt flow rate and shear viscosity. Polymers, 16.","DOI":"10.20944\/preprints202408.0359.v1"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"6655","DOI":"10.1021\/acs.jcim.5c00667","article-title":"Data-driven optimization of industrial impact polypropylene characterization: Machine learning insights","volume":"65","author":"Cunningham","year":"2025","journal-title":"J. Chem. Inf. Model."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1354","DOI":"10.1039\/D3RE00504F","article-title":"Machine learning for revealing the relationship between the process\u2013structure\u2013properties of polypropylene in-reactor alloys","volume":"9","author":"Zheng","year":"2024","journal-title":"React. Chem. Eng."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"16330","DOI":"10.1021\/acs.iecr.0c02398","article-title":"Development of adversarial transfer learning soft sensor for multigrade processes","volume":"59","author":"Liu","year":"2020","journal-title":"Ind. Eng. Chem. Res."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"4654","DOI":"10.1109\/TII.2021.3120509","article-title":"Domain adaptation mixture of Gaussian processes for online soft sensor modeling of multimode processes when sensor degradation occurs","volume":"18","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"19888","DOI":"10.1021\/acsomega.3c01832","article-title":"Adversarial transferred data-assisted soft sensor for enhanced multigrade quality prediction","volume":"8","author":"Dai","year":"2023","journal-title":"ACS Omega"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Curreri, F., Patan\u00e8, G., Xibilia, M., and Rizzo, A.F. (2021). Soft sensor transferability: A survey. Appl. Sci., 11.","DOI":"10.3390\/app11167710"},{"key":"ref_23","unstructured":"Farahani, H.S., Fatehi, A., Nadali, A., and Shoorehdeli, M.A. (2020). A novel method for designing transferable soft sensors and its application. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"371","DOI":"10.4314\/bcse.v32i2.15","article-title":"Hydrogen effect modeling on Ziegler\u2013Natta catalyst and final product properties in propylene polymerization","volume":"32","author":"Varshouee","year":"2018","journal-title":"Bull. Chem. Soc. Ethiop."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/0169-7439(87)80084-9","article-title":"Principal component analysis","volume":"2","author":"Wold","year":"1987","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/S0169-7439(01)00155-1","article-title":"PLS-regression: A basic tool of chemometrics","volume":"58","author":"Wold","year":"2001","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/0169-7439(93)85002-X","article-title":"SIMPLS: An alternative approach to partial least squares regression","volume":"18","year":"1993","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1080\/00401706.1970.10488634","article-title":"Ridge regression: Biased estimation for nonorthogonal problems","volume":"12","author":"Hoerl","year":"1970","journal-title":"Technometrics"},{"key":"ref_29","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/s10994-006-6226-1","article-title":"Extremely randomized trees","volume":"63","author":"Geurts","year":"2006","journal-title":"Mach. Learn."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: A gradient boosting machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann. Stat."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Parvez, M.A., El-Latif, A.A.A., and Elhoseny, M. (2025). An artificial intelligence-based melt flow rate prediction model for polymer properties analysis. Polymers, 17.","DOI":"10.3390\/polym17172382"}],"container-title":["Polymers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-4360\/18\/15\/1880\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T04:13:35Z","timestamp":1785644015000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-4360\/18\/15\/1880"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,31]]},"references-count":33,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["polym18151880"],"URL":"https:\/\/doi.org\/10.3390\/polym18151880","relation":{},"ISSN":["2073-4360"],"issn-type":[{"value":"2073-4360","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,31]]}}}