Machine Learning-Based Quantification of Polymer Structure Property Relationships for Predictive Material Design

Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2026 | Volume : 14 | 03 | Page :
    By

    Kalpana G. Joshi,

  • Shanthi Kumaraguru,

  • Prashant M. Yawalkar,

  • P. William,

  • Prashant V. Thokal,

  • Jaikumar M. Patil,

  1. Assistant Professor, School of Engineering and Technology, Sanjivani University, Kopargaon, Maharashtra, India
  2. Assistant Professor, Department of Information Technology, D Y Patil College of Engineering, Akurdi, Pune, Maharashtra, India
  3. Associate Professor, Department of Computer Engineering, MET’s Institute of Engineering, BKC, Nashik, Maharashtra, India
  4. Professor (Research), School of Computer Science and Technology, Karunya Institute of Technology and Sciences, Coimbatore, Tamil Nadu, India
  5. Assistant Professor, Department of Electrical Engineering, Sanjivani College of Engineering, Kopargaon, Maharashtra, India
  6. Associate Professor, Department of Computer Science and Engineering, Shri Sant Gajanan Maharaj College of Engineering, Shegaon, SGBAU, Amravati, Maharashtra, India

Abstract

Polymer structures exhibit complex, hierarchical arrangements that strongly influence macroscopic properties, yet consistent quantification remains challenging due to nonlinear interactions and limited unified modeling strategies. Existing approaches inadequately capture generalized structure–property mappings across diverse polymer systems. This research aims to establish a machine learning-based quantification model for polymer structure–property relationships to support predictive material design. A Polymer Structure Property Dataset of 5,000 polymer samples includes structural descriptors and experimentally measured thermal and physical properties. Data preprocessing involves Z-score normalization and missing value imputation using K-Nearest Neighbors (KNN). Feature extraction employs Principal Component Analysis (PCA), enhancing discriminative structural patterns while reducing dimensional redundancy. The model systematically collects polymer data, preprocesses and refines the data, it also extracts salient structural features, and feeds them into an optimized predictive engine. The proposed Electric Fish Optimizer-driven Intelligent Support Vector Machine (EFO-ISVM) combines global optimization and adaptive learning. The EFO is utilized for hyperparameter tuning due to its efficient exploration–exploitation balance inspired by electric field sensing behavior, while the ISVM performs nonlinear regression and classification to model complex structure–property dependencies with improved generalization. Quantification is achieved by mapping structural descriptors to target properties using Python, enabling precise evaluation of interdependencies and sensitivity patterns, with an achieved prediction Stability of (97.92%). The model demonstrates enhanced predictive stability, reduced error tendencies, and improved generalization across multiple property indicators. The approach supports reliable material design decisions, offering a scalable pathway for intelligent polymer engineering and advanced composite development.

Keywords: Polymer Structure–Property Relationships, Predictive Material Design, Polymer Informatics, Molecular Feature Engineering, Property Prediction Modeling.

How to cite this article:
Kalpana G. Joshi, Shanthi Kumaraguru, Prashant M. Yawalkar, P. William, Prashant V. Thokal, Jaikumar M. Patil. Machine Learning-Based Quantification of Polymer Structure Property Relationships for Predictive Material Design. Journal of Polymer & Composites. 2026; 14(03):-.
How to cite this URL:
Kalpana G. Joshi, Shanthi Kumaraguru, Prashant M. Yawalkar, P. William, Prashant V. Thokal, Jaikumar M. Patil. Machine Learning-Based Quantification of Polymer Structure Property Relationships for Predictive Material Design. Journal of Polymer & Composites. 2026; 14(03):-. Available from: https://journals.stmjournals.com/jopc/article=2026/view=245929


References

  1. Sharma, A., Mukhopadhyay, T., Rangappa, S.M., Siengchin, S. and Kushvaha, V., 2022. Advances in computational intelligence of polymer composite materials: machine learning assisted modeling, analysis and design. Archives of Computational Methods in Engineering, 29(5), pp.3341-3385. https://doi.org/10.1007/s11831-021-09700-9
  2. Das, P.P., Rabby, M.M., Vadlamudi, V. and Raihan, R., 2022. Moisture content prediction in polymer composites using machine learning techniques. Polymers, 14(20), p.4403. https://doi.org/10.3390/polym14204403
  3. Shireen, Z., Weeratunge, H., Menzel, A., Phillips, A.W., Larson, R.G., Smith-Miles, K. and Hajizadeh, E., 2022. A machine learning enabled hybrid optimization framework for efficient coarse-graining of a model polymer. npj Computational Materials, 8(1), p.224. https://doi.org/10.1038/s41524-022-00914-4
  4. Conrad, F., Mälzer, M., Schwarzenberger, M., Wiemer, H. and Ihlenfeldt, S., 2022. Benchmarking AutoML for regression tasks on small tabular data in materials design. Scientific Reports, 12(1), p.19350. https://doi.org/10.1038/s41598-022-23327-1
  5. McDonald, S.M., Augustine, E.K., Lanners, Q., Rudin, C., Catherine Brinson, L. and Becker, M.L., 2023. Applied machine learning as a driver for polymeric biomaterials design. Nature Communications, 14(1), p.4838. https://doi.org/10.1038/s41467-023-40459-8
  6. Hooshmand, M.J., Sakib-Uz-Zaman, C. and Khondoker, M.A.H., 2023. Machine learning algorithms for predicting mechanical stiffness of lattice structure-based polymer foam. Materials, 16(22), p.7173. https://doi.org/10.3390/ma16227173
  7. Shaari, N., Osman, S.H., Kamarudin, S.K., Karim, N.A., Basri, S. and Wani, A.A., 2026. Structure–property relationships in polymer electrolyte membranes for fuel cell applications: insights from molecular dynamics simulations. Polymer Bulletin, 83(5), p.243. https://doi.org/10.1007/s00289-026-06305-9
  8. Huang, X., Ma, S., Zhao, C.Y., Wang, H. and Ju, S., 2023. Exploring high thermal conductivity polymers via interpretable machine learning with physical descriptors. npj Computational Materials, 9(1), p.191. https://doi.org/10.1038/s41524-023-01154-w
  9. Kazemi-Khasragh, E., Blázquez, J.P.F., Gómez, D.G., González, C. and Haranczyk, M., 2024. Facilitating polymer property prediction with machine learning and group interaction modelling methods. International Journal of Solids and Structures, 286, p.112547. https://doi.org/10.1016/j.ijsolstr.2023.112547
  10. Malashin, I., Tynchenko, V., Gantimurov, A., Nelyub, V. and Borodulin, A., 2024. A multi-objective optimization of neural networks for predicting the physical properties of textile polymer composite materials. Polymers, 16(12), p.1752. https://doi.org/10.3390/polym16121752
  11. Struble, D.C., Lamb, B.G. and Ma, B., 2024. A prospective on machine learning challenges, progress, and potential in polymer science.  MRS communications, 14(5), pp.752-770. https://doi.org/10.1557/s43579-024-00587-8
  12. Alhusban, M., Alhusban, M. and Alkhawaldeh, A.A., 2024. The efficiency of using machine learning techniques in fiber-reinforced-polymer applications in structural engineering. Sustainability, 16(1), p.11. https://doi.org/10.3390/su16010011
  13. Qiu, H. and Sun, Z.Y., 2024. On-demand reverse design of polymers with PolyTAO. Npj Computational Materials, 10(1), p.273. https://doi.org/10.1038/s41524-024-01466-5
  14. Berladir, K., Antosz, K., Ivanov, V. and Mitaľová, Z., 2025. Machine learning-driven prediction of composite materials properties based on experimental testing data. Polymers, 17(5), p.694. https://doi.org/10.3390/polym17050694
  15. Malashin, I.P., Martysyuk, D., Nelyub, V., Borodulin, A., Gantimurov, A. and Tynchenko, V., 2025. Deep learning for property prediction of natural fiber polymer composites. Scientific Reports, 15(1), p.27837. https://doi.org/10.1038/s41598-025-10841-1
  16. Ishikiriyama, K., 2022. Polymer informatics based on the quantitative structure-property relationship using a machine-learning framework for the physical properties of polymers in the ATHAS data bank. Thermochimica Acta, 708, p.179135. https://doi.org/10.1016/j.tca.2021.179135
  17. Malashin, I.P., Tynchenko, V.S., Nelyub, V.A., Borodulin, A.S. and Gantimurov, A.P., 2023. Estimation and prediction of the polymers’ physical characteristics using the machine learning models. Polymers, 16(1), p.115. https://doi.org/10.3390/polym16010115
  18. Aditya Gujar, Manas Kale, Vaibhav Gobbur, Maya M. Charde, Amol J. Asalekar. Noise and Vibration Reduction Using Sustainable Polymer Nanocomposite Materials: A Review. Journal of Polymer & Composites. 2026; 14(03).
  19. Vijay Kumar, Apurva Jain, Rachna Narula, Megha Sehgal, Meena Siwach, Tulika Bhatia. Modern Heritage Restoration Using GANs: Insights into Polymer–Composite Aging. Journal of Polymer & Composites. 2026; 14(02):508-516.
  20. Gobind, Tejeet Singh. Fabrication and Characterization of Hybrid Composites Using Natural Fibers Reinforced in HDPE and Optimization of Injection Moulding Process Parameters to Minimize Shrinkage. Journal of Polymer & Composites. 2026; 14(02):556-585.
  21. Priya R, M. Bala Theja, Hari kumar Andem, Ankush B. Khansole, S. Mohamed Rabeek, Rekha Anantharaman, S B G Tilak Babu. Synergistic Effects of Hybridized Nano-Silica and Hemp Fiber Reinforcement on Bio-Epoxy Composites. Journal of Polymer & Composites. 2026; 14(03).
  22. Shashank S. Patokar, Bhagyashri P. Thakur, Sairaj S. Gujar, Maya M. Charde, Amol J. Asalekar. Natural Frequency Analysis of Polymer Composites. Journal of Polymer & Composites. 2026; 14(03).
  23. Santhosh Kannan, M. HemaPriya, B. Vijaya, J. Faney. Mechanical Performance and Material Properties of Nsm CFRP Polymer System. Journal of Polymer & Composites. 2026; 14(01):311-319.
Ahead of Print Subscription Original Research
Volume 14
03
Received 22/05/2026
Accepted 02/06/2026
Published 04/06/2026
Publication Time 13 Days
15

Login


My IP

PlumX Metrics