Machine Learning Assisted Design and Analysis of Polymer Composite Materials for Sustainable Renewable Energy Systems

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

    Jatin Thakur,

  • Ramesh Narwal,

  • Nishant Sharma,

  1. Student, Department of Computer Science & Engineering and Information Technology, Jaypee University of Information Technology, Himachal Pradesh, India
  2. Assistant Professor, Department of Computer Science & Engineering and Information Technology, Jaypee University of Information Technology, Himachal Pradesh, India
  3. Assistant Professor, Department of Computer Science & Engineering and Information Technology, Jaypee University of Information Technology, Himachal Pradesh, India

Abstract

Accurate prediction and optimization of polymer composite properties is of paramount importance in the design of these lightweight, durable, and sustainable materials within renewable energy technologies. This work will provide a holistic machine learning-assisted framework that unites materials informatics with domain-specific features and state-of-the-art ML methodologies in the prediction of the mechanical properties of polymer composites, such as tensile strength. This includes embedding several ensemble models, including Random Forest and Gradient Boosting, kernel methods such as SVR, neural networks, graph-based approaches, while it applies principled hyperparameter tuning and uncertainty quantification, along with model-interpretability tools such as SHAP and systematic ablation to identify the most important material and processing factors. The proposed methodology is demonstrated with curated, publicly available datasets, and we discuss means for synthetic data augmentation, cross-validation protocols, assessment of model robustness, and best practices in reporting results in a reproducible way. The results show that data-driven models reduce prediction error and speed up the processes of materials selection in view of Net Zero targets, given limited available experimental iterations; this informs intelligent lightweighting of renewable energy components. Furthermore, the study highlights the capability of machine learning models to capture complex nonlinear relationships between composition, processing parameters, and mechanical response that are difficult to address using conventional trial-and-error approaches. By reducing reliance on extensive experimental campaigns, the proposed framework supports faster design cycles and more efficient utilization of material and energy resources in renewable energy applications.

Keywords: Polymer composites, materials informatics, machine learning, random forest, XGBoost, SHAP, uncertainty quantification, renewable energy

How to cite this article:
Jatin Thakur, Ramesh Narwal, Nishant Sharma. Machine Learning Assisted Design and Analysis of Polymer Composite Materials for Sustainable Renewable Energy Systems. Journal of Polymer & Composites. 2026; 14(03):-.
How to cite this URL:
Jatin Thakur, Ramesh Narwal, Nishant Sharma. Machine Learning Assisted Design and Analysis of Polymer Composite Materials for Sustainable Renewable Energy Systems. Journal of Polymer & Composites. 2026; 14(03):-. Available from: https://journals.stmjournals.com/jopc/article=2026/view=243515


References

  1. International Energy Agency. Net zero by 2050: a roadmap for the global energy sector. Paris: IEA; 2023. Available from: https://www.iea.org/reports/net-zero-by-2050
  2. Butler KT, Davies DW, Cartwright H, Isayev O, Walsh A. Machine learning for molecular and materials science. Nature. 2018;559:547–55.
  3. Huang B, et al.. Best practices for machine learning in materials science. Nat Comput Sci. 2023;3:127–35.
  4. Materials Project Consortium. The Materials Project: a materials genome approach to accelerating materials innovation [Internet]. 2013 [cited 2025 Nov 1]. Available from: https://materialsproject.org
  5. Cassola S, et al.. Machine learning for polymer composites process simulation. Compos Struct. 2022;289:115390.
  6. Sorour SS, et al.. A review on machine learning implementation for laminated FRP composites. Compos Struct. 2024;320:116978.
  7. Malashin A, et al.. Machine learning prediction of mechanical properties of natural fiber reinforced polymer composites. Compos Struct. 2024;326:116966.
  8. FDM 3D printed composite material prediction data [Internet]. Kaggle; 2021 [cited 2025 Nov 1]. Available from: https://www.kaggle.com/datasets/ziya07/fdm-3d-printed-composite-material-prediction-data
  9. Graph networks for materials exploration [Internet]. DeepMind Research; 2023 [cited 2025 Nov 1]. Available from: https://deepmind.google/discover/blog
  10. Flores-Campos R. Polymer composite dataset [Internet]. Mendeley Data; 2023 [cited 2025 Nov 1]. doi:10.17632/9bshc597y9.1. Available from: https://data.mendeley.com/datasets/9bshc597y9/1
  11. MatWeb material property database [Internet]. 2025 [cited 2025 Nov 1]. Available from: https://www.matweb.com
  12. Composites Part A: Applied Science and Manufacturing – supplementary datasets [Internet]. Mendeley Data Repository; 2024 [cited 2025 Nov 1]. Available from: https://data.mendeley.com/journal/1359835X
  13. Lundberg SM, Lee SI. A unified approach to interpreting model predictions. Adv Neural Inf Process Syst. 2017;30:4765–74.
  14. DOME-ML Community. Data and model reporting guidelines for machine learning in science [Internet]. 2021 [cited 2025 Nov 1]. Available from: https://www.dome-ml.org
Ahead of Print Subscription Original Research
Volume 14
03
Received 30/01/2026
Accepted 18/03/2026
Published 12/05/2026
Publication Time 102 Days
1

Login


My IP

PlumX Metrics