Structure–Property Modeling of Cement-Based Multi-Component Composites Using Ensemble Machine Learning and Explainable Feature Attribution

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

    Aseem Kumar,

  • Deepak Kumar Tiwari,

  1. Research Scholar, Department of Civil engineering, GLA University, Mathura, 281406, Uttar Pradesh, India
  2. Assistant Professor, Department of Civil engineering, GLA University, Mathura, Uttar Pradesh, India

Abstract

Accurate prediction of compressive strength is central to structure–property optimization, quality control, and sustainability-driven design in cement-based composite materials. Cementitious systems represent heterogeneous multi-phase composites composed of reactive binder matrices and dispersed aggregate phases, whose macroscopic mechanical performance emerges from complex nonlinear interactions among constituents and curing-dependent microstructural evolution. This study develops a data-driven structure–property modeling framework to quantify the nonlinear dependence of compressive strength on multi-component composite composition and age. An experimental dataset of 1030 mixtures incorporating variations in binder constituents, water content, chemical admixtures, aggregate fractions including polymers waste such as fly ash, plasticizers, and curing duration was used to train and evaluate four machine learning models: artificial neural network (multilayer perceptron), support vector regression (radial basis function kernel), random forest, and extra trees. Model performance was assessed across training, validation, and testing phases using complementary statistical metrics, robustness indicators, error diagnostics, and an engineering tolerance-based reliability check. Ensemble tree-based models demonstrated superior generalization compared with neural and kernel approaches, highlighting their effectiveness in modeling heterogeneous composite systems with complex phase interactions. Among the evaluated algorithms, the extra trees model achieved the most stable predictive accuracy on unseen data. Shapley additive explanations were employed to interpret phase contributions, revealing curing age and water–binder–matrix parameters as dominant drivers of strength development, followed by binder composition and aggregate proportions. The proposed framework provides a transparent and interpretable pathway for data-driven composite design, enabling rapid screening, performance verification, and structure–property-informed optimization of cementitious composite materials.

Keywords: Concrete compressive strength; Fly Ash: Cementitious composites; Machine learning; Ensemble models; Random Forest: Super Plasticizers

How to cite this article:
Aseem Kumar, Deepak Kumar Tiwari. Structure–Property Modeling of Cement-Based Multi-Component Composites Using Ensemble Machine Learning and Explainable Feature Attribution. Journal of Polymer & Composites. 2026; 14(03):-.
How to cite this URL:
Aseem Kumar, Deepak Kumar Tiwari. Structure–Property Modeling of Cement-Based Multi-Component Composites Using Ensemble Machine Learning and Explainable Feature Attribution. Journal of Polymer & Composites. 2026; 14(03):-. Available from: https://journals.stmjournals.com/jopc/article=2026/view=243227


References

1. Barbhuiya S, Das BB, Adak D, Kapoor K, Tabish M. Low carbon concrete: advancements, challenges and future directions in sustainable construction. Discover Concrete and Cement. 2025;1:3. https://doi.org/10.1007/s44416-025-00002-y
2. Alexander M, Beushausen H. Durability, service life prediction, and modelling for reinforced concrete structures – review and critique. Cem Concr Res. 2019;122:17–29. https://doi.org/10.1016/j.cemconres.2019.04.018
3. Moccia F, Yu Q, Fernández Ruiz M, Muttoni A. Concrete compressive strength: From material characterization to a structural value. Structural Concrete. 2021;22. https://doi.org/10.1002/suco.202000211
4. DeRousseau MA, Kasprzyk JR, Srubar WV. Computational design optimization of concrete mixtures: A review. Cem Concr Res. 2018;109:42–53. https://doi.org/10.1016/j.cemconres.2018.04.007
5. Ahmed Mohd, Mallick J, AlQadhi S, Ben Kahla N. Development of Concrete Mixture Design Process Using MCDM Approach for Sustainable Concrete Quality Management. Sustainability. 2020;12:8110. https://doi.org/10.3390/su12198110
6. Rahimi MZ, Zhao R, Sadozai S, Zhu F, Ji N, Xu L. Research on the influence of curing strategies on the compressive strength and hardening behaviour of concrete prepared with Ordinary Portland Cement. Case Studies in Construction Materials. 2023;18:e02045. https://doi.org/10.1016/j.cscm.2023.e02045
7. Husem M, Gozutok S. The effects of low temperature curing on the compressive strength of ordinary and high performance concrete. Constr Build Mater. 2005;19:49–53. https://doi.org/10.1016/j.conbuildmat.2004.04.033
8. Simões S. High-Performance Advanced Composites in Multifunctional Material Design: State of the Art, Challenges, and Future Directions. Materials. 2024;17:5997. https://doi.org/10.3390/ma17235997
9. Gao J, Wang C, Chu SH. Mix design of sustainable concrete using generative models. Journal of Building Engineering. 2024;96:110618. https://doi.org/10.1016/j.jobe.2024.110618
10. Farahzadi L, Bozorgmehr Nia S, Shafei B, Kioumarsi M. Sustainability assessment of ultra-high performance concrete made with various supplementary cementitious materials. Cleaner Materials. 2025;15:100301. https://doi.org/10.1016/j.clema.2025.100301
11. Sohail MG, Wang B, Jain A, Kahraman R, Ozerkan NG, Gencturk B, et al. Advancements in Concrete Mix Designs: High-Performance and Ultrahigh-Performance Concretes from 1970 to 2016. Journal of Materials in Civil Engineering. 2018;30. https://doi.org/10.1061/(ASCE)MT.1943-5533.0002144
12. Aziz A, Mehboob SS, Tayyab A, Khan D, Hayyat K, Ali A, et al. Enhancing sustainability in self-compacting concrete by optimizing blended supplementary cementitious materials. Sci Rep. 2024;14:12326. https://doi.org/10.1038/s41598-024-62499-w
13. Mohammed A, Rafiq S, Sihag P, Kurda R, Mahmood W. Soft computing techniques: Systematic multiscale models to predict the compressive strength of HVFA concrete based on mix proportions and curing times. Journal of Building Engineering. 2021;33:101851. https://doi.org/10.1016/j.jobe.2020.101851
14. Ammar MA, Chegenizadeh A, Budihardjo MA, Nikraz H. The Effects of Crystalline Admixtures on Concrete Permeability and Compressive Strength: A Review. Buildings. 2024;14:3000. https://doi.org/10.3390/buildings14093000
15. Ravi Raj V, Madhavan C.S N, Saha BC, Vijay M, D. S, S. S, et al. Graphene-Derived Reinforced Polymer Composites for Self-Healing and Durability Enhancement in Concrete Structures. Journal of Polymer and Composites. 2025;13:77–90.
16. Palanisamy S, Kalimuthu M, Dharmalingam S, Alavudeen A, Nagarajan R, Ismail SO, et al. Effects of fiber loadings and lengths on mechanical properties of Sansevieria Cylindrica fiber reinforced natural rubber biocomposites. Mater Res Express. Institute of Physics; 2023;10. https://doi.org/10.1088/2053-1591/acefb0
17. Palaniappan M, Palanisamy S, Murugesan T mani, Tadepalli S, Khan R, Ataya S, et al. Influence of Washing with Sodium Lauryl Sulphate (SLS) Surfactant on Different Properties of Ramie Fibres. Bioresources. 2024;2:2609–25. https://doi.org/10.15376/biores.19.2.2609-2625
18. Ramasubbu R, Kayambu A, Palanisamy S, Ayrilmis N. Mechanical Properties of Epoxy Composites Reinforced with Areca catechu Fibers Containing Silicon Carbide. Bioresources [Internet]. 2024 [cited 2026 Mar 24];2:2353–70. https://doi.org/10.15376/biores.19.2.2353-2370
19. Yadav M, Srivastava D. Leathercrete-A Sustainable Approach to Fine Aggregate Replacement. Contemp Res in Multi PEER-REVIEWED JOURNAL [Internet]. 4. https://doi.org/10.5281/zenodo.15498179
20. Al-Joulani NMA. Effect of Rubber and Leather Wastes on Concrete Properties. Hebron, West Bank, State of Palestine; 2013 Oct. https://doi.org/https://dsr.ppu.edu/sites/default/files/conference/abstracts/Titl22e.pdf
21. Thakre A, Rajak TK. Utilization of Waste Sole Leather with Fly Ash for Self-Compacting Concrete. IOP Conf Ser Earth Environ Sci. Institute of Physics; 2022. https://doi.org/10.1088/1755-1315/1032/1/012002
22. Litu M, Ali MF, Shabur MA, Taimullah M, Arnob FM. Utilization of chromium tanned leather waste in cementitious and gypsum composites for sustainable construction materials. Discover Sustainability. Springer Nature; 2025;6. https://doi.org/10.1007/s43621-025-01040-z
23. Canhada JCS, Paiva FFG, Shinohara GMM, Okimoto F, Hiranobe CT, Teixeira SR, et al. Production of new concrete with leather tannery waste used as partial replacement of the natural sand. J Mater Cycles Waste Manag. Springer; 2023;25:944–53. https://doi.org/10.1007/s10163-022-01586-4
24. Mohamed S, Elemam H, Seleem MH, Sallam HEDM. Effect of fiber addition on strength and toughness of rubberized concretes. Sci Rep. Nature Research; 2024;14. https://doi.org/10.1038/s41598-024-54763-w
25. Liu Q, Hou F, Ge D, Lv S, Ju Z. Study on Performance and Aging Mechanism of Rubber-Modified Asphalt Under Variable-Intensity UV Aging. Materials. Multidisciplinary Digital Publishing Institute (MDPI); 2025;18. https://doi.org/10.3390/ma18133186
26. Chauhan VS, Sadique MdR, Alam MohdM, Farooqi MohdA. Development of a reliable rock slope stability model utilizing field and analytical data – An integration of FE-ML approaches. Artificial Intelligence in Geosciences. 2025;6:100158. https://doi.org/10.1016/j.aiig.2025.100158
27. Dindar S, Akyurt SE, Sorgun M. A novel nonlinear regression equation for predicting critical flow velocity in slurry transport: A comparative study with advanced machine learning methods and classical empirical correlations. Powder Technol. 2026;467:121604. https://doi.org/10.1016/j.powtec.2025.121604
28. Strielkowski W, Vlasov A, Selivanov K, Muraviev K, Shakhnov V. Prospects and Challenges of the Machine Learning and Data-Driven Methods for the Predictive Analysis of Power Systems: A Review. Energies (Basel). 2023;16:4025. https://doi.org/10.3390/en16104025
29. Tang Y, Kurths J, Lin W, Ott E, Kocarev L. Introduction to Focus Issue: When machine learning meets complex systems: Networks, chaos, and nonlinear dynamics. Chaos: An Interdisciplinary Journal of Nonlinear Science. 2020;30. https://doi.org/10.1063/5.0016505
30. Nafiuzzaman Md, Jakir TI, Aditi IJ, Kabir A, Ahsan KA. Different machine learning approaches to predict the compressive strength of composite cement concrete. Journal of Building Pathology and Rehabilitation. 2025;10:88. https://doi.org/10.1007/s41024-025-00598-5
31. Song Y, Zhao J, Ostrowski KA, Javed MF, Ahmad A, Khan MI, et al. Prediction of Compressive Strength of Fly-Ash-Based Concrete Using Ensemble and Non-Ensemble Supervised Machine-Learning Approaches. Applied Sciences. 2021;12:361. https://doi.org/10.3390/app12010361
32. Shaaban M, Amin M, Selim S, Riad IM. Machine learning approaches for forecasting compressive strength of high-strength concrete. Sci Rep. 2025;15:25567. https://doi.org/10.1038/s41598-025-10342-1
33. Ahmad SA, Ahmed HU, Rafiq SK, Ahmad DA. Machine learning approach for predicting compressive strength in foam concrete under varying mix designs and curing periods. Smart Construction and Sustainable Cities. 2023;1:16. https://doi.org/10.1007/s44268-023-00021-3
34. Ziolkowski P, Niedostatkiewicz M. Machine Learning Techniques in Concrete Mix Design. Materials. 2019;12:1256. https://doi.org/10.3390/ma12081256
35. Du K-L, Jiang B, Lu J, Hua J, Swamy MNS. Exploring Kernel Machines and Support Vector Machines: Principles, Techniques, and Future Directions. Mathematics. 2024;12:3935. https://doi.org/10.3390/math12243935
36. Kanat G, Yıldız Avşar E, Palanisamy S, Ashori A. Utilizing waste manhole covers and fibreboard as reinforcing fillers for thermoplastic composites. Journal of Reinforced Plastics and Composites. 2024;44:1108–18. https://doi.org/10.1177/07316844241238507
37. Manickaraj K, Thirumalaisamy R, Palanisamy S, Ayrilmis N, Massoud EES, Palaniappan M, et al. Value-added utilization of agricultural wastes in biocomposite production: Characteristics and applications. Ann. N. Y. Acad. Sci. John Wiley and Sons Inc; 2025. p. 72–91. https://doi.org/10.1111/nyas.15368
38. Mylsamy B, Aruchamy K, Marudhamuthu Shanmugam SK, Palanisamy S, Ayrilmis N. Improving performance of composites: Natural and synthetic fibre hybridisation techniques in composite materials – A review. Mater Chem Phys [Internet]. 2025;334:130439. https://doi.org/https://doi.org/10.1016/j.matchemphys.2025.130439

Ahead of Print Subscription Original Research
Volume 14
03
Received 10/03/2026
Accepted 25/03/2026
Published 08/05/2026
Publication Time 59 Days
1

Login


My IP

PlumX Metrics