Concrete strength prediction: Exploring an ensemble machine learning approach
Younes Alouan, Seif-Eddine Cherif, Badreddine Kchakech, Youssef Cherradi, Azzouz Kchikach
Abstract. The mechanical properties of concrete depend on a number of variables, which include the water cement ratio, the properties of materials, and the curing method. Recently, there has been an interest in the use of artificial intelligence (AI) methods. The current investigation utilized a number of Machine Learning (ML) models, including SVR, ANN, RFR, AdaBoost, XGBoost, and GBM, for making predictions of the compressive strength of concrete. The models considered in this investigation could offer accurate values. The data was collected from previous studies, which provided information on 1030 concrete samples. These samples were spread over a wide range of mix proportions and curing ages, thus guaranteeing good generalization capability of the models. The comparison of conventional models with ensembled models showed that there was a marked difference in favor of ensembled models after hyperparameter optimization. The R² value of XGBoost was seen to be 0.94 with a MAPE of 10.4% that was almost equal to the ANN model, while the R² value was seen to be 0.89 for the SVR.
Keywords
Concrete, Compressive Strength, Artificial intelligence, Machine Learning Algorithms, Ensemble Learning
Published online 1/10/2026, 8 pages
Copyright © 2026 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: Younes Alouan, Seif-Eddine Cherif, Badreddine Kchakech, Youssef Cherradi, Azzouz Kchikach, Concrete strength prediction: Exploring an ensemble machine learning approach, Materials Research Proceedings, Vol. 58, pp 9-16, 2026
DOI: https://doi.org/10.21741/9781644903933-2
The article was published as article 2 of the book Emerging Research in Materials for Environment, and Civil Infrastructure
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] D. M. Frangopol and M. Soliman, “Life-cycle of structural systems: recent achievements and future directions,” Structure and Infrastructure Engineering, vol. 12, no. 1, 2016. https://doi.org/10.1080/15732479.2014.999794
[2] H. Sun, H. V. Burton, and H. Huang, “Machine learning applications for building structural design and performance assessment: State-of-the-art review,” Jan. 01, 2021, Elsevier Ltd. https://doi.org/10.1016/j.jobe.2020.101816
[3] M. Mohtasham Moein et al., “Predictive models for concrete properties using machine learning and deep learning approaches: A review,” Jan. 01, 2023, Elsevier Ltd. https://doi.org/10.1016/j.jobe.2022.105444
[4] I. Nunez and M. L. Nehdi, “Machine learning prediction of carbonation depth in recycled aggregate concrete incorporating SCMs,” Constr Build Mater, vol. 287, Jun. 2021. https://doi.org/10.1016/j.conbuildmat.2021.123027
[5] G. N. Kumar and G. V. V. Satyanarayana, “Strength and durability properties of quaternary blended high strength concrete,” in E3S Web of Conferences, EDP Sciences, Jun. 2023. https://doi.org/10.1051/e3sconf/202339101205
[6] J. Huang, M. M. S. Sabri, D. V. Ulrikh, M. Ahmad, and K. A. M. Alsaffar, “Predicting the Compressive Strength of the Cement-Fly Ash–Slag Ternary Concrete Using the Firefly Algorithm (FA) and Random Forest (RF) Hybrid Machine-Learning Method,” Materials, vol. 15, no. 12, Jun. 2022. https://doi.org/10.3390/ma15124193
[7] I. C. Yeh, “Modeling of strength of high-performance concrete using artificial neural networks,” Cem Concr Res, vol. 28, no. 12, pp. 1797–1808, 1998. https://doi.org/10.1016/S0008-8846(98)00165-3
[8] Y. Xu et al., “Computation of high-performance concrete compressive strength using standalone and ensembled machine learning techniques,” Materials, vol. 14, no. 22, Nov. 2021. https://doi.org/10.3390/ma14227034
[9] A. Qayyum Khan, H. Ahmad Awan, M. Rasul, Z. Ahmad Siddiqi, and A. Pimanmas, “Optimized artificial neural network model for accurate prediction of compressive strength of normal and high strength concrete,” Cleaner Materials, vol. 10, Dec. 2023. https://doi.org/10.1016/j.clema.2023.100211
[10] H. V. T. Mai, T. A. Nguyen, H. B. Ly, and V. Q. Tran, “Prediction Compressive Strength of Concrete Containing GGBFS using Random Forest Model,” Advances in Civil Engineering, vol. 2021, 2021. https://doi.org/10.1155/2021/6671448
[11] W. Wang, Y. Zhong, G. Liao, Q. Ding, T. Zhang, and X. Li, “Prediction of Compressive Strength of Concrete Specimens Based on Interpretable Machine Learning,” Materials, vol. 17, no. 15, Aug. 2024. https://doi.org/10.3390/ma17153661
[12] D. C. Feng et al., “Machine learning-based compressive strength prediction for concrete: An adaptive boosting approach,” Constr Build Mater, vol. 230, Jan. 2020. https://doi.org/10.1016/j.conbuildmat.2019.117000
[13] A. H. A. Ahmed, W. Jin, and M. A. H. Ali, “Prediction of compressive strength of recycled concrete using gradient boosting models,” Ain Shams Engineering Journal, vol. 15, no. 9, p. 102975, Sep. 2024. https://doi.org/10.1016/J.ASEJ.2024.102975
