Prediction of the Compressive Strength of Graphene Oxide-Containing Concrete Using Machine Learning Models and a Deep Neural Network
Keywords:
graphene oxide, nano-engineered concrete, compressive strength, Machine Learning, deep neural network, data augmentationAbstract
The aim of this study was to develop a comparative computational framework for predicting the compressive strength of control and additive-modified concrete mixtures and to compare the performance of six algorithms with different levels of complexity. The dataset comprised 27 actual laboratory observations from three mixture families, C0, CG, and CP, evaluated at ages of 7, 28, and 90 days with three replicates for each condition. To prevent information leakage and obtain a more realistic estimate of model generalizability, each mixture type-age combination was treated as an independent group, and the models were evaluated using three-fold group cross-validation. In each fold, 18 actual observations were allocated for training and 9 for testing. Data augmentation was applied exclusively to the training set, and five synthetic samples were generated for each actual observation using controlled Gaussian perturbation. After removing variables with no variability, three features-sample age, graphene oxide content, and the recorded polymer-modifier content-were retained as effective modeling variables. Out-of-fold prediction results showed that support vector regression achieved the best performance among the evaluated models, with a coefficient of determination of 0.771, a root mean squared error of 2.059 MPa, and a mean absolute error of 1.641 MPa, followed by gradient boosting and linear regression. The Friedman test, based on the mean errors of the nine independent groups, confirmed a statistically significant overall difference among the models (χ² = 27.159, p < 0.001). In addition, the Wilcoxon test with Holm correction showed that the superiority of support vector regression over the deep neural network, Extra Trees, and Random Forest was statistically significant; however, its differences from linear regression and gradient boosting were not significant after multiple-comparison correction. Permutation importance analysis for the support vector regression model further showed that the recorded polymer-modifier content, sample age, and graphene oxide content accounted for approximately 57.0%, 30.1%, and 12.9%, respectively, of the performance degradation caused by feature permutation. Overall, the findings indicate that, in small datasets, proper validation design, prevention of information leakage, and group-based evaluation play a more decisive role in obtaining reliable predictions than merely increasing model complexity.
Downloads
References
1. Udumulla, D., Ginigaddara, T., Jayasinghe, T., Mendis, P., & Baduge, S. (2024). Effect of Graphene Oxide Nanomaterials on the Durability of Concrete: A Review on Mechanisms, Provisions, Challenges, and Future Prospects. Materials, 17(10), 2411. https://doi.org/10.3390/ma17102411
2. Hu, Z. Y., Wan, Y., Duan, Y. J., Shi, Y. H., Gu, C. P., Ma, R., Dong, J. J., & Cui, D. (2025). A Review of the Impact of Graphene Oxide on Cement Composites. Nanomaterials, 15(3), 216. https://doi.org/10.3390/nano15030216
3. Fonseka, I., Mohotti, D., Wijesooriya, K., Lee, C. K., & Mendis, P. (2024). Influence of graphene oxide properties, superplasticiser type, and dispersion technique on mechanical performance of graphene oxide-added concrete. Construction and Building Materials, 428, 136415. https://doi.org/10.1016/j.conbuildmat.2024.136415
4. Zhang, R., Long, Z., Long, G., Wang, J., Wang, X., Zhang, X., & Jiang, Y. (2024). Mechanism of graphene oxide concrete macro-micro properties evolution under large temperature difference freeze-thaw action. Construction and Building Materials, 415, 135019. https://doi.org/10.1016/j.conbuildmat.2024.135019
5. Lu, D., Qu, F., Punetha, P., Zeng, X., Luo, Z., & Li, W. (2024). Graphene oxide nano-engineered recycled aggregate concrete for sustainable construction: A critical review. Developments in the Built Environment, 18, 100444. https://doi.org/10.1016/j.dibe.2024.100444
6. Wang, Q., Zhao, H., Luo, Z., Liu, S., Zhou, C., & Liu, H. (2024). Properties evaluation of concrete made with recycled coarse aggregate modified by graphene oxide. Journal of Building Engineering, 84, 108546. https://doi.org/10.1016/j.jobe.2024.108546
7. Devapura, P., Ginigaddara, T., Udumulla, D., Mendis, P., Booy, M., & Herath, N. (2025). Effect of graphene oxide on interfacial transition zone and strength enhancement of recycled aggregate concrete. Journal of Building Engineering, 105, 112570. https://doi.org/10.1016/j.jobe.2025.112570
8. Cheng, S., Chen, K., Wu, Q., Chen, X., Zhao, C., & Wu, Z. (2024). Influence of industrial-grade graphene oxide on macro and micro properties of ultra-high performance concrete incorporating recycled fine aggregate. Construction and Building Materials, 417, 135427. https://doi.org/10.1016/j.conbuildmat.2024.135427
9. Mao, K., Yu, J., Yang, B., Liu, H., Shen, L., Elchalakani, M., & Alqawzai, S. (2024). Mechanical properties of graphene oxide modified ultra-high-performance concrete containing coarse aggregate. Journal of Building Engineering, 86, 108754. https://doi.org/10.1016/j.jobe.2024.108754
10. He, T., Xie, W., Wang, F., Yu, Z., Xu, F., Li, J., Deng, Y., Ding, Q., Hao, Y., Xu, W., & Yu, H. (2024). A Study on the Mechanism by Which Graphene Oxide Affects the Macroscopic Properties and Microstructure of Abrasion-Resistant Ultra-High-Performance Concrete (UHPC). Coatings, 14(12), 1482. https://doi.org/10.3390/coatings14121482
11. You, X. M., Zhang, J., Zhong, J., Fu, B., & Yu, T. (2024). Properties of ultra-high-performance concrete with recycled macro fibers: Effects of fiber coating with graphene oxide. Construction and Building Materials, 456, 139283. https://doi.org/10.1016/j.conbuildmat.2024.139283
12. Ali, I., Burakova, I. V., Burakov, A. E., Aljaboobi, D. Z. M., Yarkin, V. O., Tkachev, A. G., Bentalib, A., & Imanova, G. (2024). Use of macromolecules lignosulfonate and graphene oxide to prepare non-autoclaved aerated concrete. International Journal of Biological Macromolecules, 282, 136763. https://doi.org/10.1016/j.ijbiomac.2024.136763
13. Rao, P. T., Prakash, J., Alexander, R., Shinde, M. J., & Dasgupta, K. (2024). Role of graphene oxide infusion in concrete to elevate strength and fire performance in construction concrete. Diamond and Related Materials, 147, 111269. https://doi.org/10.1016/j.diamond.2024.111269
14. Bai, E., Wang, Z., Du, Y., Ren, B., & Liu, C. (2024). Mechanical properties and strain rate effect of graphene oxide grafted carbon fiber modified concrete under dynamic impact load. Construction and Building Materials, 445, 137978. https://doi.org/10.1016/j.conbuildmat.2024.137978
15. Antolín-Rodríguez, A., Merino-Maldonado, D., Fernández-Raga, M., González-Domínguez, J. M., Morán-del Pozo, J. M., García-González, J., & Juan-Valdés, A. (2024). Microstructural, durability and colorimetric properties of concrete coated with a controlled application of graphene oxide. Journal of Building Engineering, 86, 108920. https://doi.org/10.1016/j.jobe.2024.108920
16. Antolín-Rodríguez, A., Merino-Maldonado, D., González-Domínguez, J. M., Fernández-Raga, M., Morán-del Pozo, J. M., García-González, J., & Juan-Valdés, A. (2024). Performance of graphene oxide as a water-repellent coating nanomaterial to extend the service life of concrete structures. Heliyon, 10(1), e23969. https://doi.org/10.1016/j.heliyon.2023.e23969
17. Xiong, B., Zhang, L., Lu, X., Tian, B., Yan, P., Li, Q., Li, M., & Wu, K. (2025). Research on the mechanism of graphene oxide in enhancing the resistance of concrete to chloride salt erosion. Construction and Building Materials, 487, 142108. https://doi.org/10.1016/j.conbuildmat.2025.142108
18. Djenaoucine, L., Argiz, C., Picazo, Á., Moragues, A., & Gálvez, J. C. (2025). The corrosion-inhibitory influence of graphene oxide on steel reinforcement embedded in concrete exposed to a 3.5M NaCl solution. Cement and Concrete Composites, 155, 105835. https://doi.org/10.1016/j.cemconcomp.2024.105835
19. Kumar, S., Bheel, N., Zardari, S., Alraeeini, A. S., Almaliki, A. H., & Benjeddou, O. (2024). Effect of graphene oxide on mechanical, deformation and drying shrinkage properties of concrete reinforced with fly ash as cementitious material by using RSM modelling. Scientific Reports, 14(1), 18675. https://doi.org/10.1038/s41598-024-69601-2
20. Udeze, O. J., Mohammed, B. S., Adebanjo, A. U., & Abdulkadir, I. (2024). Optimizing an eco-friendly high-density concrete for offshore applications: A study on fly ash partial replacement and graphene oxide nano reinforcement. Case Studies in Chemical and Environmental Engineering, 9, 100592. https://doi.org/10.1016/j.cscee.2023.100592
21. Fonseka, I., Mohotti, D., Wijesooriya, K., Lee, C. K., & Mendis, P. (2025). Evaluating the performance of cement-reduced concrete using graphene oxide: Synergistic effects on mechanical properties. Results in Engineering, 26, 104742. https://doi.org/10.1016/j.rineng.2025.104742
22. Domínguez-Santos, D., Muñoz, P., Morales-Ferreiro, J. O., Acuña, C., Diaz-Droguett, D. E., & Villaro, E. (2025). Reinforced Concrete with Graphene Oxide: Techno-Economic Feasibility for Reduced Cement Usage and CO2 Emissions. International Journal of Concrete Structures and Materials, 19(1), 52. https://doi.org/10.1186/s40069-025-00793-1
23. Meddage, D. P. P., Fonseka, I., Mohotti, D., Wijesooriya, K., & Lee, C. K. (2024). An explainable machine learning approach to predict the compressive strength of graphene oxide-based concrete. Construction and Building Materials, 449, 138346. https://doi.org/10.1016/j.conbuildmat.2024.138346
24. Yang, J., Zeng, B., Ni, Z., Fan, Y., Hang, Z., Wang, Y., Feng, C., & Yang, J. (2023). Comparison of traditional and automated machine learning approaches in predicting the compressive strength of graphene oxide/cement composites. Construction and Building Materials, 394, 132179. https://doi.org/10.1016/j.conbuildmat.2023.132179
25. Montazerian, A., Baghban, M. H., Ramachandra, R., & Goutianos, S. (2023). A machine learning approach for assessing the compressive strength of cementitious composites reinforced by graphene derivatives. Construction and Building Materials, 409, 134014. https://doi.org/10.1016/j.conbuildmat.2023.134014
26. Zhu, J. H., Yao, Z., & Pei, C. (2023). Deep mining the mechanical behavior of graphene oxide–cement composites using data-driven artificial intelligence techniques. Construction and Building Materials, 408, 133668. https://doi.org/10.1016/j.conbuildmat.2023.133668
