DATA-DRIVEN PREDICTION OF CONCRETE COMPRESSIVE STRENGTH
DOI:
https://doi.org/10.69980/6w4tee68Keywords:
Concrete compressive strength, data-driven prediction, multiple regression , concrete mix design, model validationAbstract
Concrete compressive strength is a critical indicator of structural performance and material quality, but conventional laboratory testing is time-consuming and unsuitable for rapid preliminary assessment. This study developed an interpretable data-driven model for predicting concrete compressive strength. The UCI Concrete Compressive Strength Dataset initially contained 1,030 observations; after removing 25 duplicate records, 1,005 unique observations were analysed. Descriptive, correlation, and multiple regression analyses were conducted, followed by an 80:20 training-testing validation. The model was statistically significant and explained 60.4% of the variation in compressive strength. Cement was the strongest positive predictor, followed by blast-furnace slag, curing age, and fly ash, whereas water showed a significant negative effect. The testing model achieved an R2of 0.580, a mean absolute error of 8.90 MPa, and a root mean squared error of 11.19 MPa. The findings demonstrate that concrete strength can be estimated with moderate accuracy using readily available mixture variables. However, the remaining unexplained variation indicates that curing conditions, cement grade, aggregate characteristics, and testing factors should be incorporated in future models. The proposed approach can support preliminary mix evaluation but should complement rather than replace laboratory testing.
References
1.Altuncı, Y. T. (2024). A comprehensive study on the estimation of concrete compressive strength using machine learning models. Buildings, 14(12), 3851.
2.Ben Chaabene, W., Flah, M., & Nehdi, M. L. (2020). Machine learning prediction of mechanical properties of concrete: Critical review. Construction and Building Materials, 260, 119889.
3.Khan, A. Q., Muhammad, S. G., Raza, A., Chaimahawan, P., & Pimanmas, A. (2025). Advanced machine learning techniques for predicting compressive strength of ultra-high-performance concrete. Frontiers of Structural and Civil Engineering, 19(4), 503–523.
4.Kim, J., & Lee, D. (2025). Comparative study on hyperparameter tuning for predicting concrete compressive strength. Buildings, 15(13), 2173.
5.Kumar, M., Biswas, R., Kumar, D. R., Samui, P., Kaloop, M. R., & Eldessouki, M. (2023). Soft computing-based prediction models for compressive strength of concrete. Case Studies in Construction Materials, 19, e02321.
6.Kumar, R., Althaqafi, E., Patro, S. G. K., Simic, V., Babbar, A., Pamucar, D., Singh, S. K., & Verma, A. (2024). Machine and deep learning methods for concrete strength prediction: A bibliometric and content analysis review of research trends and future directions. Applied Soft Computing, 164, 111956.
7.Lan, W. (2024). Accurate compressive strength prediction using machine learning algorithms and optimization techniques. Journal of Engineering and Applied Science, 71, Article 1.
8.Li, P., Zhang, Z., & Gu, J. (2024). Prediction of concrete compressive strength based on ISSA-BPNN-AdaBoost. Materials, 17(23), 5727.
9.Liu, G., & Sun, B. (2023). Concrete compressive strength prediction using an explainable boosting machine model. Case Studies in Construction Materials, 18, e01845.
10.Loureiro, A. A. B., & Stefani, R. (2024). Comparing the performance of machine learning models for predicting the compressive strength of concrete. Discover Civil Engineering, 1, Article 19.
11.Malhotra, K., Mishra, D., & Tumrate, C. S. (2023). Prediction of concrete compressive strength employing machine learning techniques. Materials Today: Proceedings. Advance online publication.
12.Mandal, S., Shiuly, A., Sau, D., Mondal, A. K., & Sarkar, K. (2024). Study on the use of different machine learning techniques for prediction of concrete properties from their mixture proportions with their deterministic and robust optimisation. AI in Civil Engineering, 3, Article 7.
13.Moein, M. M., Saradar, A., Rahmati, K., Ghasemzadeh Mousavinejad, S. H., Bristow, J., Aramali, V., & Karakouzian, M. (2023). Predictive models for concrete properties using machine learning and deep learning approaches: A review. Journal of Building Engineering, 63, 105444.
14.Muhammad, U. J., Aminu, I. I., Mahmoud, I. A., Aliyu, U. U., Usman, A. G., Jibril, M. M., Malami, S. I., & Abba, S. I. (2024). An improved prediction of high-performance concrete compressive strength using ensemble models and neural networks. AI in Civil Engineering, 3(1), Article 21.
15.Murthy, M. N., Amruth, S. K., Marulasiddappa, S. B., & Naganna, S. R. (2024). Modeling the compressive strength of binary and ternary blended high-performance concrete mixtures using ensemble machine learning models. Soft Computing, 28, 6683–6693.
16.Nikoopayan Tak, M. S., Feng, Y., & Mahgoub, M. (2025). Advanced machine learning techniques for predicting concrete compressive strength. Infrastructures, 10(2), 26.
17.Núñez, I., Marani, A., Flah, M., & Nehdi, M. L. (2021). Estimating compressive strength of modern concrete mixtures using computational intelligence: A systematic review. Construction and Building Materials, 310, 125279.
18.Sah, A. K., & Hong, Y.-M. (2024). Performance comparison of machine learning models for concrete compressive strength prediction. Materials, 17(9), 2075.
19.Sathiparan, N., Jeyananthan, P., & Subramaniam, D. N. (2023). Prediction of compressive strength of fly ash blended pervious concrete: A machine learning approach. International Journal of Pavement Engineering, 24(2), Article 2287146.
20.Shrivastava, S., & Shrivastava, T. (2024). Prediction of concrete’s compressive strength using machine learning algorithms. Materials Today: Proceedings, 103, 183–189.
21.Terlumun, S., Onyia, M. E., & Okafor, F. O. (2024). Predicting the compressive strength of self-compacting concrete using artificial intelligence techniques: A review. AI in Civil Engineering, 3, Article 14.
22.Vargas, J. F., Oviedo, A. I., Ortega, N. A., Orozco, E., Gómez, A., & Londoño, J. M. (2024). Machine-learning-based predictive models for compressive strength, flexural strength, and slump of concrete. Applied Sciences, 14(11), 4426.
23.Xiao, K., Zhang, H., Wei, S., Zhu, C., He, J., Zhu, S., & Yang, X. (2025). Prediction of compressive strength of high-performance concrete based on multiple machine learning models. Frontiers in Materials, 12, 1698248.
24.Yang, S., Sun, J., & Zhifeng, X. (2024). Prediction on compressive strength of recycled aggregate self-compacting concrete by machine learning method. Journal of Building Engineering, 88, 109055.
25.Yu, G., Zhu, S., & Xiang, Z. (2024). The prediction of pervious concrete compressive strength based on a convolutional neural network. Buildings, 14(4), 907.
26.Zhou, R., Tang, Y., Li, H., & Liu, Z. (2024). Predicting the compressive strength of ultra-high-performance concrete using a decision tree machine learning model enhanced by the integration of two optimization meta-heuristic algorithms. Journal of Engineering and Applied Science, 71, Article 43.
27.Ziółkowski, P. (2025). Influence of optimization algorithms and computational complexity on concrete compressive strength prediction machine learning models for concrete mix design. Materials, 18(6), 1386.
