Machine Learning-Based Forecasting of Compressive Strength for Ambient-Cured GGBS Geopolymer Concrete

Mithesh Kumar, Amar R, Devanand R, Chethan B A, Harsha H N, Guruprasad M. Hugar

Abstract

Geopolymer concrete is gaining attention as a sustainable alternative to Ordinary Portland Cement (OPC) concrete because of its lower carbon emissions and improved durability. However, predicting the compressive strength of Ground Granulated Blast Furnace Slag (GGBS)-based geopolymer concrete under ambient curing remains difficult due to the complex and non-linear effects of mix proportions and curing parameters. This study addresses that problem by developing machine learning models to predict the compressive strength of M25 grade GGBS-based geopolymer concrete using a dataset of 80 laboratory-tested samples, supplemented with published data. The input variables included NaOH molarity, aggregate proportions, activator-to-binder ratio, additional water content, activator composition, and curing age. A multi-layer feed-forward Artificial Neural Network (ANN) and Linear Regression (LR) model were developed in Python after normalizing all inputs using min-max scaling. Model performance was evaluated using Mean Absolute Error (MAE), coefficient of determination (R²), and Root Mean Squared Error (RMSE). The ANN model outperformed LR, achieving an MAE of 2.15 N/mm², R² of 0.951, and RMSE of 2.89 N/mm², compared with an MAE of 3.24 N/mm², R² of 0.923, and RMSE of 4.18 N/mm² for LR. Sensitivity analysis showed that curing age, NaOH molarity, and activator-to-binder ratio were the most influential factors governing strength development. The results confirm that ANN-based prediction can accurately estimate compressive strength while reducing experimental effort and supporting sustainable mix design.

Keywords

References

[1] U. N. Environment, K. L. Scrivener, V. M. John, and E. M. Gartner, “Eco-efficient cements: Potential economically viable solutions for a low-CO2 cement-based materials industry,” Cement and Concrete Research, vol. 114, pp. 2–26, 2018, doi:10.1016/j.cemconres.2018.03.015.

[2] J. L. Provis, “Alkali-activated materials,” Cement and Concrete Research, vol. 114, pp. 40–48, 2018, doi: 10.1016/j.cemconres.2017.02.009.

[3] C. Shi, D. Roy, and P. Krivenko, Alkali-Activated Cements and Concretes. Boca Raton, FL, USA: CRC Press, 2003.

[4] H. Khosravi and M. Bahram, “Prediction of geopolymer concrete compressive strength using artificial neural network and genetic algorithm,” Results in Engineering, vol. 27, Art. no. 105537, 2025, doi:10.1016/j.rineng.2025.105537.

[5] M. Abuhussain, A. Ahmad, M. Amin, F. Althoey, Y. Gamil, and T. Najeh, “Data-driven approaches for strength prediction of alkali-activated composites,” Case Studies in Construction Materials, vol. 20, Art. no. e02920, Feb. 2024, doi: 10.1016/j.cscm.2024.e02920.

[6] I.-C. Yeh, “Modeling of strength of high-performance concrete using artificial neural networks,” Cement and Concrete Research, vol. 28, no. 12, pp. 1797–1808, 1998, doi:10.1016/S0008-8846(98)00165-3.

[7] M. M. Islam, M. A.-M. Provath, G. M. Sadiqul Islam, and M. T. Islam, “Strength prediction of geopolymer concrete with wide‐ranged binders and properties using artificial neural network,” Advances in Civil Engineering, vol. 2024, no. 1, Art. no. 8534390, 2024, doi: 10.1155/adce/8534390.

[8] F. Rehman, S. A. Khokhar, and R. A. Khushnood, “ANN based predictive mimicker for mechanical and rheological properties of eco-friendly geopolymer concrete,” Case Studies in Construction Materials, vol. 17, Art. no. e01536, 2022, doi:10.1016/j.cscm.2022.e01536.

[9] X. Qin, Q. Ma, R. Guo, Z. Song, Z. Lin, and H. Zhou, “Compressive strength prediction of alkali‐activated slag concretes by using artificial neural network (ANN) and alternating conditional expectation (ACE),” Advances in Civil Engineering, vol. 2022, no. 1, Art. no. 8214859, 2022, doi: 10.1155/2022/8214859.

[10] H. Tanyildizi, “Deep learning–based prediction of compressive strength of eco-friendly geopolymer concrete,” Environmental Science and Pollution Research, vol. 31, no. 28, pp. 41246–41266, 2024.

[11] G.-H. Fang, Z.-M. Lin, C.-Z. Xie, Q.-Z. Han, M.-Y. Hong, and X.-Y. Zhao, “Optimized machine learning model for predicting compressive strength of alkali-activated concrete through multi-faceted comparative analysis,” Materials, vol. 17, no. 20, Art. no. 5086, 2024, doi: 10.3390/ma17205086.

[12] S. Philip and N. Marakkath, “Compressive strength prediction and feature analysis for GGBS-Based geopolymer concrete using optimized XGBoost and SHAP: A comparative study of optimization algorithms and experimental validation,” Journal of Building Engineering, vol. 108, Art. no. 112879, 2025, doi: 10.1016/j.jobe.2025.112879.

[13] H. U. Ahmed, A. A. Mohammed, and A. Mohammed, “Soft computing models to predict the compressive strength of GGBS/FA-geopolymer concrete,” PLoS One, vol. 17, no. 5, Art. no. e0265846, 2022, doi: 10.1371/journal. pone.0265846.

[14] Ground Granulated Blast Furnace Slag for Use in Cement, Mortar and Concrete – Specification, IS 16714, Bureau of Indian Standards, New Delhi, India, 2018.

[15] Coarse and Fine Aggregate for Concrete – Specification, IS 383, Bureau of Indian Standards, New Delhi, India, 2016.

[16] Methods of Testing Aggregates for Concrete – Part 3: Specific Gravity, Density, Voids, Absorption, and Bulking, IS 2386 (Part 3), Bureau of Indian Standards, New Delhi, India, 1963.

[17] M. A. M. Morsy, S. A. Saleh, A. H. Shalan, “Experimental verification for machine-learning approaches in compressive strength prediction of alkali-activated concrete,” Journal of Structural Design and Construction Practice, vol. 30, no. 1, Art. no. 04023058, 2024, doi: 10.1061/JSDCCC.SCENG-1565.

[18] Methods of Test for Aggregates for Concrete – Part 4: Mechanical Properties, IS 2386 (Part 4), Bureau of Indian Standards, New Delhi, India, 1963.

[19] R. Cao, Z. Fang, M. Jin, and Y. Shang, “Application of machine learning approaches to predict the strength property of geopolymer concrete,” Materials, vol. 15, no. 7, Art. no. 2400, 2022, doi: 10.3390/ma15072400.

[20] Methods of Tests for Strength of Concrete, IS 516, Bureau of Indian Standards, New Delhi, India, 1959.

[21] Y. Dodo, K. Arif, M. Alyami, M. Ali, T. Najeh, and Y. Gamil, “Estimation of compressive strength of waste concrete utilizing fly ash/slag in concrete with interpretable approaches: optimization and graphical user interface (GUI),” Scientific Reports, vol. 14, no. 1, Art. no. 4598, 2024, doi: 10.1038/s41598-024-54513-y.

[22] G. K. Arunvivek, S. Anandaraj, P. Kumar, B. Pratap, and R. Y. Sembeta, “Compressive strength modelling of cenosphere and copper slag-based geopolymer concrete using deep learning model,” Scientific Reports, vol. 15, no. 1, Art. no. 27849, 2025, doi:10.1038/s41598-025-13176-z.

[23] T. Gupta and M. C. Rao, “Prediction of compressive strength of geopolymer concrete using machine learning techniques,” Structural Concrete, vol. 23, no. 5, pp. 3073–3090, 2022, doi: 10.1002/suco.202100354.

[24] H. Taghavizade Zahiri and H. Tanyildizi, “Application of ANN & ANFIS models in determining compressive strength of concrete,” Journal of Soft Computing in Civil Engineering, vol. 2, no. 1, pp. 62–70, 2018, doi: 10.22115/ scce.2018.51114.

[25] H. X. Mohammed, A. S. Mohammed, and A. M. T. Hassan, “Soft computing models to evaluate the effect of fly ash and ground granulated blast furnace slag (GGBS) on the compressive strength of concrete in normal and high strength ranges,” Structures, vol. 58, Art. no. 105459, 2023, doi:10.1016/j.istruc.2023.105459.

[26] A. M. Alnadish, M. Hamza, S. Ali, N. Murad, and S. M. K. Durrani, “Machine learning–driven optimization of compressive and tensile strength in concrete with GGBS, eggshell powder, and waste glass powder,” Scientific Reports, vol. 15, no. 1, Art. no. 40499, 2025, doi:10.1038/s41598-025-24438-1.

[27] G. X. K. Ramujee and P. Sadula, “Prediction of geopolymer concrete compressive strength using convolutional neural networks,” Computer Modeling in Engineering & Sciences, vol. 139, no. 2, pp. 1921–1940, 2024, doi: 10.32604/cmes.2023.043384.

Full Text: PDF

DOI: 10.14416/j.asep.2026.07.013

Refbacks

There are currently no refbacks.

Username
Password
Remember me

Applied Science and Engineering Progress