MODELLING THE COMPRESSIVE STRENGTH OF COSTUS AFER-MODIFIED FLY ASH GEOPOLYMER CONCRETE AS A FUNCTION OF CURING TEMPERATURE, ACTIVATOR RATIO, AND NAOH CONCENTRATION
DOI:
https://doi.org/10.60787/jnamp.vol73no.755Keywords:
Water saturation,, ensemble model, neural network, well log, MATLAB, core data, learning, reservoirAbstract
The use of geopolymer concrete as a sustainable alternative to ordinary Portland cement concrete has increased, but predicting its compressive strength remains challenging due to complex interactions among mix and curing parameters. This study developed Multilinear Regression (MLR) and Random Forest (RF) models to predict the compressive strength of Costus afer modified fly ash geopolymer concrete using curing temperature, activator ratio, and sodium hydroxide concentration. Model performance was evaluated using R², MAE, MSE, and MAPE. The RF model outperformed MLR, achieving R² values of 0.9898 and 0.9882 for training and testing, respectively, with testing MAE, MSE, and MAPE of 1.3396 MPa, 2.2104 MPa², and 6.11%. Feature importance analysis identified curing temperature as the most influential parameter, followed by activator ratio, while sodium hydroxide concentration had the least effect. The RF model offers a reliable tool for strength prediction and mixture optimization.
Downloads
References
UN Environment, Scrivener, K.L., John, V.M. and Gartner, E.M. (2018). Eco-efficient cements: Potential economically viable solutions for a low-CO2 cement-based materials industry. Cement and concrete Research, 114, pp.2-26.
Abiodun, Y.O., Olanrewaju, O.A., Gbenebor, O.P., Ochulor, E.F., Obasa, D.V. and Adeosun, S.O. (2022). Cutting cement industry CO2 emissions through metakaolin use in construction. Atmosphere, 13(9), p.1494.
Marandi, N. and Shirzad, S. (2025). Sustainable cement and concrete technologies: A review of materials and processes for carbon reduction. Innovative Infrastructure Solutions, 10(9), p.408.
Horan, C., Genedy, M., Juenger, M. and van Oort, E. (2022). Fly Ash-based Geopolymers as lower carbon footprint alternatives to Portland cement for well cementing applications. Energies, 15(23), p.8819.
Castillo, H., Collado, H., Droguett, T., Vesely, M., Garrido, P. and Palma, S. (2022). State of the art of geopolymers: A review. e-Polymers, 22(1), pp.108-124.
Kumar, S.G.K.M., Kinuthia, J.M., Oti, J. and Adeleke, B.O. (2025). Geopolymer Chemistry and Composition: A Comprehensive Review of Synthesis, Reaction Mechanisms, and Material Properties—Oriented with Sustainable Construction. Materials, 18(16), p.3823.
Shobeiri, V., Bennett, B., Xie, T. and Visintin, P. (2021). A comprehensive assessment of the global warming potential of geopolymer concrete. Journal of Cleaner Production, 297, p.126669.
Sharma, B., Rajput, A.S. and Barbhuiya, S. (2026). Life cycle assessment of energy and CO2 emission in clinker, OPC, and PPC production: case studies and pathways to emission reduction. Innovative Infrastructure Solutions, 11(6), p.337.
Qaidi, S., Najm, H.M., Abed, S.M., Ahmed, H.U., Al Dughaishi, H., Al Lawati, J., Sabri, M.M., Alkhatib, F. and Milad, A. (2022). Fly ash-based geopolymer composites: A review of the compressive strength and microstructure analysis. Materials, 15(20), p.7098.
Khan, Q.S., Mumtaz, T., Qazi, A.U. and Pham, T.M. (2024). Influence of alkaline activators on mechanical properties of environmentally friendly geopolymer concrete under different curing regimes. Environmental Science and Pollution Research, 31(50), pp.60619-60639.
Mohamed, O.A. (2023). Effects of the curing regime, acid exposure, alkaline activator dosage, and precursor content on the strength development of mortar with alkali-activated slag and fly ash binder: a critical review. Polymers, 15(5), p.1248.
Mohammed, T.O., Aman, U.H., Bin, H.M.Z. and Fanijo, E.O. (2025). Recent Advances in Fly Ash-and Slag-Based Geopolymer Cements. Sustainability, 17(24), p.11167.
. Ahmed, M.M., Sadoon, A., Bassuoni, M.T. and Ghazy, A. (2024). Utilizing agricultural residues from hot and cold climates as sustainable SCMs for low-carbon concrete. Sustainability, 16(23), p.10715.
Onsongo, S.K., Olukuru, J., Munyao, O.M. and Mwabonje, O. (2025). The role of agricultural ashes (rice husk ash, coffee husk ash, sugarcane bagasse ash, palm oil fuel ash) in cement production for sustainable development in Africa. Discover Sustainability, 6(1), p.62.
Devadharshini, M. and Vasugi, K. (2025). A Comprehensive Review and Future Directions on Utilization of Agricultural Waste Ash in Geopolymer Concrete. International Journal of Engineering Trends and Technology, 73(9), pp.125-140.
Harmaji, A., Kirana, M.C. and Jafari, R. (2024). Machine learning to predict workability and compressive strength of low-and high-calcium fly ash–based geopolymers. Crystals, 14(10), p.830.
Mushthofa, M., Thedy, J., Teguh, M., Purwanto, Pratama, A.G. and Han, A.L. (2026). Artificial Intelligence in Geopolymer Concrete Mix Design: A Comprehensive Review of Techniques and Applications. Iranian Journal of Science and Technology, Transactions of Civil Engineering, 50(1), pp.49-81.
Li, F., Rana, M.S. and Qurashi, M.A. (2025). Advanced machine learning techniques for predicting concrete mechanical properties: A comprehensive review of models and methodologies. Multiscale and Multidisciplinary Modeling, Experiments and Design, 8(1), p.110.
Al-Shamasneh, A.A.R., Mahmoodzadeh, A., Karim, F.K., Saidani, T., Alghamdi, A., Alnahas, J. and Sulaiman, M. (2025). Application of machine learning techniques to predict the compressive strength of steel fiber reinforced concrete. Scientific Reports, 15(1), p.30674.
ASTM C618-19 (2022). Standard Specification for Coal Fly Ash and Raw or Calcined Natural Pozzolan for Use in Concrete. ASTM International, West Conshohocken, USA.
Palanisamy, E. and Ramasamy, M. (2022). Dependency of sisal and banana fiber on mechanical and durability properties of polypropylene hybrid fiber reinforced concrete. Journal of Natural Fibers, 19(8), pp.3147-3157.
BS EN 12620:2013. Aggregates for concrete. BSI, Brussels.
BS EN 15743:2010+A1:2015. Supersulfated cement. Composition, specifications and conformity criteria. BSI, Brussels.
Albidah, A., Alghannam, M., Abbas, H., Almusallam, T. and Al-Salloum, Y. (2021). Characteristics of metakaolin-based geopolymer concrete for different mix design parameters. Journal of Materials Research and Technology, 10, pp.84-98.
Nath, P., and Sarker, P.K. (2017). Flexural Strength and Elastic Modulus of Ambient-Cured Blended Low-Calcium Fly Ash Geopolymer Concrete, Construction and Building Materials, 130, 22–31.
Ahmed, H.U., Mohammed, A.A., Rafiq, S., Mohammed, A.S., Mosavi, A., Sor, N.H., and Qaidi, S.M.A. (2021). Compressive Strength of Sustainable Geopolymer Concrete Composites: A Stateof-the-Art Review, Sustainability, 13, 1-38.
BS EN 12390-3:2019. Testing hardened concrete – compressive strength of test specimens. BSI, Brussels.
Weisberg, S. (2005). Applied Linear Regression. 3rd Ed. John Wiley & Sons, NewJersey.
Pardoe, I. (2020). Multiple Linear Regression. In: Applied Regression Modeling, I. Pardoe (Ed.). https://doi.org/10.1002/9781119615941.ch3
Matsimbe, J., Dinka, M., Olukanni, D. and Musonda, I. (2024). Fundamental machine learning algorithms and statistical models applied in strength prediction of geopolymers: a systematic review. Discover Applied Sciences, 6(10), p.538.
Mienye, I.D. and Sun, Y. (2022). A survey of ensemble learning: Concepts, algorithms, applications, and prospects. IEEE Access, 10, pp. 99129-99149.
Halabaku, E. and Bytyçi, E. (2024). Overfitting in Machine Learning: A Comparative Analysis of Decision Trees and Random Forests. Intelligent Automation & Soft Computing, 39(6).
Hilloulin, B. and Umunnakwe, R. (2024). Machine learning-aided prediction of shrinkage in modern concrete: Focus on mix proportions and SCMs. Journal of Building Engineering, 98, p.111410.
Zhang, M., Zhang, C., Zhang, J., Wang, L. and Wang, F. (2023). Effect of composition and curing on alkali activated fly ash-slag binders: Machine learning prediction with a random forest-genetic algorithm hybrid model. Construction and Building Materials, 366, p.129940.
Velusamy, P. and Thangavel, R. (2026). Predictive modeling of age-dependent strength in concrete incorporating GGBS, silica fume, and phosphogypsum using XGBoost, Random Forest, and Weibull analysis. Mechanics of Time-Dependent Materials, 30(1), p.2.
Azevedo, A.G.S., Strecker, K., Barros, L.A., Tonholo, L.F. and Lombardi, C.T. (2019). Effect of curing temperature, activator solution composition and particle size in Brazilian fly-ash based geopolymer production. Materials Research, 22, p.e20180842.
Cheng, Y., Cong, P., Zhao, Q., Hao, H., Mei, L., Zhang, A., Han, Z. and Hu, M. (2022). Study on the effectiveness of silica fume-derived activator as a substitute for water glass in fly ashbased geopolymer. Journal of Building Engineering, 51, p.104228.
Nodehi, M. and Taghvaee, V.M. (2022). Alkali-activated materials and geopolymer: a review of common precursors and activators addressing circular economy. Circular Economy and Sustainability, 2(1), pp.165-196.
Guo, L., Liu, J., Zhou, M. and An, S. (2024). Effect of an alkali activators on the compressive strength and reaction mechanism of coal gangue-slag-fly ash geopolymer grouting materials. Construction and Building Materials, 426, p.136012.
Parhi, S.K. and Patro, S.K. (2023). Prediction of compressive strength of geopolymer concrete using a hybrid ensemble of grey wolf optimized machine learning estimators. Journal of Building Engineering, 71, p.106521.
Rathnayaka, M., Karunasinghe, D., Gunasekara, C., Wijesundara, K., Lokuge, W. and Law, D.W. (2024). Machine learning approaches to predict compressive strength of fly ash-based geopolymer concrete: A comprehensive review. Construction and Building Materials, 419, p.135519.
Hu, H., Jiang, M., Tang, M., Liang, H., Cui, H., Liu, C., Ji, C., Wang, Y., Jian, S., Wei, C. and Song, S. (2025). Prediction of compressive strength of fly ash-based geopolymers concrete based on machine learning. Results in Engineering, p.106492.
Abdellatief, M., Hassan, Y.M., Elnabwy, M.T., Wong, L.S., Chin, R.J. and Mo, K.H. (2024). Investigation of machine learning models in predicting compressive strength for ultra-highperformance geopolymer concrete: A comparative study. Construction and Building Materials, 436, p.136884.
Bin, F., Hosseini, S., Chen, J., Samui, P., Fattahi, H. and Jahed Armaghani, D. (2024). Proposing optimized random forest models for predicting compressive strength of geopolymer composites. Infrastructures, 9(10), p.181.
Cihan, M.T. and Cihan, P. (2025). Bayesian-Optimized ensemble models for geopolymer concrete compressive strength prediction with interpretability analysis. Buildings, 15(20), p.3667.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 The Journals of the Nigerian Association of Mathematical Physics
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
