Vol. 16 No. 01 (2026): Journal of Materials & Construction
##common.pageHeaderLogo.altText##
JOURNAL OF MATERIALS & CONSTRUCTION

ISSN: 2734-9438

Website: www.jomc.vn

AI-Based prediction of fine-aggregate geopolymer concrete strength using machine learning algorithms

Le Thanh Ha a:1:{s:5:"vi_VN";s:0:"";} , Do Tran Minh Vu

Keywords:

Fine-aggregate geopolymer concrete
Fly ash
Ground granulated blast-furnace slag
Flexural strength
Compressive strength
Machine learning algorithms

Abstract

This study presents a machine learning framework implemented in WEKA to predict the compressive and flexural strengths of fine-aggregate geopolymer concrete (FAGPC). Utilizing two experimental datasets (90 instances for compressive strength and 45 instances for flexural strength), the study investigated the non-linear relationships between fly ash/ ground granulated blast-furnace slag contents, curing age and strength. Four classical regression algorithms—M5P, REP Tree, Random Forest and Random Tree —were systematically evaluated using an 80/20 train-test split. Model performance was evaluated by using several statistical performance indicators, including the Correlation Coefficient (R), mean absolute error (MAE), relative absolute error (RAE), mean squared error (MSE), and root mean squared error (RMSE). The results demonstrate reliable predictive performance for both mechanical properties. For compressive strength, the Random Tree model achieved the highest correlation (R = 0.7628), while the REP Tree model yielded the lowest error (RMSE = 7.02 MPa) on the test set. For flexural strength, the Random Forest model emerged as the superior predictor, achieving an outstanding correlation coefficient (R = 0.8833) and a low RMSE of 1.00 MPa. These findings indicate that the selected input variables (precursor content, curing age) are sufficient to capture the complex behavior of FAGPC.

User Navigation

How to Cite

Le Thanh Ha, & Do Tran Minh Vu. (2026). AI-Based prediction of fine-aggregate geopolymer concrete strength using machine learning algorithms . JOURNAL OF MATERIALS & CONSTRUCTION, 16(01). https://doi.org/10.54772/jomc.v16i01.1183

References

  1. Jithendra, C. and S. Elavenil, Role of Superplasticizer on GGBS based Geopolymer Concrete under ambient curing. Materials Today: Proceedings, 2019. 18: p. 148-154.
  2. Davidovits, J., Geopolymer chemistry and applications. 2008: Geopolymer Institute.
  3. Duxson, P., et al., Geopolymer technology: the current state of the art. Journal of materials science, 2007. 42(9): p. 2917-2933.
  4. Provis, J.L. and S.A. Bernal, Geopolymers and related alkali-activated materials. Annual review of materials research, 2014. 44(1): p. 299-327.
  5. San Nicolas, R., B. Walkley, and J. Van Deventer, Fly ash-based geopolymer chemistry and behavior, in Coal combustion products (ccp's). 2017, Elsevier. p. 185-214.
  6. Shi, C., D. Roy, and P. Krivenko, Alkali-activated cements and concretes. 2003: CRC press.
  7. Chen, K., et al., Development of low-calcium fly ash-based geopolymer mortar using nanosilica and hybrid fibers. Ceramics International, 2021. 47(15): p. 21791-21806.
  8. Ryu, G.S., et al., The mechanical properties of fly ash-based geopolymer concrete with alkaline activators. Construction and building materials, 2013. 47: p. 409-418.
  9. Le, Q.-H., et al., Machine learning based models for predicting compressive strength of geopolymer concrete. Frontiers of Structural and Civil Engineering, 2024. 18(7): p. 1028-1049.
  10. Paudel, S., et al., Compressive strength of concrete material using machine learning techniques. Cleaner Engineering and Technology, 2023. 15: p. 100661.
  11. Despotovic, M., et al., Evaluation of empirical models for predicting monthly mean horizontal diffuse solar radiation. Renewable and Sustainable Energy Reviews, 2016. 56: p. 246-260.
  12. Willmott, C.J. and K. Matsuura, Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate research, 2005. 30(1): p. 79-82.
  13. Chen, T. and C. Guestrin. Xgboost: A scalable tree boosting system. in Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining. 2016.
  14. Ke, G., et al., Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, 2017. 30.
  15. Wang, X., Y. Liu, and H. Xin. Bond strength prediction of concrete-encased steel structures using hybrid machine learning method. in Structures. 2021. Elsevier.
  16. Breiman, L., Random forests. Machine learning, 2001. 45(1): p. 5-32.
  17. Khan, A.U., et al., Predictive modeling for compressive strength of blended cement concrete using hybrid machine learning models. Multiscale and Multidisciplinary Modeling, Experiments and Design, 2025. 8(1): p. 25.
  18. Yuan, Y., et al., Predicting the compressive strength of UHPC with coarse aggregates in the context of machine learning. Case Studies in Construction Materials, 2023. 19: p. e02627.
  19. García, S., J. Luengo, and F. Herrera, Data preprocessing in data mining. Vol. 72. 2015: Springer.
  20. Ziegel, E.R., The elements of statistical learning. 2003, Taylor & Francis.
  21. Fernández, A., et al., SMOTE for learning from imbalanced data: progress and challenges, marking the 15-year anniversary. Journal of artificial intelligence research, 2018. 61: p. 863-905.
  22. Hall, M., et al., The WEKA data mining software: an update. ACM SIGKDD explorations newsletter, 2009. 11(1): p. 10-18.
  23. Saputro, D.R.S., WEKA 3.6. 9 (Waikato Environment for Knowledge Analysis): Tools untuk Memahami Machine Learning. 2023: Stiletto Book.
  24. Sindhunata, et al., Effect of curing temperature and silicate concentration on fly-ash-based geopolymerization. Industrial & Engineering Chemistry Research, 2006. 45(10): p. 3559-3568.
  25. Quinlan, J.R., C4. 5: programs for machine learning. 2014: Elsevier.
  26. Legates, D.R. and G.J. McCabe Jr, Evaluating the use of “goodness‐of‐fit” measures in hydrologic and hydroclimatic model validation. Water resources research, 1999. 35(1): p. 233-241.
  27. Arabiat, A., M. Altayeb, and T. Alkhrissat, Innovative AI Approaches for Concrete Strength Prediction: Towards Sustainable Buildings. Civil Engineering and Architecture, 2025. 13: p. 4254-4265.