journal article·2025-06-27Open access

Integrating advanced data imputation techniques and machine learning models to develop a predictive model for compressive strength of geopolymer concrete

Madushan Rathnayaka, Kushan Wijesundara, Chamila Gunasekara, David W. Law, Dulakshi Karunasingha, Weena Lokuge

Abstract

Abstract Geopolymer concrete (GPC) offers an environmentally sustainable alternative to Portland cement, reducing carbon emissions and utilizing fly ash. However, accurately predicting GPC’s compressive strength remains challenging due to complex interactions among the chemical, physical, and mineralogical properties of fly ash, alkali activators, and curing conditions. This study presents a novel predictive model that integrates advanced data imputation techniques and machine learning models—Artificial neural network (ANN), Random Forest (RF), and Extreme Gradient Boosting (XGB)—to address missing data and material variability. The final ANN model, which incorporates the chemical composition, surface area, particle size, and amorphous content of fly ash, achieved a testing accuracy of 90% in predicting the compressive strength of GPC, with values ranging from 10 to 80 MPa. The ANN model for compressive strength prediction of GPC outperformed XGB and RF by 38% and 29%, respectively, highlighting its superior ability to generalize to new data. SHAP analysis identified total water content, Fe2O3, and BET surface area as the most influential parameters, with optimized values leading to enhanced compressive strength. Additionally, ANN-based imputation consistently outperformed traditional methods, namely MICE, SVD and KNN, improving data integrity and achieving superior model performance with the highest R2 and lowest RMSE and MAE for both train and test data sets. This research provides a robust methodology for predicting GPC compressive strength, offering valuable insights for mix design and addressing the challenges of material variability and missing data.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Concrete and Cement Materials Research · Innovative concrete reinforcement materials · Concrete Properties and Behavior

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (47)

Show source-provided references
1. Alaneme GU, Olonade KA, Esenogho E, Lawan MM. Proposed simplified methodological approach for designing geopolymer concrete mixtures. Sci Rep. 2024;14(1):15191.10.1038/s41598-024-66093-y ↗
2. Luan C, Zhou A, Li Y, Zou D, Gao P, Liu T. CO2 avoidance cost of fly ash geopolymer concrete. Constr Build Mater. 2024;416: 135193.10.1016/j.conbuildmat.2024.135193 ↗
3. Duxson P, Provis JL. Designing precursors for geopolymer cements. J Am Ceram Soc. 2008;91(12):3864–9.10.1111/j.1551-2916.2008.02787.x ↗
4. Hardjito D, Wallah SE, Sumajouw DM, Rangan BV. Factors influencing the compressive strength of fly ash-based geopolymer concrete. Civil engineering dimension. 2004;6(2):88–93.
5. J. Davidovits, Geopolymer chemistry and applications. Geopolymer Institute, 2008.
6. Zhuang XY, et al. Fly ash-based geopolymer: clean production, properties and applications. J Clean Prod. 2016;125:253–67.10.1016/j.jclepro.2016.03.019 ↗
7. Ghafoor MT, Khan QS, Qazi AU, Sheikh MN, Hadi M. Influence of alkaline activators on the mechanical properties of fly ash based geopolymer concrete cured at ambient temperature. Constr Build Mater. 2021;273: 121752.10.1016/j.conbuildmat.2020.121752 ↗
8. Sindhunata, Van Deventer J, Lukey G, Xu H. Effect of curing temperature and silicate concentration on fly-ash-based geopolymerization. Ind Eng Chem Res. 2006;45(10):3559–68.10.1021/ie051251p ↗
9. Assi LN, Deaver EE, Ziehl P. Effect of source and particle size distribution on the mechanical and microstructural properties of fly ash-based geopolymer concrete. Constr Build Mater. 2018;167:372–80.10.1016/j.conbuildmat.2018.01.193 ↗
10. C. Gunasekara. “Influence of properties of fly ash from different sources on the mix design and performance of geopolymer concrete” RMIT University. Accessed 2022–08–08, 2022.
11. Rathnayaka M, Karunasinghe D, Gunasekara C, Wijesundara K, Lokuge W, Law DW. Machine learning approaches to predict compressive strength of fly ash-based geopolymer concrete: a comprehensive review. Constr Build Mater. 2024;419: 135519.10.1016/j.conbuildmat.2024.135519 ↗
12. Temuujin J, Van Riessen A, Williams R. Influence of calcium compounds on the mechanical properties of fly ash geopolymer pastes. J Hazard Mater. 2009;167(1–3):82–8.10.1016/j.jhazmat.2008.12.121 ↗
13. Duxson P, Fernández-Jiménez A, Provis JL, Lukey GC, Palomo A, van Deventer JS. Geopolymer technology: the current state of the art. J Mater Sci. 2007;42:2917–33.10.1007/s10853-006-0637-z ↗
14. Herath C, Gunasekara C, Law DW, Setunge S. Long term mechanical performance of nano-engineered high volume fly ash concrete. J Build Eng. 2021;43: 103168.10.1016/j.jobe.2021.103168 ↗
15. Ahmed HU, Mohammed AS, Mohammed AA, Faraj RH. Systematic multiscale models to predict the compressive strength of fly ash-based geopolymer concrete at various mixture proportions and curing regimes. PLoS ONE. 2021;16(6): e0253006.10.1371/journal.pone.0253006 ↗
16. Junninen H, Niska H, Tuppurainen K, Ruuskanen J, Kolehmainen M. Methods for imputation of missing values in air quality data sets. Atmos Environ. 2004;38(18):2895–907.10.1016/j.atmosenv.2004.02.026 ↗
17. Zhang X, Dai C, Li W, Chen Y. Prediction of compressive strength of recycled aggregate concrete using machine learning and Bayesian optimization methods. Front Earth Sci. 2023;11:1112105.10.3389/feart.2023.1112105 ↗
18. Batista GE, Monard MC. An analysis of four missing data treatment methods for supervised learning. Appl Artif Intell. 2003;17(5–6):519–33.10.1080/713827181 ↗
19. Rubin DB. Inference and missing data. Biometrika. 1976;63(3):581–92.10.1093/biomet/63.3.581 ↗
20. Van Buuren S, Groothuis-Oudshoorn K. Mice: multivariate imputation by chained equations in R. J Stat Softw. 2011;45:1–67.10.18637/jss.v045.i03 ↗
21. Lyngdoh GA, Zaki M, Krishnan NA, Das S. Prediction of concrete strengths enabled by missing data imputation and interpretable machine learning. Cement Concr Compos. 2022;128: 104414.10.1016/j.cemconcomp.2022.104414 ↗
22. Pereira RC, Abreu PH, Rodrigues PP, Figueiredo MA. Imputation of data missing not at random: artificial generation and benchmark analysis. Expert Syst Appl. 2024;249: 123654.10.1016/j.eswa.2024.123654 ↗
23. Choudhury SJ, Pal NR. Imputation of missing data with neural networks for classification. Knowl-Based Syst. 2019;182:104838.10.1016/j.knosys.2019.07.009 ↗
24. Troyanskaya O, et al. Missing value estimation methods for DNA microarrays. Bioinformatics. 2001;17(6):520–5.10.1093/bioinformatics/17.6.520 ↗
25. Bhogayata A, Kakadiya S, Makwana R. Neural network for mixture design optimization of geopolymer concrete. ACI Mater J. 2021. https://doi.org/10.14359/51732711.10.14359/51732711 ↗
26. Huynh AT, et al. A machine learning-assisted numerical predictor for compressive strength of geopolymer concrete based on experimental data and sensitivity analysis. Appl Sci. 2020. https://doi.org/10.3390/app10217726.10.3390/app10217726 ↗
27. Pham TT. A neural network approach for predicting hardened property of geopolymer concrete. Int J GEOMATE. 2020;19(74):176–84. https://doi.org/10.21660/2020.74.72565.10.21660/2020.74.72565 ↗
28. Dao DV, Ly HB, Trinh SH, Le TT, Pham BT. Artificial intelligence approaches for prediction of compressive strength of geopolymer concrete. Materials (Basel). 2019. https://doi.org/10.3390/ma12060983.10.3390/ma12060983 ↗
29. Peng Y, Unluer C. Analyzing the mechanical performance of fly ash-based geopolymer concrete with different machine learning techniques. Constr Build Mater. 2022. https://doi.org/10.1016/j.conbuildmat.2021.125785.10.1016/j.conbuildmat.2021.125785 ↗
30. Khan MA, et al. Geopolymer concrete compressive strength via artificial neural network, adaptive neuro fuzzy interface system, and gene expression programming with K-fold cross validation. Front Mater. 2021. https://doi.org/10.3389/fmats.2021.621163.10.3389/fmats.2021.621163 ↗
31. Gunasekara C, Atzarakis P, Lokuge W, Law DW, Setunge S. Novel analytical method for mix design and performance prediction of high calcium fly ash geopolymer concrete. Polymers. 2021. https://doi.org/10.3390/polym13060900.10.3390/polym13060900 ↗
32. Nguyen KT, Nguyen QD, Le TA, Shin J, Lee K. Analyzing the compressive strength of green fly ash based geopolymer concrete using experiment and machine learning approaches. Constr Build Mater. 2020;247: 118581.10.1016/j.conbuildmat.2020.118581 ↗
33. Ahmad M, Rashid K, Tariq Z, Ju M. Utilization of a novel artificial intelligence technique (ANFIS) to predict the compressive strength of fly ash-based geopolymer. Constr Build Mater. 2021. https://doi.org/10.1016/j.conbuildmat.2021.124251.10.1016/j.conbuildmat.2021.124251 ↗
34. Khan MA, et al. Compressive strength of fly-ash-based geopolymer concrete by gene expression programming and random forest. Adv Civil Eng. 2021;2021:1–17. https://doi.org/10.1155/2021/6618407.10.1155/2021/6618407 ↗
35. Chu H-H, et al. Sustainable use of fly-ash: use of gene-expression programming (GEP) and multi-expression programming (MEP) for forecasting the compressive strength geopolymer concrete. Ain Shams Eng J. 2021;12(4):3603–17.10.1016/j.asej.2021.03.018 ↗
36. Gomaa E, Han T, ElGawady M, Huang J, Kumar A. Machine learning to predict properties of fresh and hardened alkali-activated concrete. Cem Concr Compos. 2021. https://doi.org/10.1016/j.cemconcomp.2020.103863.10.1016/j.cemconcomp.2020.103863 ↗
37. Rathnayaka M, Karunasingha D, Gunasekara C, Law DW, Wijesundara K, Lokuge W. Mix design determination procedure for geopolymer concrete based on target strength method. Arch Civil Mech Eng. 2024;24(3):192.10.1007/s43452-024-01002-8 ↗
38. Little RJ. A test of missing completely at random for multivariate data with missing values. J Am Stat Assoc. 1988;83(404):1198–202.10.1080/01621459.1988.10478722 ↗
39. Amran YM, Alyousef R, Alabduljabbar H, El-Zeadani M. Clean production and properties of geopolymer concrete: a review. J Clean Prod. 2020;251: 119679.10.1016/j.jclepro.2019.119679 ↗
40. Hardjito D, Wallah SE, Sumajouw DM, Rangan BV. On the development of fly ash-based geopolymer concrete. Mater J. 2004;101(6):467–72.
41. Xu H, Van Deventer J. The geopolymerisation of alumino-silicate minerals. Int J Miner Process. 2000;59(3):247–66.10.1016/S0301-7516(99)00074-5 ↗
42. Nath P, Sarker PK. Effect of GGBFS on setting, workability and early strength properties of fly ash geopolymer concrete cured in ambient condition. Constr Build Mater. 2014;66:163–71.10.1016/j.conbuildmat.2014.05.080 ↗
43. Provis JL, Bernal SA. Geopolymers and related alkali-activated materials. Annu Rev Mater Res. 2014;44(1):299–327.10.1146/annurev-matsci-070813-113515 ↗
44. Widjajakusuma J, Bali I, Ng GP, Wibowo KA. An experimental study on the mechanical properties of low-aluminum and rich-iron-calcium fly ash-based geopolymer concrete. Adv Technol Innov. 2022;7(4):295.10.46604/aiti.2022.10525 ↗
45. Castillo H, et al. Factors affecting the compressive strength of geopolymers: a review. Minerals. 2021;11(12):1317.10.3390/min11121317 ↗
46. Provis JL, Van Deventer JSJ. Geopolymers: structures, processing, properties and industrial applications. Elsevier; 2009.10.1533/9781845696382 ↗
47. Risdanareni P, Ekaputri JJ, Triwulan T. The influence of alkali activator concentration to mechanical properties of geopolymer concrete with trass as a filler. Mater Sci Forum. 2015;803:125–34.10.4028/www.scientific.net/MSF.803.125 ↗