Predicting compressive strength of polyurethane-modified light weight geopolymer bricks using hybrid AI models
Source abstract
Abstract
Abstract Lightweight geopolymer bricks have emerged as efficient and sustainable architectural materials, offering reduced density, enhanced thermal insulation, and excellent fire resistance. Their lower structural weight improves seismic performance and design flexibility, while their reduced carbon footprint makes them a viable alternative to conventional construction materials. In parallel, Artificial Intelligence-driven predictive approaches have become essential for optimizing material performance and accelerating innovation in sustainable construction. This study investigates the application of advanced hybrid AI models, ANFIS-GA, CNN-LSTM, SVM + K-means, and XGBoost + K-means to predict the compressive strength of polyurethane-modified lightweight geopolymer bricks. A comprehensive dataset of samples was analyzed using statistical and machine learning techniques to evaluate the influence of mix design parameters on compressive strength. The results demonstrate excellent predictive performance, also the Area Under the Curve (AUC) values for all models were remarkably high, ranging between 0.97 and 1.00, for both the training and testing datasets. Among the models, XGBoost + K-means and SVM + K-means achieved superior accuracy, with R 2 values up to 0.98 (training) and 0.96 (testing), alongside low error metrics (MAE = 1.00 MPa, RMSE = 2.25 MPa). High prediction reliability was further confirmed through coverage metrics within ±3 MPa and ±5 MPa. These findings highlight the effectiveness of hybrid AI models in predictive performance of polyurethane-modified geopolymer systems and demonstrate their potential for intelligent material design, performance optimization, and sustainable construction applications.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Innovative concrete reinforcement materials · Concrete and Cement Materials Research · Fire effects on concrete materials
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Civil Engineering Department, College of Engineering , Imam Mohammad Ibn Saud Islamic University (IMSIU) , Riyadh , 11432 , Saudi Arabia
References (70)
Show source-provided references
1. Mohi-Ud-Din, MM, Khan, MZN, Hafeez, MO, Cheema, US, Khokhar, SA, Arshad, MH. Exploring the potential of rigid polyurethane foam waste in structural lightweight concrete. Next Mater 2025;6:100399. https://doi.org/10.1016/j.nxmate.2024.100399.10.1016/j.nxmate.2024.100399 ↗
2. Fan, L, Meng, W, Teng, L, Khayat, KH. Effects of lightweight sand and steel fiber contents on the corrosion performance of steel rebar embedded in UHPC. Constr Build Mater 2020;238:117709. https://doi.org/10.1016/j.conbuildmat.2019.117709.10.1016/j.conbuildmat.2019.117709 ↗
3. Selvi, MT, Dasarathy, A, Ilango, SP. Mechanical properties on light weight aggregate concrete using high density polyethylene granules. Mater Today Proc 2023;81:926–30.10.1016/j.matpr.2021.04.302 ↗
4. Abdulkareem, OA, Mustafa, A, Bakri, AM, Kamarudin, H, Khairul Nizar, I, Saif, AEA. Effects of elevated temperatures on the thermal behavior and mechanical performance of fly ash geopolymer paste, mortar and lightweight concrete. Constr Build Mater 2014;50:377–87.10.1016/j.conbuildmat.2013.09.047 ↗
5. Sarkar, N, Dasgupta, K. Machine learning-based sensitivity analysis of engineering demand parameters for a reinforced concrete wall-frame building. Structures 2024;70:107477. https://doi.org/10.1016/j.istruc.2024.107477.10.1016/j.istruc.2024.107477 ↗
6. Taye, MM. Theoretical understanding of convolutional neural network: concepts, architectures, applications, future directions. Computation 2023;11:52. https://doi.org/10.3390/computation11030052.10.3390/computation11030052 ↗
7. Sun, Y, Cheng, H, Zhang, S, Mohan, MK, Ye, G, De Schutter, G. Prediction and optimization of alkali-activated concrete based on the random forest machine learning algorithm. Constr Build Mater 2023;385:131519. https://doi.org/10.1016/j.conbuildmat.2023.131519.10.1016/j.conbuildmat.2023.131519 ↗
8. Puppala, AJ, Ruttanaporamakul, P, Congress, SSC. Design and construction of lightweight EPS geofoam embedded geomaterial embankment system for control of settlements. Geotext Geomembr 2019;47:295–305. https://doi.org/10.1016/j.geotexmem.2019.01.015.10.1016/j.geotexmem.2019.01.015 ↗
9. Hammoudi, A, Moussaceb, K, Belebchouche, C, Dahmoune, F. Comparison of artificial neural network (ANN) and response surface methodology (RSM) prediction in compressive strength of recycled concrete aggregates. Constr Build Mater 2019;209:425–36. https://doi.org/10.1016/j.conbuildmat.2019.03.119.10.1016/j.conbuildmat.2019.03.119 ↗
10. Chang, Z, Shi, X, Zheng, K, Lu, Y, Deng, Y, Huang, J. Soft computing techniques to model the compressive strength in geo-polymer concrete: approaches based on an adaptive neuro-fuzzy inference system. Buildings 2024;14:3505. https://doi.org/10.3390/buildings14113505.10.3390/buildings14113505 ↗
11. Sharafati, A, Naderpour, H, Salih, SQ, Onyari, E, Yaseen, ZM. Simulation of foamed concrete compressive strength prediction using adaptive neuro-fuzzy inference system optimized by nature-inspired algorithms. Front Struct Civ Eng 2021;15:61–79. https://doi.org/10.1007/s11709-020-0684-6.10.1007/s11709-020-0684-6 ↗
12. Suleiman, AR, Nehdi, ML. Modeling self-healing of concrete using hybrid genetic algorithm-artificial neural network. Materials 2017;10:135. https://doi.org/10.3390/ma10020135.10.3390/ma10020135 ↗
13. Zhang, Y, Jiang, Y, Li, C, Bai, C, Zhang, F, Li, J, et al.. Prediction of cement-stabilized recycled concrete aggregate properties by CNN-LSTM incorporating attention mechanism. J Build Eng 2025;42:111137. https://doi.org/10.1016/j.mtcomm.2024.111137.10.1016/j.mtcomm.2024.111137 ↗
14. Ali, L, Alnajjar, F, Jassmi, HA, Gocho, M, Khan, W, Serhani, MA. Performance evaluation of deep CNN-based crack detection and localization techniques for concrete structures. Sensors 2021;21:1688. https://doi.org/10.3390/s21051688.10.3390/s21051688 ↗
15. Mohammadagha, M. Hyperparameter optimization strategies for tree-based machine learning models prediction: a comparative study of AdaBoost, decision trees, and random forest (April 11, 2025) 2025.10.31219/osf.io/xbkr5_v1 ↗
16. Behnood, A, Golafshani, EM. Predicting the compressive strength of silica fume concrete using hybrid artificial neural network with multi-objective grey wolves. J Clean Prod 2018;202:54–64. https://doi.org/10.1016/j.jclepro.2018.08.065.10.1016/j.jclepro.2018.08.065 ↗
17. Ruz Canul, MA, Ruz-Hernandez, JA, Alanis, AY, Gonzalez Gomez, JC, Gálvez, J. Modified soft margin optimal hyperplane algorithm for support vector machines applied to fault patterns and disease diagnosis. Symmetry 2025;17:1749. https://doi.org/10.3390/sym17101749.10.3390/sym17101749 ↗
18. Das, P, Kashem, A. Hybrid machine learning approach to prediction of the compressive and flexural strengths of UHPC and parametric analysis with Shapley additive explanations. Case Stud Constr Mater 2024;20:e02723. https://doi.org/10.1016/j.cscm.2023.e02723.10.1016/j.cscm.2023.e02723 ↗
19. Mustapha, IB, Abdulkareem, M, Jassam, TM, AlAteah, AH, Al-Sodani, KAA, Al-Tholaia, MM, et al.. Comparative analysis of gradient-boosting ensembles for estimation of compressive strength of Quaternary blend concrete. Int J Concr Struct Mater 2024;18:20. https://doi.org/10.1186/s40069-023-00653-w.10.1186/s40069-023-00653-w ↗
20. Ahmad, F, Alasskar, A, Samui, P, Asteris, PG. Machine learning-based graphical user interface for predicting high-performance concrete compressive strength: comparative analysis of gradient boosting machine, random forest, and deep neural network models. Front Struct Civ Eng 2025;19:1075–90. https://doi.org/10.1007/s11709-025-1201-8.10.1007/s11709-025-1201-8 ↗
21. Salih, AFM. Design optimization of high-performance, cost-efficient concrete enhanced with nano-CNTs: a hybrid approach using machine learning and NSGA-II. Mater Today Commun 2025;45:112251. https://doi.org/10.1016/j.mtcomm.2025.112251.10.1016/j.mtcomm.2025.112251 ↗
22. Pande, PB, Dhengare, SW, Raut, JM, Bhagat, RM, Bahoria, BV, Shelke, N, et al.. Integrated hybrid machine learning techniques and multiscale modeling towards evaluating the influence of nano-material on strength of concrete. Results Eng 2025;8:26. https://doi.org/10.1007/s41939-024-00588-z.10.1007/s41939-024-00588-z ↗
23. Parida, L, Moharana, S, Ferreira, VM, Giri, SK, Ascensão, G. A novel CNN-LSTM hybrid model for prediction of electro-mechanical impedance signal based bond strength monitoring. Sensors 2022;22:9920. https://doi.org/10.3390/s22249920.10.3390/s22249920 ↗
24. Al-Taai, SR, Azize, NM, Thoeny, ZA, Imran, H, Bernardo, LF, Al-Khafaji, Z. XGBoost prediction model optimized with Bayesian for the compressive strength of eco-friendly concrete containing ground granulated blast furnace slag and recycled coarse aggregate. Appl Sci 2023;13:8889. https://doi.org/10.3390/app13158889.10.3390/app13158889 ↗
25. Kashem, A, Das, P. Compressive strength prediction of high-strength concrete using hybrid machine learning approaches by incorporating SHAP analysis. Asian J Civ Eng 2023;24:3243–63. https://doi.org/10.1007/s42107-023-00707-0.10.1007/s42107-023-00707-0 ↗
26. Ibrahim, WMW, Hussin, K, Abdullah, MMAB, Kadir, AA. Geopolymer lightweight bricks manufactured from fly ash and foaming agent. AIP Conf Proc 2017;1835:020048.10.1063/1.4981870 ↗
27. Liu, MYJ, Alengaram, UJ, Jumaat, MZ, Mo, KH. Evaluation of thermal conductivity, mechanical and transport properties of lightweight aggregate foamed geopolymer concrete. Energy Build 2014;72:238–45. https://doi.org/10.1016/j.enbuild.2013.12.029.10.1016/j.enbuild.2013.12.029 ↗
28. Wu, J, Zhang, Z, Zhang, Y, Li, D. Preparation and characterization of ultra-lightweight foamed geopolymer (UFG) based on fly ash-metakaolin blends. Constr Build Mater 2018;168:771–9. https://doi.org/10.1016/j.conbuildmat.2018.02.097.10.1016/j.conbuildmat.2018.02.097 ↗
29. Mo, KH, Alengaram, UJ, Jumaat, MZ. A review on the use of agriculture waste material as lightweight aggregate for reinforced concrete structural members. Adv Mater Sci Eng 2014;2014:365197–9. https://doi.org/10.1155/2014/365197.10.1155/2014/365197 ↗
30. Jagarapu, DCK, Eluru, A. Strength and durability studies of lightweight fiber reinforced concrete with agriculture waste. Mater Today Proc 2020;27:914–9. https://doi.org/10.1016/j.matpr.2020.01.257.10.1016/j.matpr.2020.01.257 ↗
31. Youssf, O, Mills, JE, Elchalakani, M, Alanazi, F, Yosri, AM. Geopolymer concrete with lightweight fine aggregate: material performance and structural application. Polymers 2023;15:171. https://doi.org/10.3390/polym15010171.10.3390/polym15010171 ↗
32. Zhao, Q, Chen, Q, Alqurashi, M, Alsaluli, A, Mostafa, SA. Transforming waste into value: advancing sustainable construction materials with treated plastic waste and foundry sand in lightweight foamed concrete for a greener future. Rev Adv Mater Sci 2025;64:20250118. https://doi.org/10.1515/rams-2025-0118.10.1515/rams-2025-0118 ↗
33. Qaidi, S, Najm, HM, Abed, SM, Ozkilic, YO, Al Dughaishi, H, Alosta, M, et al.. Concrete containing waste glass as an environmentally friendly aggregate: a review on fresh and mechanical characteristics. Materials 2022;15:6222. https://doi.org/10.3390/ma15186222.10.3390/ma15186222 ↗
34. Wu, H, Gao, J, Liu, C, Zhao, Y, Li, S. Development of nano-silica modification to enhance the micro-macro properties of cement-based materials with recycled clay brick powder. J Build Eng 2024;86:108854. https://doi.org/10.1016/j.jobe.2024.108854.10.1016/j.jobe.2024.108854 ↗
35. Zeyad, AM, Mahmoud, AA, El-Sayed, AA, Aboraya, AM, Fathy, IN, Zygouris, N, et al.. Compressive strength of nano concrete materials under elevated temperatures using machine learning. Sci Rep 2024;14:24246. https://doi.org/10.1038/s41598-024-73713-0.10.1038/s41598-024-73713-0 ↗
36. Ekanayake, I, Meddage, D, Rathnayake, U. A novel approach to explain the black-box nature of machine learning in compressive strength predictions of concrete using Shapley additive explanations (SHAP). Case Stud Constr Mater 2022;16:e01059. https://doi.org/10.1016/j.cscm.2022.e01059.10.1016/j.cscm.2022.e01059 ↗
37. Lin, Y, Zhou, W, AlAteah, AH, Mostafa, SA. Recycling and reuse of waste banded iron formation as fine aggregate in the production of lightweight foamed concrete: fresh-state, mechanical, thermal, microstructure and durability properties assessment. Constr Build Mater 2024;439:137369. https://doi.org/10.1016/j.conbuildmat.2024.137369.10.1016/j.conbuildmat.2024.137369 ↗
38. Farooq, F, Jin, X, Javed, MF, Akbar, A, Shah, MI, Aslam, F, et al.. Geopolymer concrete as sustainable material: a state of the art review. Constr Build Mater 2021;306:124762.10.1016/j.conbuildmat.2021.124762 ↗
39. Tikalsky, PJ, Pospisil, J, MacDonald, W. A method for assessment of the freeze-thaw resistance of preformed foam cellular concrete. Cem Concr Res 2004;34:889–93. https://doi.org/10.1016/j.cemconres.2003.11.005.10.1016/j.cemconres.2003.11.005 ↗
40. Abd, AM, Abd, SM. Modelling the strength of lightweight foamed concrete using support vector machine (SVM). Case Stud Constr Mater 2017;6:8–15. https://doi.org/10.1016/j.cscm.2016.11.002.10.1016/j.cscm.2016.11.002 ↗
41. Mounanga, P, Gbongbon, W, Poullain, P, Turcry, P. Proportioning and characterization of lightweight concrete mixtures made with rigid polyurethane foam wastes. Cem Concr Compos 2008;30:806–14. https://doi.org/10.1016/j.cemconcomp.2008.06.007.10.1016/j.cemconcomp.2008.06.007 ↗
42. Pan, Z, Hiromi, F, Wee, T. Preparation of high performance foamed concrete from cement, sand and mineral admixtures. J Wuhan Univ Technol Mater Sci 2007;22:295–8. https://doi.org/10.1007/s11595-005-2295-4.10.1007/s11595-005-2295-4 ↗
43. Ullah, HS, Khushnood, RA, Farooq, F, Ahmad, J, Vatin, NI, Ewais, DYZ. Prediction of compressive strength of sustainable foam concrete using individual and ensemble machine learning approaches. Materials 2022;15:3166. https://doi.org/10.3390/ma15093166.10.3390/ma15093166 ↗
44. Al-Amoudi, OSB, Al-Kutti, WA, Ahmad, S, Maslehuddin, M. Correlation between compressive strength and certain durability indices of plain and blended cement concretes. Cem Concr Compos 2009;31:672–6.10.1016/j.cemconcomp.2009.05.005 ↗
45. Li, Z, Gao, X, Lu, D. Correlation analysis and statistical assessment of early hydration characteristics and compressive strength for multi-composite cement paste. Constr Build Mater 2021;310:125260. https://doi.org/10.1016/j.conbuildmat.2021.125260.10.1016/j.conbuildmat.2021.125260 ↗
46. Zhu, L, Zhao, C, Dai, J. Prediction of compressive strength of recycled aggregate concrete based on gray correlation analysis. Constr Build Mater 2021;273:121750. https://doi.org/10.1016/j.conbuildmat.2020.121750.10.1016/j.conbuildmat.2020.121750 ↗
47. Zhang, X, Akber, MZ, Poon, C, Zheng, W. Predicting the 28-day compressive strength by mix proportions: insights from a large number of observations of industrially produced concrete. Constr Build Mater 2023;400:132754.10.1016/j.conbuildmat.2023.132754 ↗
48. Mosaberpanah, MA, Eren, O. Relationship between 28-days compressive strength and compression toughness factor of ultra high performance concrete using design of experiments. Procedia Eng 2016;145:1565–72. https://doi.org/10.1016/j.proeng.2016.04.197.10.1016/j.proeng.2016.04.197 ↗
49. Kabir, A, Hasan, M, Miah, K. Predicting 28 days compressive strength of concrete from 7 days test result. In: International Conference on. Advances in Design and. Construction of Structures. (ADCS 2012). Bangalore, India. 19 - 20 October 2012. Red Hook, NY: Curran Associates, Inc.; 2012:18–22 pp.
50. Li, Z, Lu, D, Gao, X. Analysis of correlation between hydration heat release and compressive strength for blended cement pastes. Constr Build Mater 2020;260:120436. https://doi.org/10.1016/j.conbuildmat.2020.120436.10.1016/j.conbuildmat.2020.120436 ↗
51. Tayfur, S, Alver, N, Abdi, S, Saatcı, S, Ghiami, A. Characterization of concrete matrix/steel fiber de-bonding in an SFRC beam: principal component analysis and k-mean algorithm for clustering AE data. Eng Fract Mech 2018;194:73–85. https://doi.org/10.1016/j.engfracmech.2018.03.007.10.1016/j.engfracmech.2018.03.007 ↗
52. Chen, L, Shan, W, Liu, P. Identification of concrete aggregates using K-means clustering and level set method. Structures 2021;34:2069–76. https://doi.org/10.1016/j.istruc.2021.08.048.10.1016/j.istruc.2021.08.048 ↗
53. Rezzoug, A, AlAteah, AH, Alinsaif, S, Mostafa, SA. Durability prediction of sustainable marine concrete under freeze-thaw cycles using multi-objective machine learning models. Case Stud Constr Mater 2025;22:e04787. https://doi.org/10.1016/j.cscm.2025.e04787.10.1016/j.cscm.2025.e04787 ↗
54. Ahmad, SA, Ahmed, HU, Rafiq, SK, Ahmad, DA. Machine learning approach for predicting compressive strength in foam concrete under varying mix designs and curing periods. Smart Constr Sustain Cities 2023;1:16. https://doi.org/10.1007/s44268-023-00021-3.10.1007/s44268-023-00021-3 ↗
55. Liu, X, AlAteah, AH, Alsubeai, A, Alahmari, TS, Mostafa, SA. Prediction of flexural strength of concrete with eggshell and glass powders: advanced cutting-edge approach for sustainable materials. Rev Adv Mater Sci 2024;63:20240055. https://doi.org/10.1515/rams-2024-0055.10.1515/rams-2024-0055 ↗
56. Ahmed, HU, Abdalla, AA, Mohammed, AS, Mohammed, AA, Mosavi, A. Statistical methods for modeling the compressive strength of geopolymer mortar. Materials 2022;15:1868. https://doi.org/10.3390/ma15051868.10.3390/ma15051868 ↗
57. Xie, HS, Gandla, SR, Shi, O, Solanki, P. Multivariate regression and variance in concrete curing methods: strength prediction with experiments. Appl Sci 2023;13:12239. https://doi.org/10.3390/app132212239.10.3390/app132212239 ↗
58. Quanwei, Z, Qi, C, AlAteah, AH, Alfares, AM, Alinsaif, S, Mostafa, SA. AI-based prediction for the strength, cost, and sustainability of eggshell and date palm ash-blended concrete. Rev Adv Mater Sci 2025;64:20250113. https://doi.org/10.1515/rams-2025-0113.10.1515/rams-2025-0113 ↗
59. Li, Z, Qi, J, Hu, Y, Wang, J. Estimation of bond strength between UHPC and reinforcing bars using machine learning approaches. Eng Struct 2022;262:114311. https://doi.org/10.1016/j.engstruct.2022.114311.10.1016/j.engstruct.2022.114311 ↗
60. Yuan, Y, Yang, M, Shang, X, Xiong, Y, Zhang, Y. Predicting the compressive strength of UHPC with coarse aggregates in the context of machine learning. Case Stud Constr Mater 2023;19:e02627. https://doi.org/10.1016/j.cscm.2023.e02627.10.1016/j.cscm.2023.e02627 ↗
61. Zhang, C, Tian, H, Zhang, L, Jiao, P. Robust AUC optimization under the supervision of clean data. Sci Rep 2024;14:16693. https://doi.org/10.1038/s41598-024-66788-2.10.1038/s41598-024-66788-2 ↗
62. Kim, SK. Versatile tolerance reflected estimations. J Stat Theor Appl 2025;24:725–39. https://doi.org/10.1007/s44199-025-00129-8.10.1007/s44199-025-00129-8 ↗
63. Shahani, NM, Zheng, X, Wei, X, Jiang, H. Hybrid machine learning approach for accurate prediction of the drilling rate index. Sci Rep 2024;14:24080. https://doi.org/10.1038/s41598-024-75639-z.10.1038/s41598-024-75639-z ↗
64. Elshaarawy, MK, Zeleňáková, M, Armanuos, AM. Hydraulic performance modeling of inclined double cutoff walls beneath hydraulic structures using optimized ensemble machine learning. Sci Rep 2025;15:27592. https://doi.org/10.1038/s41598-025-10990-3.10.1038/s41598-025-10990-3 ↗
65. Al-Shamasneh, AR, Mahmoodzadeh, A, Kewalramani, M, Alghamdi, A, Alnahas, J, Sulaiman, M, et al.. Hybrid machine learning models for predicting the tensile strength of reinforced concrete incorporating nano-engineered and sustainable supplementary cementitious materials. Sci Rep 2025;15:35805. https://doi.org/10.1038/s41598-025-19741-w.10.1038/s41598-025-19741-w ↗
66. Liu, JY, Zhang, XL, Jin, XY, Wang, MT, Zhang, YY, Wang, XY. Nutrient allocation patterns in different aboveground organs at different reproductive stages of four introduced Calligonum species in a common garden in North-Western China. Front Plant Sci 2024;15:1504216. https://doi.org/10.3389/fpls.2024.1504216.10.3389/fpls.2024.1504216 ↗
67. Babaei, H, Zamani, M, Mohammadi, S. The impact of data splitting methods on machine learning models: a case study for predicting concrete workability. Mach Learn Comput Sci Eng 2025;1:21. https://doi.org/10.1007/s44379-025-00021-3.10.1007/s44379-025-00021-3 ↗
68. Singh, R, Tipu, RK, Mir, AA, Patel, M. Predictive modelling of flexural strength in recycled aggregate-based concrete: a comprehensive approach with machine learning and global sensitivity analysis. Iran J Sci Technol Trans Civ Eng 2025;49:1089–114.10.1007/s40996-024-01489-4 ↗
69. Arsalan, MH, Mubin, O, Al Mahmud, A, Khan, IA, Hassan, AJ. Mapping data-driven research impact science: the role of machine learning and artificial intelligence. Metrics 2025;2:5. https://doi.org/10.3390/metrics2020005.10.3390/metrics2020005 ↗
70. Wang, Z, Sun, T, Sun, Y, Liu, N. Evaluating the strength properties of high-performance concrete in the form of ensemble and hybrid models using deep learning techniques. Sci Rep 2025;15:25453. https://doi.org/10.1038/s41598-025-10860-y.10.1038/s41598-025-10860-y ↗