Improving Concrete Durability Using Rice Husk Ash through Advanced Water-Binder Ratio Prediction with XAI-Enhanced Models

Abstract:

Accurately predicting the water-binder ratio (W/B ratio) is crucial for achieving rice husk ash supplemented concrete structures' desired strength and durability. This study introduces an innovative approach for W/B ratio prediction, utilizing cutting-edge machine learning algorithms in combination with Explainable Artificial Intelligence (XAI) techniques. The research employs hybrid ensemble learning models, including Random Forest (RF), CATBoost (CB), Whale Optimization Algorithm-optimized RF (RF-WOA), and Moth Flame Optimization-optimized CB (CB-MFOA). The results indicate that these hybridized models significantly outperform the standalone models (RF and CATBoost) and traditional empirical methods (feret’s law, Abram’s law and bolomey’s method), with the CB-MFOA model achieving the highest accuracy, demonstrated by an R-value of 0.9984 during the calibration phase. In the verification phase, the CB model excelled with an R-value of 0.966. In addition to model performance, the study integrates XAI methods to explain the predictions and identify the key factors influencing the w/b ratio. Cement was found to be the most critical variable, enhancing the accuracy of the CB-MFOA model. The findings confirm that the proposed method improves prediction precision and provides engineers with a reliable tool to optimize concrete mix designs, thereby improving the durability and sustainability of concrete. This research contributes to the broader field of concrete technology by advancing the application of AI-based solutions in civil engineering and related fields.

• Periodical: Materials Science Forum (Volume 1162)
• Pages: 85-94
• DOI: https://doi.org/10.4028/p-S0cABU
• Online since: October 2025
• Authors: Paul O. Awoyera*, Abba Bashir, Andi Asiz, Sani I. Abba, Krishna P. Arunachalam, Daha Shehu Aliyu
• Keywords: Compressive Strength, Durability, Shrinkage, Sustainability, Water Binder Ratio

References

[1] R. Kishore, V. Bhikshma, and P. J. Prakash, "Study on Strength Characteristics of High Strength Rice Husk Ash Concrete," Procedia Eng., vol. 14, p.2666–2672, 2011.

DOI: 10.1016/j.proeng.2011.07.335

[2] P. R. Rangan, R. Irmawaty, A. A. Amiruddin, and B. Bakri, "Compressive strength of laterite soil stabilized with rice straw ash and fly ash based geopolymer," IOP Conf. Ser. Earth Environ. Sci., vol. 419, no. 1, p.012026, Jan. 2020.

DOI: 10.1088/1755-1315/419/1/012026

[3] A. Salas Montoya, C.-W. Chung, and J.-H. Kim, "High Performance Concretes with Highly Reactive Rice Husk Ash and Silica Fume," Materials (Basel)., vol. 16, no. 11, p.3903, May 2023.

DOI: 10.3390/ma16113903

[4] K. C. Hover, "The influence of water on the performance of concrete," Constr. Build. Mater., vol. 25, no. 7, p.3003–3013, 2011.

DOI: 10.1016/j.conbuildmat.2011.01.010

[5] A. M. Mansor, R. P. Borg, A. M. M Hamed, M. M. Gadeem, and M. M. Saeed, "The effects of water-cement ratio and chemical admixtures on the workability of concrete," IOP Conf. Ser. Mater. Sci. Eng., vol. 442, p.012017, Nov. 2018.

DOI: 10.1088/1757-899X/442/1/012017

[6] B. Khasanov, N. Vatin, Z. Ismailova, and T. Mirzaev, "Physical modification of concrete mix and concrete," IOP Conf. Ser. Mater. Sci. Eng., vol. 883, no. 1, p.012205, Jul. 2020.

DOI: 10.1088/1757-899X/883/1/012205

[7] D. Zheng et al., "Flexural Strength Prediction of Steel Fiber-Reinforced Concrete Using Artificial Intelligence," Materials (Basel)., vol. 15, no. 15, p.5194, Jul. 2022.

DOI: 10.3390/ma15155194

[8] R. M. N. de Assunção, B. Royer, J. S. Oliveira, G. Rodrigues Filho, and L. A. de Castro Motta, "Synthesis, characterization, and application of the sodium poly(styrenesulfonate) produced from waste polystyrene cups as an admixture in concrete," J. Appl. Polym. Sci., vol. 96, no. 5, p.1534–1538, Jun. 2005.

DOI: 10.1002/app.21528

[9] K. Kobayashi et al., "Data-Driven Multi-scale Modeling and Robust Optimization of Composite Structure with Uncertainty Quantification," in Handbook of Smart Energy Systems, Cham: Springer International Publishing, 2023, p.1333–1343.

DOI: 10.1007/978-3-030-97940-9_207

[10] S. Abdelgader, M. Kurpinska, J. Khatib, and H. Abdelgader, "Concrete Mix Design Using Abrams and Bolomey Methods," BAU J. - Sci. Technol., vol. 4, no. 1, 2022.

DOI: 10.54729/mjps9917

[11] A. Kargari, H. Eskandari-Naddaf, and R. Kazemi, "Effect of cement strength class on the generalization of Abrams' law," Struct. Concr., vol. 20, no. 1, p.493–505, 2019.

DOI: 10.1002/suco.201700275

[12] J. de Brito, R. Kurda, and P. R. da Silva, "Can we truly predict the compressive strength of concrete without knowing the properties of aggregates?," Appl. Sci., vol. 8, no. 7, 2018.

DOI: 10.3390/app8071095

[13] E. I. Nadelman and K. E. Kurtis, "Application of Powers' model to modern portland and portland limestone cement pastes," J. Am. Ceram. Soc., vol. 100, no. 9, p.4219–4231, 2017.

DOI: 10.1111/jace.14913

[14] D. O. Nduka, B. J. Olawuyi, O. O. Joshua, and I. O. Omuh, "A Study on Gel/Space Ratio Development in Binary Mixture Containing Portland Cement and Meta-Illite Calcined Clay/Rice Husk Ash," Gels, vol. 8, no. 2, 2022.

DOI: 10.3390/gels8020085

[15] Z. P. Bažant and L. J. Najjar, "Nonlinear water diffusion in nonsaturated concrete," Matériaux Constr., vol. 5, no. 1, p.3–20, 1972.

DOI: 10.1007/BF02479073

[16] P. Krauss and T. Paret, " Review of Properties of Concrete , 5th Ed., by A. M. NevillePrentice Hall, Pearson, San Francisco, CA; 2012; ISBN 0273755803 and 978-0273755807; 846 pp.; $160 (paperback). ," J. Perform. Constr. Facil., vol. 28, no. 3, p.630–630, 2014.

DOI: 10.1061/(asce)cf.1943-5509.0000595

[17] S. Ghani, N. Kumar, M. Gupta, and S. Saharan, "Machine learning approaches for real-time prediction of compressive strength in self-compacting concrete," Asian J. Civ. Eng., vol. 25, no. 3, p.2743–2760, 2024.

DOI: 10.1007/s42107-023-00942-5

[18] M. I. Khan and Y. M. Abbas, "Robust extreme gradient boosting regression model for compressive strength prediction of blast furnace slag and fly ash concrete," Mater. Today Commun., vol. 35, no. January, p.105793, 2023.

DOI: 10.1016/j.mtcomm.2023.105793

[19] S. I. Malami, F. H. Anwar, S. Abdulrahman, S. I. Haruna, S. I. A. Ali, and S. I. Abba, "Implementation of hybrid neuro-fuzzy and self-turning predictive model for the prediction of concrete carbonation depth: A soft computing technique," Results Eng., vol. 10, no. December 2020, p.100228, 2021.

DOI: 10.1016/j.rineng.2021.100228

[20] 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, no. October, p.105459, 2023.

DOI: 10.1016/j.istruc.2023.105459

[21] F. Aslam and M. Zubair, "Supplementary cementitious materials in blended cement concrete : Advancements in predicting compressive strength through machine learning," Mater. Today Commun., vol. 38, no. October 2023, p.107725, 2024.

DOI: 10.1016/j.mtcomm.2023.107725

[22] S. Wang et al., "Prediction and optimization model of sustainable concrete properties using machine learning , deep learning and swarm intelligence : A review," J. Build. Eng., vol. 80, no. October, p.108065, 2023.

DOI: 10.1016/j.jobe.2023.108065

[23] H. Adel, M. I. Ghazaan, and A. H. Korayem, Machine learning applications for developing sustainable construction materials. Elsevier Inc., 2022.

DOI: 10.1016/B978-0-323-90508-4.00002-2

[24] C. Qi, B. Huang, M. Wu, K. Wang, S. Yang, and G. Li, "Concrete Strength Prediction Using Different Machine Learning Processes: Effect of Slag, Fly Ash and Superplasticizer," Materials (Basel)., vol. 15, no. 15, 2022.

DOI: 10.3390/ma15155369

[25] R. H. Faraj, A. A. Mohammed, and K. M. Omer, "Modeling the compressive strength of eco-friendly self-compacting concrete incorporating ground granulated blast furnace slag using soft computing techniques," Environ. Sci. Pollut. Res., vol. 29, no. 47, p.71338–71357, 2022.

DOI: 10.1007/s11356-022-20889-5

[26] M. I. Shah, S. A. Memon, M. S. Khan Niazi, M. N. Amin, F. Aslam, and M. F. Javed, "Machine Learning-Based Modeling with Optimization Algorithm for Predicting Mechanical Properties of Sustainable Concrete," Adv. Civ. Eng., vol. 2021, 2021.

DOI: 10.1155/2021/6682283

[27] M. M. Jibril et al., "Implementation of nonlinear computing models and classical regression for predicting compressive strength of high-performance concrete," Appl. Eng. Sci., vol. 15, no. April, p.100133, 2023.

DOI: 10.1016/j.apples.2023.100133

[28] E. Li et al., "Developing a hybrid model of salp swarm algorithm-based support vector machine to predict the strength of fiber-reinforced cemented paste backfill," Eng. Comput., vol. 37, no. 4, p.3519–3540, 2021.

DOI: 10.1007/s00366-020-01014-x

[29] 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)," Sci. Rep., vol. 14, no. 1, p.1–23, 2024.

DOI: 10.1038/s41598-024-54513-y

[30] I. Thapa and S. Ghani, "Enhancing unconfined compressive strength prediction in nano-silica stabilized soil: a comparative analysis of ensemble and deep learning models," Model. Earth Syst. Environ., vol. 10, no. 4, p.5079–5102, Aug. 2024.

DOI: 10.1007/s40808-024-02052-w

[31] A. Kumar et al., "Compressive Strength Prediction of Lightweight Concrete: Machine Learning Models," Sustainability, vol. 14, no. 4, p.2404, Feb. 2022.

DOI: 10.3390/su14042404

[32] G. Concrete et al., "Prediction of Mechanical Properties of Fly-Ash / Slag-Based," 2022.

[33] B. Aldeen, A. Almahameed, and H. R. Sobuz, "The Role of Hybrid Machine Learning for Predicting Strength Behavior of Sustainable Concrete," vol. 11, no. 4, p.2012–2032, 2023.

DOI: 10.13189/cea.2023.110425

[34] A. Kashem, R. Karim, P. Das, and S. Dip, "Case Studies in Construction Materials Compressive strength prediction of sustainable concrete incorporating rice husk ash ( RHA ) using hybrid machine learning algorithms and parametric analyses," vol. 20, no. January, p.1–26, 2024.

DOI: 10.1016/j.cscm.2024.e03030

[35] S. Khursheed, J. Jagan, P. Samui, and S. Kumar, "Compressive strength prediction of fly ash concrete by using machine learning techniques," Innov. Infrastruct. Solut., vol. 6, no. 3, p.1–21, 2021.

DOI: 10.1007/s41062-021-00506-z

[36] A. Ahmad et al., "Prediction of Compressive Strength of Fly Ash Based Concrete Using Individual and Ensemble Algorithm," Materials (Basel)., vol. 14, no. 4, p.794, Feb. 2021.

DOI: 10.3390/ma14040794

[37] Y. Kellouche, B. Boukhatem, M. Ghrici, R. Rebouh, and A. Zidol, "Neural network model for predicting the carbonation depth of slag concrete," Asian J. Civ. Eng., vol. 22, no. 7, p.1401–1414, 2021.

DOI: 10.1007/s42107-021-00390-z

[38] U. S. Biswal, M. Mishra, M. K. Singh, and D. Pasla, "Experimental investigation and comparative machine learning prediction of the compressive strength of recycled aggregate concrete incorporated with fly ash, GGBS, and metakaolin," Innov. Infrastruct. Solut., vol. 7, no. 4, p.1–20, 2022.

DOI: 10.1007/s41062-022-00844-6

[39] M. Singh, P. Choudhary, A. K. Bedi, S. Yadav, and R. S. Chhabra, "Compressive Strength Estimation of Waste Marble Powder Incorporated Concrete Using Regression Modelling," Coatings, vol. 13, no. 1, p.1–17, 2023.

DOI: 10.3390/coatings13010066

[40] Y. Jiang, H. Li, and Y. Zhou, "Compressive Strength Prediction of Fly Ash Concrete Using Machine Learning Techniques," Buildings, vol. 12, no. 5, 2022.

DOI: 10.3390/buildings12050690

[41] J. Huang et al., "Predicting the Compressive Strength of the Cement-Fly Ash – Slag Ternary Concrete Using the Firefly Algorithm ( FA )," 2022.

DOI: 10.3390/ma15124193

[42] A. ElNemr, "Generating water/binder ratio -to- strength curves for cement mortar used in Masnory walls," Constr. Build. Mater., vol. 233, p.117249, 2020.

DOI: 10.1016/j.conbuildmat.2019.117249

[43] A. Bashir, M. M. Jibril, U. M. Jibrin, S. I. Abba, and S. I. Malami, "A new strategy using intelligent hybrid learning for prediction of water binder ratio of concrete with rice husk ash as a supplementary cementitious material." Aug. 21, 2024.

DOI: 10.21203/rs.3.rs-4770030/v1