Explainable Machine Learning Framework for Predicting and Optimizing Fly Ash Slag Concrete Mixture Composition Based on SHAP Analysis and Multi-Algorithm Benchmarking
DOI:
https://doi.org/10.56741/jnest.v5i03.2259Keywords:
Concrete Compressive Strength, Fly Ash, Genetic Algorithm, SHAP, Support Vector RegressionAbstract
Optimizing fly ash slag concrete mixtures is a complex material-engineering problem because mixture variables interact non-linearly, making conventional single variable approaches inadequate. This study develops an interpretable prediction-and-optimization framework comprising three contributions: (1) benchmarking five machine-learning algorithms Support Vector Regression (SVR), Artificial Neural Network (ANN), Random Forest, XGBoost, and LightGBM using hyperparameters optimized through Bayesian optimization (Optuna/TPE); (2) applying SHAP analysis to identify the contribution of each mixture variable; and (3) using a Genetic Algorithm (GA) to optimize concrete mixtures for three strength classes based on the best performing surrogate model. Starting from the 1,030-sample UCI concrete strength benchmark dataset, records were screened according to three Indonesian standards (SNI 2847:2019, SNI 2461:2011, and SNI 8297:2016), resulting in 542 samples that satisfied the specified technical limits. Data augmentation was evaluated using six noise levels, with 2% identified as optimal, producing a final dataset of 1,074 samples. Five-fold cross-validation demonstrated that SVR achieved the highest predictive performance (C=193.39, gamma=0.658, epsilon=0.146), with R²=0.939±0.020 and RMSE=3.30±0.45 MPa, followed by XGBoost (R²=0.934), LightGBM (R²=0.931), ANN (R²=0.925), and Random Forest (R²=0.920). SHAP analysis identified cement, age, and superplasticizer as the most influential variables, consistent with cement hydration mechanisms and Abrams’ law. GA optimization produced three mix designs corresponding to target strengths of 15.00, 27.50, and 54.99 MPa for Classes I-III, respectively. The proposed framework provides an accurate, interpretable, and standards-compliant approach for preliminary sustainable concrete mixture design across different structural applications.
Downloads
References
X.-Y. Wang, “Impact of climate change on the optimization of mixture design of low-CO2 concrete containing fly ash and slag,” Sustainability, vol. 11, no. 12, e3394, Jun. 2019, doi: 10.3390/su11123394.
S. Barbhuiya, B. B. Das, D. Adak, K. Kapoor, and M. Tabish, “Low carbon concrete: Advancements, challenges and future directions in sustainable construction,” Discover Concrete and Cement, vol. 1, no. 1, e3, Mar. 2025, doi: 10.1007/s44416-025-00002-y.
Q. Chen et al., “Compressive strength prediction of high-performance concrete: Integrating multi-ingredient influences and mix proportion insights,” Constr. Build. Mater., vol. 451, e138791, Nov. 2024, doi: 10.1016/j.conbuildmat.2024.138791.
M. R. Raju et al., “Machine learning for predicting strength properties of waste iron slag concrete,” Heliyon, vol. 11, no. 3, e42133, Feb. 2025, doi: 10.1016/j.heliyon.2025.e42133.
A. A. B. Loureiro and R. Stefani, “Comparing the performance of machine learning models for predicting the compressive strength of concrete,” Discover Civil Eng., vol. 1, no. 1, e19, Jun. 2024, doi: 10.1007/s44290-024-00022-w.
S. I. Hassan et al., “Systematic literature review on the application of machine learning for the prediction of properties of different types of concrete,” PeerJ Comput. Sci., vol. 10, e1853, May 2024, doi: 10.7717/peerj-cs.1853.
Z. Yuan, W. Zheng, and H. Qiao, “Machine learning based optimization for mix design of manufactured sand concrete,” Constr. Build. Mater., vol. 467, e140256, Mar. 2025, doi: 10.1016/j.conbuildmat.2025.140256.
M. Kioumarsi, H. Dabiri, A. Kandiri, and V. Farhangi, “Compressive strength of concrete containing furnace blast slag; optimized machine learning-based models,” Clean. Eng. Technol., vol. 13, e100604, Apr. 2023, doi: 10.1016/j.clet.2023.100604.
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, e105459, Dec. 2023, doi: 10.1016/j.istruc.2023.105459.
S. K. Parhi and S. K. Patro, “Prediction of compressive strength of geopolymer concrete using a hybrid ensemble of grey wolf optimized machine learning estimators,” J. Building Eng., vol. 71, e106521, Jul. 2023, doi: 10.1016/j.jobe.2023.106521.
X. Luo, Y. Li, Q. Wang, J. Mu, and Y. Liu, “Machine learning based modeling for predicting the compressive strength of solid waste material-incorporated magnesium phosphate cement,” J. Clean. Prod., vol. 442, e141172, Feb. 2024, doi: 10.1016/j.jclepro.2024.141172.
S. Elhishi, A. M. Elashry, and S. El-Metwally, “Unboxing machine learning models for concrete strength prediction using XAI,” Sci. Rep., vol. 13, no. 1, e19892, Nov. 2023, doi: 10.1038/s41598-023-47169-7.
M. S. N. Tak, Y. Feng, and M. Mahgoub, “Advanced machine learning techniques for predicting concrete compressive strength,” Infrastructures (Basel)., vol. 10, no. 2, e26, Jan. 2025, doi: 10.3390/infrastructures10020026.
S. Wang, P. Xia, F. Gong, Q. Zeng, K. Chen, and Y. Zhao, “Multi objective optimization of recycled aggregate concrete based on explainable machine learning,” J. Clean. Prod., vol. 445, e141045, Mar. 2024, doi: 10.1016/j.jclepro.2024.141045.
Y. Gu, R. Fan, Y. Li, J. Zhao, Z. Song, and H. Chu, “Multi-objective optimization for nano-silica-modified concrete based on explainable machine learning,” Nanomaterials, vol. 15, no. 18, e1423, Sep. 2025, doi: 10.3390/nano15181423.
R. K. Tipu, V. R. Panchal, and K. S. Pandya, “Multi-objective optimization of the concrete mixture blended with mineral admixture using machine learning and NSGA-II algorithms,” in Lecture Notes in Mechanical Eng., 2023, pp. 165–174. doi: 10.1007/978-981-19-9285-8_16.
W. J. Park, T. Noguchi, and H. S. Lee, “Genetic algorithm in mix proportion design of recycled aggregate concrete,” Computers & concrete, vol. 11, no. 3, pp. 183–199, Mar. 2013, doi: 10.12989/cac.2013.11.3.183.
I. Yeh, “Concrete Compressive Strength,” UCI Machine Learning Repository, 1998, doi: 10.24432/C5PK67.
L. Breiman, “Random Forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, Oct. 2001, doi: 10.1023/A:1010933404324.
T. Chen and C. Guestrin, “XGBoost,” in Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discov. Data Mining, New York, Aug. 2016, pp. 785–794. doi: 10.1145/2939672.2939785.
G. Ke et al., “LightGBM: A highly efficient gradient boosting decision tree,” in Adv. Neural Inf. Processing Systems, Curran Associates, Inc., 2017, pp. 3146–3154. [Online]. Available: https://proceedings.neurips.cc/paper_files/paper/2017/file/6449f44a102fde848669bdd9eb6b76fa-Paper.pdf
T. Akiba, S. Sano, T. Yanase, T. Ohta, and M. Koyama, “Optuna,” in Proc. 25th ACM SIGKDD Int. Conf. Knowl. Discov. Data Mining, New York, Jul. 2019, pp. 2623–2631. doi: 10.1145/3292500.3330701.
J. Bergstra, R. Bardenet, Y. Bengio, and Y. Kegl, “Algorithms for hyper-parameter optimization,” in Adv. Neural Inf. Processing Systems, J. Shawe-Taylor, R. Zemel, P. Bartlett, F. Pereira, and K. Weinberger, Eds., Curran Associates, Inc., 2011, pp. 2546–2554. [Online]. Available: https://proceedings.neurips.cc/paper_files/paper/2011/file/86e8f7ab32cfd12577bc2619bc635690-Paper.pdf
M. Z. Naser and A. H. Alavi, “Error metrics and performance fitness indicators for artificial intelligence and machine learning in engineering and sciences,” Architecture, Structures and Construction, vol. 3, no. 4, pp. 499–517, Dec. 2023, doi: 10.1007/s44150-021-00015-8.
S. M. Lundberg and S.-I. Lee, “A unified approach to interpreting model predictions,” in Adv. Neural Inf. Processing Systems, 2017, pp. 4765–4774. [Online]. Available: https://proceedings.neurips.cc/paper_files/paper/2017/hash/8a20a8621978632d76c43dfd28b67767-Abstract.html
Downloads
Published
How to Cite
Issue
Section
Categories
License
Copyright (c) 2026 Journal of Novel Engineering Science and Technology
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
