This study combines an experimental lightweight-concrete program with a small-sample machine-learning benchmark. Eleven mixtures were produced by replacing normal-weight fine and coarse aggregates with expanded clay at volumetric ratios from 0 to 100%. Density and compressive strength were measured at 7, 14, and 28 days. Under the adopted requirement of 28-day strength not lower than 40 MPa, the mixture containing 60% lightweight and 40% normal-weight aggregate provided the lowest measured density (1925 kg/m³) while retaining 42.7 MPa compressive strength. Python-based degree-2 polynomial models were fitted to the 11 series averages and compared by leave-one-out cross-validation (LOOCV) with Random Forest, XGBoost, and a compact multilayer perceptron. The polynomial model achieved the best LOOCV density performance (R² = 0.9883; RMSE = 31.33 kg/m³) and remained competitive for strength (R² = 0.9700; RMSE = 0.91 MPa), whereas the MLP produced the best strength score. The results support an interpretable polynomial model for preliminary screening of this small, single-factor dataset, while broader predictive claims require larger multi-factor data.
M. B. Khan, A. O. Baarimah, M. S. M. Banaimoon, M. B. Ramu, A. F. Ebrahim, B. T. Alsulami, and H. Almujibah, “Exploring the synergy between aluminum powder and silica fume in enhancing lightweight concrete characteristics,” Scientific Reports, vol. 15, Art. no. 26349, 2025, [Online]. Available: https://doi.org/10.1038/s41598-025-26349-7.
M. R. Ahmad and B. Chen, “Experimental research on the performance of lightweight concrete containing foam and expanded clay aggregate,” Composites Part B: Engineering, vol. 171, pp. 46-60, 2019, [Online]. Available: https://doi.org/10.1016/j.compositesb.2019.04.025.
T. J. Rajeeth, A. Sharma, R. Honnalli, S. Yantrapalli, S. N. Shinde, and S. Thenmozhial, “Experimental investigation and optimization of cellular lightweight concrete using foam content and prediction using response surface methodology,” Discover Sustainability, vol. 6, 2025, [Online]. Available: https://doi.org/10.1007/s43621-025-01829-y.
A. A. Aziz and I. F. Al Mulla, “An experimental investigation of the mechanical properties of lightweight concrete with pumice aggregate and polypropylene fibers,” Engineering, Technology & Applied Science Research, vol. 15, no. 5, pp. 26344-26350, 2025, [Online]. Available: https://doi.org/10.48084/etasr.12495.
X. Zhang, X. Kuang, J. H. Yang, and S. R. Wang, “Experimental study on mechanical properties of lightweight concrete with shale aggregate replaced part by natural sand,” Electronic Journal of Structural Engineering, vol. 17, pp. 85-94, 2017, [Online]. Available: https://doi.org/10.56748/ejse.17222.
S. Chandra and L. Berntsson, Lightweight Aggregate Concrete: Science, Technology and Applications. Norwich, NY, USA: Noyes Publications, 2002.
O. Fozilov, A. Martazaev, S. Razzakov, R. Mavlonov, and B. Maksud ugli, “Numerical modeling of reinforced concrete structures made of lightweight concrete using ANSYS,” Vibroengineering Procedia, vol. 60, pp. 683-689, 2025, [Online]. Available: https://doi.org/10.21595/vp.2025.25511.
A. Martazaev, S. Razzakov, R. Mavlonov, O. Fozilov, and B. Maksud ugli, “Theoretical assessment of the mechanical properties of fiber concrete using the dispersion analysis method,” Vibroengineering Procedia, vol. 60, pp. 788-794, 2025, [Online]. Available: https://doi.org/10.21595/vp.2025.25362.
R. S. Mehany, H. M. Mohamed, and B. Benmokrane, “Flexural Strength and Serviceability of GFRP-Reinforced Lightweight Self-Consolidating Concrete Beams,” Journal of Composites for Construction, vol. 26, no. 3, Art. no. 04022020, Jun. 2022, doi: 10.1061/(ASCE)CC.1943-5614.0001208.
A. A. Yadav et al., “AI-driven sustainable concrete mix design: Hybrid deep Q-Learning and genetic algorithms-based multi-objective machine learning optimizations for high structural strength, low cost, and low carbon footprints,” Structures, vol. 82, 2025, [Online]. Available: https://doi.org/10.1016/j.istruc.2025.110443.
J. Wang, J. Deng, S. Li, W. Du, Z. Zhang, and X. Liu, “Explainable Machine Learning for Multicomponent Concrete: Predictive Modeling and Feature Interaction Insights,” Materials, vol. 18, no. 19, Art. no. 4456, 2025, [Online]. Available: https://doi.org/10.3390/ma18194456.
I. C. Yeh, “Modeling of strength of high-performance concrete using artificial neural networks,” Cement and Concrete Research, vol. 28, no. 12, pp. 1797-1808, 1998, [Online]. Available: https://doi.org/10.1016/S0008-8846(98)00165-3.
A. S. Balykov, E. A. Kaledina, and S. V. Volodin, “Compressive strength prediction and composition design of structural lightweight concretes using machine learning methods,” Nanotechnologies in Construction, vol. 15, pp. 171-186, 2023, [Online]. Available: https://doi.org/10.15828/2075-8545-2023-15-2-171-186.
F. Hussain, S. A. Khan, R. A. Khushnood, A. Hamza, and F. Rehman, “Machine learning-based predictive modeling of sustainable lightweight aggregate concrete,” Sustainability, vol. 15, no. 1, Art. no. 641, 2023, [Online]. Available: https://doi.org/10.3390/su15010641.
S. H. Han, K. H. Khayat, S. Park, and J. Yoon, “Machine learning-based approach for optimizing mixture proportion of recycled plastic aggregate concrete considering compressive strength, dry density, and production cost,” Journal of Building Engineering, vol. 83, Art. no. 108393, 2024, [Online]. Available: https://doi.org/10.1016/j.jobe.2023.108393.
P. Ziolkowski, “Influence of optimization algorithms and computational complexity on concrete compressive strength prediction machine learning models for concrete mix design,” Materials, vol. 18, no. 6, Art. no. 1386, 2025, [Online]. Available: https://doi.org/10.3390/ma18061386.
GOST 10180-2012: Concrete. Methods for Determining Strength Using Control Specimens. Moscow, Russia: Standartinform, 2013.
L. Breiman, “Random forests,” Machine Learning, vol. 45, no. 1, pp. 5-32, 2001, [Online]. Available: https://doi.org/10.1023/A:1010933404324.
T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, pp. 785-794, 2016, [Online]. Available: https://doi.org/10.1145/2939672.2939785.
F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay, “Scikit-learn: Machine learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825-2830, 2011.
American Concrete Institute Committee 213, ACI 213R-03: Guide for Structural Lightweight-Aggregate Concrete. Farmington Hills, MI, USA, 2003.
ASTM International, ASTM C330/C330M-17a: Standard Specification for Lightweight Aggregates for Structural Concrete. West Conshohocken, PA, USA, 2017.
S. A. Stel’makh, E. M. Shcherban’, A. N. Beskopylny, L. R. Mailyan, B. Meskhi, I. Razveeva, and N. Beskopylny, “Prediction of mechanical properties of highly functional lightweight fiber-reinforced concrete based on deep neural network and ensemble regression trees methods,” Materials, vol. 15, no. 19, Art. no. 6740, 2022, [Online]. Available: https://doi.org/10.3390/ma15196740.
Y. T. Altuncı, “A comprehensive study on the estimation of concrete compressive strength using machine learning models,” Buildings, vol. 14, no. 12, Art. no. 3851, 2024, [Online]. Available: https://doi.org/10.3390/buildings14123851.
