Integrated Prediction Model for Normal and Recycled Aggregate Concrete Strength Using Ensemble Learning Techniques

Sujiat; Eko wahyu Abryandoko; Ocha Silvia Kencana; Nayla Farikha Zahra

doi:10.56741/jnest.v5i02.2092

Integrated Prediction Model for Normal and Recycled Aggregate Concrete Strength Using Ensemble Learning Techniques

Authors

Sujiat Universitas Bojonegoro https://orcid.org/0009-0000-4336-9201
Eko wahyu Abryandoko Universitas Bojonegoro https://orcid.org/0000-0003-0480-6135
Ocha Silvia Kencana Universitas Bojonegoro
Nayla Farikha Zahra Universitas Bojonegoro https://orcid.org/0009-0007-3978-2109

DOI:

https://doi.org/10.56741/jnest.v5i02.2092

Keywords:

Compressive Strength Prediction, LightGBM, Machine Learning, Recycled Aggregate Concrete

Abstract

Recycled aggregate concrete (RAC) is a sustainable alternative construction material to reduce natural resource exploitation and manage construction and demolition waste. However, predicting the mechanical performance of RAC remains a challenge due to the high variability of recycled aggregate properties. The purpose of this study is to develop a machine learning model to predict the compressive strength of recycled aggregate-based concrete and compare its performance with normal concrete. The dataset used consists of 2165 samples (1600 normal concrete and 565 recycled aggregate concrete) collected from various scientific publications. Three tree-based machine learning algorithms (Random Forest, XGBoost, and LightGBM) were implemented and optimized using RandomizedSearchCV with 5-fold cross-validation. The results showed that LightGBM provided the best performance with R² = 0.92, MAE = 2.45 MPa, and RMSE = 3.52 MPa on the test set. This model is able to predict the compressive strength of normal concrete (R² = 0.92) and recycled aggregate concrete (R² = 0.91) with almost the same accuracy, indicating strong generalization. Feature importance analysis revealed that curing age, cement content, and water content are the most important factors in compressive strength prediction, while for RAC, recycled aggregate water absorption (WRCA) also makes a significant contribution. Error analysis shows that residuals are random and normally distributed without systematic bias. This model can reliably predict concrete compressive strength in the range of 20-60 MPa with an average error of ±3-4 MPa and can be integrated into mix proportioning design software to improve the efficiency of the design process and support the use of sustainable construction materials.

Downloads

Download data is not yet available.

Author Biographies

Sujiat, Universitas Bojonegoro

is a full-time lecturer in the Department of Civil Engineering at Universitas Bojonegoro (Unigoro), Bojonegoro, Indonesia. He holds a Master’s degree in Engineering and is actively involved in scientific research, particularly in the field of pavement engineering, including studies on optimum asphalt content analysis. (email: radenjiat89@gmail.com)

Eko wahyu Abryandoko, Universitas Bojonegoro

is a lecturer and academic at Universitas Bojonegoro (Unigoro), Bojonegoro, Indonesia, where he currently serves as the Head of the Industrial Engineering Study Program. He received his Doctoral degree (Ph.D.) in 2025, with research focused on the development of rehabilitation robots for post-stroke patients. (email: abryandoko@gmail.com)

Ocha Silvia Kencana, Universitas Bojonegoro

is an undergraduate student in the Department of Industrial Engineering, Universitas Bojonegoro, Indonesia. (email: silviaocha5@gmail.com)

Nayla Farikha Zahra, Universitas Bojonegoro

is an undergraduate student in the Department of Industrial Engineering, Universitas Bojonegoro, Indonesia. (email: ppuja8839@gmail.com)

References

A. T. Balasbaneh, W. Sher, J. Li, and A. Ashour, “Systematic review of construction waste management scenarios: Informing life cycle sustainability analysis,” Circular Econ. Sustain., vol. 5, no. 1, pp. 529-553, 2025. doi: 10.1007/s43615-024-00424-z. DOI: https://doi.org/10.1007/s43615-024-00424-z

S. Lee, H. Chang, and J. Lee, “Construction and demolition waste management and its impacts on the environment and human health: Moving forward sustainability enhancement,” Sustain. Cities Soc., vol. 115, e105855, 2024. doi: 10.1016/j.scs.2024.105855. DOI: https://doi.org/10.1016/j.scs.2024.105855

I. Papamichael, I. Voukkali, P. Loizia, and A. A. Zorpas, “Construction and demolition waste framework of circular economy: A mini review,” Waste Manag. Res., vol. 41, no. 12, pp. 1728-1740, 2023, doi: 10.1177/0734242X231190804. DOI: https://doi.org/10.1177/0734242X231190804

G. C. R. Hasibuan et al., “Integrating circular economy into construction and demolition waste management: A bibliometric review of sustainable engineering practices in the built environment,” Case Stud. in Chem. Environ. Eng., vol. 11, e101159, 2025, doi: 10.1016/j.cscee.2025.101159. DOI: https://doi.org/10.1016/j.cscee.2025.101159

X. Yuan et al., “Machine Learning Prediction Models to Evaluate the Strength of Recycled Aggregate Concrete,” Materials, vol. 15, no. 8, e2823, 2022, doi: 10.3390/ma15082823. DOI: https://doi.org/10.3390/ma15082823

D. Wang et al., “Mechanical performance of recycled aggregate concrete in green civil engineering: Review,” Case Stud. in Constr. Mater., vol. 19, e02384, 2023, doi: 10.1016/j.cscm.2023.e02384. DOI: https://doi.org/10.1016/j.cscm.2023.e02384

Y. Ji, D. Wang, and J. Wang, “Study of recycled concrete properties and prediction using machine learning methods,” J. Build. Eng., vol. 94, e110067, 2024, doi: 10.1016/j.jobe.2024.110067. DOI: https://doi.org/10.1016/j.jobe.2024.110067

H. G. Gebremariam, S. Taye, and A. G. Tarekegn, “Compressive strength prediction of carbonated recycled aggregate concrete using regression based machine learning models,” Sci. Rep., 2026, doi: 10.1038/s41598-026-36197-8. DOI: https://doi.org/10.1038/s41598-026-36197-8

X. Zhang, C. Dai, W. Li, and Y. Chen, “Prediction of compressive strength of recycled aggregate concrete using machine learning and Bayesian optimization methods,” Front. Earth Sci. (Lausanne)., vol. 11, e1112105, 2023, doi: 10.3389/feart.2023.1112105. DOI: https://doi.org/10.3389/feart.2023.1112105

M. Hosseinzadeh, M. Dehestani, and A. Hosseinzadeh, “Prediction of mechanical properties of recycled aggregate fly ash concrete employing machine learning algorithms,” J. Build. Eng., vol. 76, e107006, 2023, doi: 10.1016/j.jobe.2023.107006. DOI: https://doi.org/10.1016/j.jobe.2023.107006

M. S. Khan et al., “Explainable AutoML models for predicting the strength of high-performance concrete using Optuna, SHAP and ensemble learning,” Front. Mater., vol. 12, e1542655, 2025, doi: 10.3389/fmats.2025.1542655. DOI: https://doi.org/10.3389/fmats.2025.1542655

A. Jaglan and R. R. Singh, “Recycled aggregate concrete incorporating GGBS and polypropylene fibers using RSM and machine learning techniques,” Buildings, vol. 15, no. 1, e66, 2025, doi: 10.3390/buildings15010066. DOI: https://doi.org/10.3390/buildings15010066

D. Demirtürk, Ö. Mintemur, and A. Arslan, “Optimizing LightGBM and XGBoost algorithms for estimating compressive strength in high-performance concrete,” Arab. J. Sci. Eng., vol. 51, no. 4, pp. 4401-4423, 2025, doi: 10.1007/s13369-025-10217-7. DOI: https://doi.org/10.1007/s13369-025-10217-7

A. Ahmad, K. A. Ostrowski, M. Maślak, F. Farooq, I. Mehmood, and A. Nafees, “Comparative study of supervised machine learning algorithms for predicting the compressive strength of concrete at high temperature,” Mat., vol. 14, no. 15, e4222, 2021, doi: 10.3390/ma14154222. DOI: https://doi.org/10.3390/ma14154222

N. D. Hoang, “Leveraging a hybrid machine learning approach for compressive strength estimation of roller-compacted concrete with recycled aggregates,” Math., vol. 12, no. 16, e2542, 2024, doi: 10.3390/math12162542. DOI: https://doi.org/10.3390/math12162542

Q. Wang, R. Dai, H. Zhang, H. Zheng, and X. Liang, “Machine learning-based prediction method for drying shrinkage of recycled aggregate concrete,” J. Build. Eng., vol. 96, e110493, 2024, doi: 10.1016/j.jobe.2024.110493. DOI: https://doi.org/10.1016/j.jobe.2024.110493

Y. Zhang, W. Ren, Y. Chen, Y. Mi, J. Lei, and L. Sun, “Predicting the compressive strength of high-performance concrete using an interpretable machine learning model,” Sci. Rep., vol. 14, no. 1, e28346, 2024, doi: 10.1038/s41598-024-79502-z. DOI: https://doi.org/10.1038/s41598-024-79502-z

N. Elshaboury, A. Al-Sakkaf, E. M. Abdelkader, and G. Alfalah, “Construction and demolition waste management research: A science mapping analysis,” Int. J. Environ. Res. Pub. Health, vol. 19, no. 8, e4496, 2022. doi: 10.3390/ijerph19084496. DOI: https://doi.org/10.3390/ijerph19084496

L. Huang, H. Cui, S. Li, and E. Guo, “Hybrid machine learning for elastic modulus prediction in recycled aggregate concrete,” Multiscale Multidiscip. Modeling Expt. Design, vol. 8, no. 7, e323, 2024, doi: 10.1007/s41939-025-00909-w. DOI: https://doi.org/10.1007/s41939-025-00909-w

明邱, “Dataset of compressive strength and slump of normal concrete,” Feb. 2024. doi: 10.17632/zrsbhndz9f.1.

Md. M. Rahman and R. Aayaz, “Recycled aggregate-metakeolin enhanced concrete Compressive Strength DataSet,” Feb. 2025. [Online]. Available: https://data.mendeley.com/datasets/zs42wxbvyf/1