Predicting Flexural Strength of FRP-Strengthened Waste Aggregate Concrete Beams with Machine Learning: A Step Towards Sustainability

Sangthongtong, Arissaman; Chatveera, Burachat; Sua-iam, Gritsada; Nawaz, Adnan; Mehmood, Tahir; Suparp, Suniti; Salman, Muhammad; Noman, Muhammad; Hussain, Qudeer; Saingam, Panumas

doi:10.3390/buildings16081512

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

Predicting Flexural Strength of FRP-Strengthened Waste Aggregate Concrete Beams with Machine Learning: A Step Towards Sustainability

by

Arissaman Sangthongtong

¹,

Burachat Chatveera

²,

Gritsada Sua-iam

³

,

Adnan Nawaz

⁴

,

Tahir Mehmood

⁵

,

Suniti Suparp

⁶

,

Muhammad Salman

⁷

,

Muhammad Noman

⁸

,

Qudeer Hussain

⁹ and

Panumas Saingam

^10,*

¹

Civil Engineering Department, Electrical and Civil Engineering Division, Academic Faculty, Navaminda Kasatriyadhiraj Royal Air Force Academy, Saraburi 18180, Thailand

²

Department of Civil Engineering, Faculty of Engineering, Rangsit Campus, Thammasat University, Pathum Thani 12121, Thailand

³

Department of Civil Engineering, Faculty of Engineering, Rajamangala University of Technology Phra Nakhon, Bangkok 10800, Thailand

⁴

Department of Civil Engineering, COMSATS University Islamabad, Wah Campus, Islamabad 45550, Pakistan

⁵

Architecture and Civil Engineering Department, Sultan Qaboos University, Muscat 123, Oman

⁶

Department of Civil and Environmental Engineering, Faculty of Engineering, Srinakharinwirot University, Nakhonnayok 26120, Thailand

⁷

Department of Mathematics, Computer Science and Engineering, University of Quebec at Rimouski, Rimouski, QC G5L 3A1, Canada

⁸

Civil and Coastal Engineering Department, University of Florida, Gainesville, FL 32603, USA

⁹

Civil Engineering Department, Kasem Bundit University, Bangkok 10510, Thailand

¹⁰

Department of Civil Engineering, School of Engineering, King Mongkut’s Institute of Technology Ladkrabang, Bangkok 10520, Thailand

^*

Author to whom correspondence should be addressed.

Buildings 2026, 16(8), 1512; https://doi.org/10.3390/buildings16081512

Submission received: 7 February 2026 / Revised: 22 March 2026 / Accepted: 8 April 2026 / Published: 12 April 2026

(This article belongs to the Collection Advanced Concrete Materials in Construction)

Download Versions Notes

Abstract

Using waste materials in the manufacture of concrete has many environmental advantages. However, it can be difficult to estimate structural performance, especially when beams are reinforced with fiber-reinforced polymers (FRP). In order to provide a data-driven approach to sustainable structural design, this work explores the use of machine learning (ML) approaches to forecast the flexural strength of FRP-strengthened waste aggregate concrete beams. A total number of 92 experimental datasets were used to develop and assess four ML algorithms: Random Forest (RF), Decision Tree (DT), Neural Network (NN), and Extreme Gradient Boosting (XGBoost). Regression plots, Taylor diagrams, statistical measures (R2R^2R2, RMSE, MAE, MSE), and explainable AI (XAI) tools, including SHAP, LIME, and partial dependence plots (PDPs), were used to evaluate the model’s performance. RF outperformed NN in terms of predictive accuracy, while XGBoost exhibited similar performance to RF. The most significant predictors, according to a SHAP analysis, were beam length and fiber length, with the lower followed by steel tensile strength, fiber width, and concrete compressive strength. LIME offered local interpretability for individual predictions, but PDPs demonstrated optimal parameter ranges and a nonlinear feature strength relationship. The findings provide engineers with a strong decision-support tool for designing green infrastructure, since they show that ensemble-based models can accurately represent the intricate, nonlinear dynamics controlling flexural behavior in sustainable FRP-strengthened waste aggregate concrete beams.

Keywords: machine learning; random forest; XGBoost; SHAP; FRP-strengthened waste aggregate concrete beams; sustainability

Share and Cite

MDPI and ACS Style

Sangthongtong, A.; Chatveera, B.; Sua-iam, G.; Nawaz, A.; Mehmood, T.; Suparp, S.; Salman, M.; Noman, M.; Hussain, Q.; Saingam, P. Predicting Flexural Strength of FRP-Strengthened Waste Aggregate Concrete Beams with Machine Learning: A Step Towards Sustainability. Buildings 2026, 16, 1512. https://doi.org/10.3390/buildings16081512

AMA Style

Sangthongtong A, Chatveera B, Sua-iam G, Nawaz A, Mehmood T, Suparp S, Salman M, Noman M, Hussain Q, Saingam P. Predicting Flexural Strength of FRP-Strengthened Waste Aggregate Concrete Beams with Machine Learning: A Step Towards Sustainability. Buildings. 2026; 16(8):1512. https://doi.org/10.3390/buildings16081512

Chicago/Turabian Style

Sangthongtong, Arissaman, Burachat Chatveera, Gritsada Sua-iam, Adnan Nawaz, Tahir Mehmood, Suniti Suparp, Muhammad Salman, Muhammad Noman, Qudeer Hussain, and Panumas Saingam. 2026. "Predicting Flexural Strength of FRP-Strengthened Waste Aggregate Concrete Beams with Machine Learning: A Step Towards Sustainability" Buildings 16, no. 8: 1512. https://doi.org/10.3390/buildings16081512

APA Style

Sangthongtong, A., Chatveera, B., Sua-iam, G., Nawaz, A., Mehmood, T., Suparp, S., Salman, M., Noman, M., Hussain, Q., & Saingam, P. (2026). Predicting Flexural Strength of FRP-Strengthened Waste Aggregate Concrete Beams with Machine Learning: A Step Towards Sustainability. Buildings, 16(8), 1512. https://doi.org/10.3390/buildings16081512

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Predicting Flexural Strength of FRP-Strengthened Waste Aggregate Concrete Beams with Machine Learning: A Step Towards Sustainability

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI