Prediction of splitting tensile strength of fiber-reinforced recycled aggregate concrete utilizing machine learning models with SHAP analysis

The infrastructure industry utilizes a significant number of natural resources and produces a lot of construction waste, both of which have negative environmental effects. As a solution, recycled aggregate concrete has emerged as a practical substitute. Predicting strength accurately is essential fo...

Full description

Saved in:
Bibliographic Details
Main Authors: Md Al Adnan, Muhammad Babur, Faisal Farooq, Mursaleen Shahid, Zamiul Ahmed, Pobithra Das
Format: Article
Language:English
Published: Elsevier 2025-12-01
Series:Hybrid Advances
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2773207X25001319
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850236425421717504
author Md Al Adnan
Muhammad Babur
Faisal Farooq
Mursaleen Shahid
Zamiul Ahmed
Pobithra Das
author_facet Md Al Adnan
Muhammad Babur
Faisal Farooq
Mursaleen Shahid
Zamiul Ahmed
Pobithra Das
author_sort Md Al Adnan
collection DOAJ
description The infrastructure industry utilizes a significant number of natural resources and produces a lot of construction waste, both of which have negative environmental effects. As a solution, recycled aggregate concrete has emerged as a practical substitute. Predicting strength accurately is essential for cutting design time and expenses while limiting material waste from numerous mixing tests. Machine learning methods tackle structural engineering issues, including the prediction of Splitting Tensile Strength (STS). In this study, used four novel machine learning models such as Random Forest Regression (RFR), Extreme Gradient Boosting (XGBoost), Gradient Boosted Regression Trees (GBRT), and Bagging Regressor (BR) with grid search for hyperparameter tuning to forecast the splitting tensile strength of fiber-reinforced recycled aggregate concrete (FRRAC). The machine learning models demonstrated high reliability in predicting splitting tensile strength, including robust values for R-squared (R2), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE) and Mean Absolute Error (MAE). The prediction performance of the GBRT models showed the greatest R2 value of 0.95 during the training stage and R2 value of 0.83 during the testing phase. The XGBoost, RFR and BR models found R-square values were 0.822, 0.781 and 0.824 at the testing phase, respectively. Moreover, the RFR, BR, GBRT, and XGBoost model RMSE values were found to be 0.333, 0.298, 0.276, and 0.3004 at the testing phase, respectively, where the GBRT model RMSE value was found to be good. The GBRT model showed the lowest uncertainty value of both phases, with values of 0.619 and 0.597 for the training and testing phases, respectively. Furthermore, SHapley Additive exPlanations (SHAP) analysis found that CR, and additional of Fiber were the most influential input features and replacement percentage of CR (%) and RCA Absorption capacity (%) inputs had the lowest impact of Fiber-Reinforced Recycled Aggregate Concrete for predicting splitting tensile strength. These results indicate that the suggested technique can significantly contribute to sustainable construction practices by precisely predicting splitting tensile strength.
format Article
id doaj-art-4eb353fff4fb457ca77e4a1cff1c4426
institution OA Journals
issn 2773-207X
language English
publishDate 2025-12-01
publisher Elsevier
record_format Article
series Hybrid Advances
spelling doaj-art-4eb353fff4fb457ca77e4a1cff1c44262025-08-20T02:01:58ZengElsevierHybrid Advances2773-207X2025-12-011110050710.1016/j.hybadv.2025.100507Prediction of splitting tensile strength of fiber-reinforced recycled aggregate concrete utilizing machine learning models with SHAP analysisMd Al Adnan0Muhammad Babur1Faisal Farooq2Mursaleen Shahid3Zamiul Ahmed4Pobithra Das5Institute of Information Technology, Noakhali Science and Technology University, Noakhali, BangladeshDepartment of Civil Engineering, Faculty of Engineering, University of Central Punjab, PakistanDepartment of Engineering, Aarhus University, DenmarkDepartment of Industrial Engineering, University of Trento, Trento, ItalyDepartment of Civil Engineering, East West University, BangladeshDepartment of Civil Engineering, Leading University, Sylhet, 3112, Bangladesh; Corresponding author.The infrastructure industry utilizes a significant number of natural resources and produces a lot of construction waste, both of which have negative environmental effects. As a solution, recycled aggregate concrete has emerged as a practical substitute. Predicting strength accurately is essential for cutting design time and expenses while limiting material waste from numerous mixing tests. Machine learning methods tackle structural engineering issues, including the prediction of Splitting Tensile Strength (STS). In this study, used four novel machine learning models such as Random Forest Regression (RFR), Extreme Gradient Boosting (XGBoost), Gradient Boosted Regression Trees (GBRT), and Bagging Regressor (BR) with grid search for hyperparameter tuning to forecast the splitting tensile strength of fiber-reinforced recycled aggregate concrete (FRRAC). The machine learning models demonstrated high reliability in predicting splitting tensile strength, including robust values for R-squared (R2), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE) and Mean Absolute Error (MAE). The prediction performance of the GBRT models showed the greatest R2 value of 0.95 during the training stage and R2 value of 0.83 during the testing phase. The XGBoost, RFR and BR models found R-square values were 0.822, 0.781 and 0.824 at the testing phase, respectively. Moreover, the RFR, BR, GBRT, and XGBoost model RMSE values were found to be 0.333, 0.298, 0.276, and 0.3004 at the testing phase, respectively, where the GBRT model RMSE value was found to be good. The GBRT model showed the lowest uncertainty value of both phases, with values of 0.619 and 0.597 for the training and testing phases, respectively. Furthermore, SHapley Additive exPlanations (SHAP) analysis found that CR, and additional of Fiber were the most influential input features and replacement percentage of CR (%) and RCA Absorption capacity (%) inputs had the lowest impact of Fiber-Reinforced Recycled Aggregate Concrete for predicting splitting tensile strength. These results indicate that the suggested technique can significantly contribute to sustainable construction practices by precisely predicting splitting tensile strength.http://www.sciencedirect.com/science/article/pii/S2773207X25001319Splitting tensile strengthMachine learningRecycled aggregate concreteFiber-reinforcedAnd SHapley additive exPlanations
spellingShingle Md Al Adnan
Muhammad Babur
Faisal Farooq
Mursaleen Shahid
Zamiul Ahmed
Pobithra Das
Prediction of splitting tensile strength of fiber-reinforced recycled aggregate concrete utilizing machine learning models with SHAP analysis
Hybrid Advances
Splitting tensile strength
Machine learning
Recycled aggregate concrete
Fiber-reinforced
And SHapley additive exPlanations
title Prediction of splitting tensile strength of fiber-reinforced recycled aggregate concrete utilizing machine learning models with SHAP analysis
title_full Prediction of splitting tensile strength of fiber-reinforced recycled aggregate concrete utilizing machine learning models with SHAP analysis
title_fullStr Prediction of splitting tensile strength of fiber-reinforced recycled aggregate concrete utilizing machine learning models with SHAP analysis
title_full_unstemmed Prediction of splitting tensile strength of fiber-reinforced recycled aggregate concrete utilizing machine learning models with SHAP analysis
title_short Prediction of splitting tensile strength of fiber-reinforced recycled aggregate concrete utilizing machine learning models with SHAP analysis
title_sort prediction of splitting tensile strength of fiber reinforced recycled aggregate concrete utilizing machine learning models with shap analysis
topic Splitting tensile strength
Machine learning
Recycled aggregate concrete
Fiber-reinforced
And SHapley additive exPlanations
url http://www.sciencedirect.com/science/article/pii/S2773207X25001319
work_keys_str_mv AT mdaladnan predictionofsplittingtensilestrengthoffiberreinforcedrecycledaggregateconcreteutilizingmachinelearningmodelswithshapanalysis
AT muhammadbabur predictionofsplittingtensilestrengthoffiberreinforcedrecycledaggregateconcreteutilizingmachinelearningmodelswithshapanalysis
AT faisalfarooq predictionofsplittingtensilestrengthoffiberreinforcedrecycledaggregateconcreteutilizingmachinelearningmodelswithshapanalysis
AT mursaleenshahid predictionofsplittingtensilestrengthoffiberreinforcedrecycledaggregateconcreteutilizingmachinelearningmodelswithshapanalysis
AT zamiulahmed predictionofsplittingtensilestrengthoffiberreinforcedrecycledaggregateconcreteutilizingmachinelearningmodelswithshapanalysis
AT pobithradas predictionofsplittingtensilestrengthoffiberreinforcedrecycledaggregateconcreteutilizingmachinelearningmodelswithshapanalysis