STATISTICAL AND EXPLAINABLE MACHINE LEARNING MODELS FOR PREDICTING CONCRETE COMPRESSIVE STRENGTH A COMPARATIVE PREDICTIVE ANALYSIS
DOI:
https://doi.org/10.69980/bh15b277Keywords:
Concrete compressive strength, Machine learning, Support Vector Regression, SHAP, Explainable artificial intelligenceAbstract
This Study has created a comparative statistical and explainable machine-learning model for predicting concrete compressive strength based on the mixture-design variables. This was analyzed using experimental data of 235 concrete mixtures with five predictors, namely cement, fly ash, R Sand, M Sand and water and compressive strength at 3, 7, 28 and 90 days. The compressive strength at 28 days was considered the main prediction target. Decision Tree, Random Forest, Gradient Boosting, Support Vector Regression, and K-Nearest Neighbors models were used in combination with descriptive statistics, Pearson correlation, multicollinearity analysis, and multiple linear regression. R 2, MAE, MSE, RMSE and five-fold cross-validation were used to assess model performance. Findings indicated that nonlinear models were significantly better when compared to Multiple Linear Regression. Support Vector Regression had the best test result, R 2 = 0.9995, MAE = 0.096, MSE = 0.047, and RMSE = 0.218, and the lowest cross-validated RMSE = 0.246. SHAP analysis showed cement and fly ash to be the most significant predictors, followed by R Sand, M Sand and water. The results indicate that explainable machine learning has the potential to deliver very accurate and interpretable concrete-strength predictions, justifying the fast mix-evaluation and engineering decision-making.
References
[1]. Young BA, Hall A, Pilon L, Gupta P, Sant G. Can the compressive strength of concrete be estimated from knowledge of the mixture proportions?: New insights from statistical analysis and machine learning methods. Cement and concrete research. 2019;115:379–88.
[2]. Jayaprakash G, Muthuraj MP. Prediction of compressive strength of various SCC mixes using relevance vector machine. Comput Mater Continua. 2018;54(1):83–102.
[3]. Han Q, Gui C, Xu J, Lacidogna G. A generalized method to predict the compressive strength of high-performance concrete by improved random forest algorithm. Construction and Building Materials. 2019;226:734–42.
[4]. Zhang J, Ma G, Huang Y, Aslani F, Nener B. Modelling uniaxial compressive strength of lightweight self-compacting concrete using random forest regression. Construction and Building Materials. 2019;210:713–9.
[5]. DeRousseau MA, Laftchiev E, Kasprzyk JR, Rajagopalan B, Srubar III WV. A comparison of machine learning methods for predicting the compressive strength of field-placed concrete. Construction and Building Materials. 2019;228:116661.
[6]. Chopra P, Sharma RK, Kumar M, Chopra T. Comparison of Machine Learning Techniques for the Prediction of Compressive Strength of Concrete. Rossi PP, editor. Advances in Civil Engineering. 2018 Jan;2018(1):5481705. doi:10.1155/2018/5481705
[7]. Al-Shamiri AK, Kim JH, Yuan TF, Yoon YS. Modeling the compressive strength of high-strength concrete: An extreme learning approach. Construction and Building Materials. 2019;208:204–19.
[8]. Feng DC, Liu ZT, Wang XD, Chen Y, Chang JQ, Wei DF, et al. Machine learning-based compressive strength prediction for concrete: An adaptive boosting approach. Construction and Building Materials. 2020;230:117000.
[9]. Farooq F, Nasir Amin M, Khan K, Rehan Sadiq M, Javed MF, Aslam F, et al. A comparative study of random forest and genetic engineering programming for the prediction of compressive strength of high strength concrete (HSC). Applied Sciences. 2020;10(20):7330.
[10]. Huynh AT, Nguyen QD, Xuan QL, Magee B, Chung T, Tran KT, et al. A machine learning-assisted numerical predictor for compressive strength of geopolymer concrete based on experimental data and sensitivity analysis. Applied Sciences. 2020;10(21):7726.
[11]. Wan Z, Xu Y, Šavija B. On the use of machine learning models for prediction of compressive strength of concrete: influence of dimensionality reduction on the model performance. Materials. 2021;14(4):713.
[12]. Arrieta AB, Díaz-Rodríguez N, Del Ser J, Bennetot A, Tabik S, Barbado A, et al. Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Information fusion. 2020;58:82–115.
[13]. Lundberg SM, Erion G, Chen H, DeGrave A, Prutkin JM, Nair B, et al. From local explanations to global understanding with explainable AI for trees. Nature machine intelligence. 2020;2(1):56–67.
[14]. Chaabene WB, Flah M, Nehdi ML. Machine learning prediction of mechanical properties of concrete: Critical review. Construction and Building Materials. 2020;260:119889.
[15]. Xu J, Zhou L, He G, Ji X, Dai Y, Dang Y. Comprehensive machine learning-based model for predicting compressive strength of ready-mix concrete. Materials. 2021;14(5):1068.
[16]. Oyebisi S. Raw dataset for evaluating the effects of M sand and fly ash on concrete strength using experimental and machine learning approaches [Internet]. 2024 Jul 26. doi:10.5281/zenodo.13000484
[17]. Nunez I, Marani A, Flah M, Nehdi ML. Estimating compressive strength of modern concrete mixtures using computational intelligence: A systematic review. Construction and Building Materials. 2021;310:125279.
[18]. Nguyen MH, Ly HB. Development of machine learning methods to predict the compressive strength of fiber-reinforced self-compacting concrete and sensitivity analysis. Construction and Building Materials. 2023;367:130339.
[19]. Nguyen NH, Abellán-García J, Lee S, Garcia-Castano E, Vo TP. Efficient estimating compressive strength of ultra-high performance concrete using XGBoost model. Journal of Building Engineering. 2022;52:104302.
[20]. Pakzad SS, Roshan N, Ghalehnovi M. Comparison of various machine learning algorithms used for compressive strength prediction of steel fiber-reinforced concrete. Scientific Reports. 2023;13(1):3646.
[21]. Qureshi HJ, Alyami M, Nawaz R, Hakeem IY, Aslam F, Iftikhar B, et al. Prediction of compressive strength of two-stage (preplaced aggregate) concrete using gene expression programming and random forest. Case Studies in Construction Materials. 2023;19:e02581.
[22]. Zeng Z, Zhu Z, Yao W, Wang Z, Wang C, Wei Y, et al. Accurate prediction of concrete compressive strength based on explainable features using deep learning. Construction and Building Materials. 2022;329:127082.
[23]. Jia JF, Chen XZ, Bai YL, Li YL, Wang ZH. An interpretable ensemble learning method to predict the compressive strength of concrete. In: Structures [Internet]. Elsevier; 2022 [cited 2026 Sep 12]. p. 201–13. Available from: https://www.sciencedirect.com/science/article/pii/S2352012422009559
[24]. Li XH, Cao CC, Shi Y, Bai W, Gao H, Qiu L, et al. A survey of data-driven and knowledge-aware explainable AI. IEEE Transactions on Knowledge and Data Engineering. 2020;34(1):29–49.
[25]. Liu G, Sun B. Concrete compressive strength prediction using an explainable boosting machine model. Case Studies in Construction Materials. 2023;18:e01845.
[26]. Sun B, Cui W, Liu G, Zhou B, Zhao W. A hybrid strategy of AutoML and SHAP for automated and explainable concrete strength prediction. Case Studies in Construction Materials. 2023;19:e02405.
[27]. Elhishi S, Elashry AM, El-Metwally S. Unboxing machine learning models for concrete strength prediction using XAI. Scientific Reports. 2023;13(1):19892.
[28]. Zhang Y, Ren W, Chen Y, Mi Y, Lei J, Sun L. Predicting the compressive strength of high-performance concrete using an interpretable machine learning model. Scientific Reports. 2024;14(1):28346.
[29]. Elshaarawy MK, Alsaadawi MM, Hamed AK. Machine learning and interactive GUI for concrete compressive strength prediction. Scientific Reports. 2024;14(1):16694.
