Improving forecasting of concrete strength using advanced machine learning methods

Improving forecasting of concrete strength using advanced machine learning methods Prabakaran Ellappan Dr. N.G.P. Institute of Technology, India http://orcid.org/0009-0007-6716-8560 Lakshmi Keshav Velagapudi Ramakrishna Siddhartha Engineering College, India Kalyana Chakravarthy Polichetty Raja Vels Institute of Science, Technology & Advanced Studies, India Gunnam Sanijya R.V.R. & J.C. College of Engineering, India

Abstract This study presents an improved technique that uses many machine-learning models to estimate the compressive strength of concrete. The goal of the project is to increase the precision of strength predictions based on the age and composition of concrete mixes. Cement, fly ash, water, superplasticizer, coarse and fine aggregate, and sample age are among the materials. Megapascals (MPa) are used to quantify compressive strength. To determine the connections between mix proportions, age, and strength, a variety of blends were examined. Machine learning techniques including Random Forest, XGBoost, AdaBoost, Bagging, Support Vector Regression, and Linear Regression were used. The efficiency of the model was assessed using performance indicators such as accuracy, R-squared (R2), Mean Absolute Error (MAE), and Mean Squared Error (MSE). With an MAE of 2.2, MSE of 10.5, R2 of 0.94, MAPE of 8.5, RMSE of 3.25, and accuracy of 0.92, XGBoost (optimized) performed the best. This model performed noticeably better than others, highlighting how machine learning may improve predictions of compressive strength and optimize the composition of concrete, thus promoting the fields of materials science and civil engineering.
2025 e20240789 S1517-70762025000100284 http://creativecommons.org/licenses/by/4.0/ http://creativecommons.org/licenses/by/4.0/ http://creativecommons.org/licenses/by/4.0/ 10.1590/1517-7076-rmat-2024-0789 http://www.scielo.br/scielo.php?script=sci_arttext&pid=S1517-70762025000100284&tlng=en http://www.scielo.br/scielo.php?script=sci_pdf&pid=S1517-70762025000100284&tlng=en Materials Today. Communications ZHENG W. 35 105901 2023 10.1016/j.mtcomm.2023.105901 “Sustainable predictive model of concrete utilizing waste ingredient: individual alogrithms with optimized ensemble approaches” Geotechnical and Geological Engineering ALADEJARE A.E. 39 6 4427 2021 10.1007/s10706-021-01772-5 “Empirical estimation of uniaxial compressive strength of rock: database of simple, multiple, and artificial intelligence-based regressions” Transportation Geotechnics ALADEJARE A.E. 32 100680 2022 10.1016/j.trgeo.2021.100680 “Data-driven characterization of the correlation between uniaxial compressive strength and Youngs’ modulus of rock without regression models” Matéria (Rio de Janeiro) SRINIVASAN S.S. 29 3 e20240194 2024 10.1590/1517-7076-rmat-2024-0194 “The structural performance of fiber-reinforced concrete beams with nanosilica” Polymers AHMAD A. 13 19 3389 2021 10.3390/polym13193389 “Prediction of geopolymer concrete compressive strength using novel machine learning algorithms” Journal of Ceramic Processing Research VARUTHAIYA M. 23 6 912 2022 “Concrete with sisal fibered geopolymer: a behavioral study” Journal of Advanced Concrete Technology AHMED A.H.A. 20 6 404 2022 10.3151/jact.20.404 “Artificial intelligence models for predicting mechanical properties of recycled aggregate concrete (RAC): critical review” Bulletin of Materials Science THIKE P.H. 43 1 211 2020 10.1007/s12034-020-02154-y “Significance of artificial neural network analytical models in materials’ performance prediction” ADEBAYO J. 2022 “Towards effective tools for debugging machine learning models” Energy and Buildings ADEBAYO P. 320 114646 2024 10.1016/j.enbuild.2024.114646 “Development, modeling, and optimization of ground source heat pump systems for cold climates: a comprehensive review” Journal of Environmental Nanotechnology NAVEEN KUMAR S. 13 2 368 2024 10.13074/jent.2024.06.242584 “A comprehensive microstructural analysis for enhancing concrete’s longevity and environmental sustainability” Journal of Renewable Energy and Environment KINATTINKARA S. 10 1 19 2023 “Deriving an alternative energy using anaerobic co-digestion of water hyacinth, food waste, and cow manure” World Journal of Advanced Research and Reviews ADEWUYI A.Y. 23 1 2469 2024 10.30574/wjarr.2024.23.1.2229 “Application of big data analytics to forecast future waste trends and inform sustainable planning” Engineering and Science KHAJEHZADEH M. 29 1120 1120 2024 “Effective machine-learning models for rock mass deformation modulus estimation based on rock mass classification systems” International Journal of Machine Learning and Cybernetics CHEN Y. 13 7 2089 2022 10.1007/s13042-022-01566-y “A novel method for financial distress prediction based on sparse neural networks with L 1/2 regularization” Resources Policy WANG F. 85 103747 2023 10.1016/j.resourpol.2023.103747 “Emerging pathways to sustainable economic development: An interdisciplinary exploration of resource efficiency, technological innovation, and ecosystem resilience in resource-rich regions” OTCHERE D.A. 2024 Data science and machine learning applications in subsurface engineering Heliyon KHAJEHZADEH M. 9 12 e23012 2023 10.1016/j.heliyon.2023.e23012 “Predicting slope safety using an optimized machine learning model” AIP Conference Proceedings PARTHASAARATHI R. 2861 050002 2023 10.1063/5.0158672 “A stiffness analysis of treated and non-treated meshed coir layer fibre reinforced cement concrete” Journal of Energy Storage MEHRAJ N. 97 112794 2024 10.1016/j.est.2024.112794 “Use of artificial intelligence methods in designing thermal energy storage tanks: a bibliometric analysis” Virtual and Physical Prototyping NG W.L. 15 3 340 2020 10.1080/17452759.2020.1771741 “Deep learning for fabrication and maturation of 3D bioprinted tissues and organs” Research on Engineering Structures and Materials NAVEEN ARASU A. 9 3 843 2023 “Optimization of high performance concrete composites by using nano materials” Computers & Industrial Engineering SUN Q. 189 109948 2024 10.1016/j.cie.2024.109948 “Does environmental carbon pressure lead to low-carbon technology innovation? Empirical evidence from Chinese cities based on satellite remote sensing and machine learning” International Journal of Construction Management MAVI K. 24 14 1550 2023 10.1080/15623599.2023.2266676 “Forecasting project success in the construction industry using adaptive neuro-fuzzy inference system” Journal of Advanced Research in Applied Sciences and Engineering Technology PARTHASAARATHI R. 35 1 106 2024 “Analysing the Impact and Investigating Coconut Shell Fiber Reinforced Concrete (CSFRC) under Varied Loading Conditions” Scientific Reports HOSSEINI S. 13 1 18582 2023 10.1038/s41598-023-46064-5 “Assessment of the ground vibration during blasting in mining projects using different computational approaches” Results in Engineering KOMADJA G.C. 10 100227 2021 10.1016/j.rineng.2021.100227 “Geotechnical and geological investigation of slope stability of a section of road cut debris-slopes along NH-7, Uttarakhand, India” Proceedings of the IEEE SAMEK W. 109 3 247 2021 10.1109/JPROC.2021.3060483 “Explaining deep neural networks and beyond: a review of methods and applications” Journal of Critical Reviews NAVEEN ARASU A. 7 17 3827 2020 “Investigation on partial replacement of cement by GGBS” Proceedings of the IEEE SAMEK W. 109 3 247 2021 10.1109/JPROC.2021.3060483 “Explaining deep neural networks and beyond: a review of methods and applications” Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency DENG W.H. 473 2022 10.1145/3531146.3533113 “Exploring how machine learning practitioners (try to) use fairness toolkits” International Journal of Biological Macromolecules MOHAMMADPOUR A. 277 2 134060 2024 10.1016/j.ijbiomac.2024.134060 “Bioengineered FeZn/GA@ Cu nanocomposite utilizing spent coffee ground extract and gum arabic: enhanced nitrate removal via (RSM) and machine learning optimization” Sustainability ADEWUYI O.B. 14 22 15448 2022 10.3390/su142215448 “Power system voltage stability margin estimation using adaptive neuro-fuzzy Inference system enhanced with particle swarm optimization” Matéria (Rio de Janeiro) KADHAR S.A. 29 1 e20230336 2024 10.1590/1517-7076-rmat-2023-0336 “Optimizing flow, strength, and durability in high-strength self-compacting and self-curing concrete utilizing lightweight aggregates” Buildings HAN S. 13 6 1411 2023 10.3390/buildings13061411 “Performance improvement of recycled concrete aggregates and their potential applications in infrastructure: a review” Journal of the Balkan Tribological Association SHANKAR S. 30 1 142 2024 “Exploring the strength and durability characteristics of high-performance fibre reinforced concrete containing nanosilica” The Science of the Total Environment ASHRAF U. 937 173425 2024 10.1016/j.scitotenv.2024.173425 “An ensemble-based strategy for robust predictive volcanic rock typing efficiency on a global-scale: a novel workflow driven by big data analytics” The Asian Review of Civil Engineering VIVEK S. 9 2 1 2020 10.51983/tarce-2020.9.2.2556 “Experimental investigation on bricks by using cow dung, rice husk, egg shell powder as a partial replacement for fly ash” Environmental Science and Pollution Research International SAINI S.K. 30 43 97463 2023 10.1007/s11356-023-29049-9 “Modeling flood susceptibility zones using hybrid machine learning models of an agricultural dominant landscape of India” MRS Communications ESPINO M.T. 13 2 193 2023 10.1557/s43579-023-00332-7 “Statistical methods for design and testing of 3D-printed polymers” Matéria (Rio de Janeiro) APPADURAI A.S. 29 4 e20240404 2024 10.1590/1517-7076-rmat-2024-0404 “Mechanical characterization and durability studies on concrete developed with M-Sand and River Sand” Matéria (Rio de Janeiro) SAKTHIVEL S. 29 4 e20240422 2024 10.1590/1517-7076-rmat-2024-0422 “Optimizing concrete strength with tapioca peel ash: a central composite design approach” Scientific Reports AGOR C.D. 13 1 2814 2023 10.1038/s41598-023-30008-0 “Evaluation of sisal fiber and aluminum waste concrete blend for sustainable construction using adaptive neuro-fuzzy inference system”