Investigation of the Effect of Copula Model on Improving the Accuracy of Neural Networks in Predicting the Compressive Strength of Concrete Used in Concrete Pavements

Articles in Press

Document Type : Research Paper

Authors

1 Master of Science, Department of Civil Engineering, Faculty of Engineering, Ferdowsi University of Mashhad, Iran

2 Department of Civil Engineering, Engineering Faculty,Ferdowsi University of Mashhad, Mashhad, Iran And School of Civil Engineering, College of Engineering, University of Tehran, Tehran, Iran

Abstract

In recent years, the use of machine learning methods for predicting the mechanical properties of concrete has received significant attention. Among these, accurate prediction of concrete compressive strength is considered one of the most important design parameters in concrete pavements. However, the limitation of experimental data is one of the main challenges in developing accurate machine learning models. In this study, a hybrid approach based on the Gaussian copula model and artificial neural networks (Copula-ANN) is proposed to augment the training data and improve the accuracy of compressive strength prediction of concrete. The dataset used in this research was extracted from the standard Yeh dataset and includes concrete mix design variables and compressive strength. The performance of the proposed model was compared with a conventional neural network and linear regression. The results showed that the use of the copula method significantly improved the performance of the neural network, increasing the coefficient of determination (R²) from 0.914 to 0.976. To evaluate the generalization capability of the model, external validation was performed using experimental data of high-strength concrete reported in reliable studies. The results of this validation indicated a good agreement between the predicted values and the experimental data, confirming the accuracy and reliability of the proposed model .Finally, the results demonstrate the ability of the proposed model to improve the accuracy of concrete compressive strength prediction and enhance the generalization capability of machine learning models in concrete engineering problems.

Keywords

Main Subjects

Journal of Transportation Infrastructure Engineering

Articles in Press, Accepted Manuscript
Available Online from 07 June 2026

Files

History

  • Receive Date: 10 May 2026
  • Revise Date: 02 June 2026
  • Accept Date: 07 June 2026

Share

How to cite

Statistics