A new approach to predict the compression index using artificial intelligence methods

Abstract

The compression index is one of the important geotechnical parameters, essential for the structural design. Since the determination of the compression index based on oedometer tests is relatively expensive and time-consuming, different authors have proposed for its estimation models using regression analysis and artificial neuron networks. However, they have ignored several parameters that could have increased the predictive capability of models. Other studies have concluded that genetic programming could have yielded better results. Unfortunately, no compression index models or effective comparisons of different methods have been published. The aim of this study is to propose a novel approach for estimating the compression index more accurately. To test the approach, a comparison study using K-fold cross-validation technique was conducted utilizing several models of multilayer neural networks, genetic programming, and multiple regression analysis. These models have been applied to 373 oedometer test samples to predict the compression index from soil physical parameters. The results indicate that the neural network with two hidden layers (7-14-4-1) provides the most appropriate prediction, compared with other models and the formulae suggested by previous studies. Based on these findings, this study‏ proposed a MATLAB script for efficiently estimating the compression index in the future studies.

Keywords:

• Compression index
• laboratory tests
• numerical modeling
• neural network
• genetic programming
• empirical formulae

Acknowledgements

The authors expand their considerable thanks to the National Earthquake Engineering Research Centre (CGS) of Algiers, Algiers Metro, Algiers Tramway, Cosider Engineering, Cosider Construction, and SAPTA for giving the boreholes data used as a part of this study. Also, the authors wish to express their deep gratitude to Microzoning Team of National Earthquake Engineering Research Centre and Pr. Abderrahim BALI for their helpful comments. Finally, we would like to thank the editor and the referees for their valuable comments which helped to improve quality of the paper.

Additional information

Funding

We express our deepest gratitude and appreciation to Francophone University Association for funding the scientific training in ‘Ion Mincu’ University of Architecture and Urban Planning Bucharest, Romania (Reference No: CE\DG\28\2017).