Estimation of California Bearing Ratio by Artificial Neural Network

Main Article Content

Narongdej Intaratchaiyakit


Laboratory CBR test is laborious, time-consuming, and expensive, resulting in the development of predictive models by employing multiple linear regression analysis (MLRA) and an artificial neural network (ANN). In this study, a low coefficient of determination in the testing set was deserved from the MLRA in which the gravel, sand, plastic index, and optimum moisture content were used as independent variables. However, the suitably developed ANN model was Model 5 in which fine content, plastic index, optimum moisture content and maximum dry density were used as independent variables. The Model 5 had the relatively high coefficient of determination in the testing set. The predicted CBR values using the ANN are compared with the CBR predicted by MLRA. The results demonstrate that ANN is a beneficial way of predicting CBR values, as it outperforms the MLRA. Moreover, a new ANN based formula is proposed for predicting CBR values. The new ANN based formula is beneficial to a preliminary design in earthwork for budget restrictions and limited time.  

Article Details

How to Cite
Intaratchaiyakit, N. (2023). Estimation of California Bearing Ratio by Artificial Neural Network. Rajamangala University of Technology Tawan-Ok Research Journal, 2566(1), 1–10. Retrieved from
Research article
Author Biography

Narongdej Intaratchaiyakit, Rajamangala University of Technology Tawan-ok

Faculty of Engineering and Architecture Department of Civil Engineering


Agarwal, K.B. and Ghanekar, K.D. 1970. Prediction of CBR from plasticity characteristics of soil. In: Proceeding of 2nd south-east Asian conference on soil engineering, Singapore. June 11–15. 1970. Bangkok: Asian Institute of Technology. 571–576.

Basma, A. A. and Kallas, N. 2004. Modeling soil collapse by artificial neural networks. Geotech. 22: 427–438.

Bhatt, S., Jain, P. K., and Pradesh, M. 2014. Prediction of California bearing ratio of soils using artificial neural network. AIJRSTEM. 8(2): 156–161.

Cybenko, G. 1989. Approximation by superpositions of a sigmoidal function. MCSS. 3: 303-314.

Das, S. K. and Basudhar, P. 2008. Prediction of residual friction angle of clay artificial neural network. Eng Geol. 142–145.

Erzin, Y., Rao, B. H., Patel, A., Gumaste, S.D., and Singh, D.N. 2008. Artificial neural networks for predicting soil thermal resistivity. Int J Therm Sci, 47: 1347–1358.

Erzin, Y. and Gunes, N. 2011.The prediction of swell percent and swell pressure by using neural networks. Comput. 16(2): 425–436.

Erzin, Y. and Turkoz, D. 2016, Use of neural networks for the prediction of the CBR value of some Aegean sands. Neural Comput. 27: 1415–1426.

Gunaydin, O., Gokoglu, A., and Fener, M. 2010. Prediction of artificial soil’s unconfined compression strength test using statistical analyses and artificial neural networks. Adv. Eng. Softw. 41: 1115–1123.

González Farias, I., Araujo, W., and Ruiz, G. 2018. Prediction of California Bearing Ratio from Index Properties of Soils Using Parametric and Non-parametric Models. Geotech. 36: 3485–3498.

Hecht-Nielsen, R. 1989. Theory of the back-propagation neural network. In: Proceedings of the International Joint Conference on Neural Networks, Washington. DC. 593–605.

Khandelwal, M. and Singh, TN. 2009. Prediction of blast-induced ground vibration using artificial neural network. International Journal of Rock Mechanics and Mining Sciences. 46(7): 1214–1222.

National Cooperative Highway Research Program. 2001. Guide for mechanistic and empirical – design for new and rehabilitated pavement structures. final document. In: Appendix CC-1: correlation of CBR values with soil ındex properties. West University Avenue Champaign, Illinois: Ara, Inc.

Pala, M. 2006. A new formulation for distortional buckling stress in cold-formed steel members. J Constr Steel Res. 62: 716-722.

Ramasubbarao, G. V. and Sankar, G. S. 2013. Predicting Soaked CBR Value of Fine Grained Soils Using Index and Compaction Characteristics. Jordan J. Civ. Eng. 7(3): 354–360.

Rakaraddi, P. G. and Gomarsi, V. 2015. Establishing relationship between CBR with different soil properties. Int. Res. J. Eng. Technol. 4(2): 182–188.

Rehman, A.U., Farooq, K., Mujtaba, H., and Altaf, O. 2015. Estimation of California bearing ratio (CBR) from index properties and compaction characteristics of coarse grained soil. Sci. Int. Lahore 27(6): 6207–6210.

Rehman, A.U., Farooq, K., and Mujtaba, H. 2017. Prediction of California bearing ratio (CBR) and compaction characteristics of granular soils. Acta Geotech. Slov. 14(1): 62–72.

Shahin, M.A. and Jaksa, M. 2002. Artificial neural network-based settlement prediction formula for shallow foundations on granular soils. Australian Geomechanics, 45–52.

Shahin, M.A. 2015. A review of artificial intelligence applications in shallow foundations. Int. J. Geotech. 9: 49-60.

Taskiran, T. 2010. Prediction of California bearing ratio (CBR) of fine grained soils by AI methods. Adv. Eng. Softw. 41(6): 886–892.

Taha, S., Gabr, A. and El-Badawy, S. 2019. Regression and Neural Network Models for California Bearing Ratio Prediction of Typical Granular Materials in Egypt. Arab J Sci Eng. 44: 8691–8705.

Wai, K. M. 2006. California bearing ratio correlation with soil index properties master of engineering (civil–geotechnics). Faculty of Civil Engineering, University Teknology Malaysia.

Yildirim, B. and Gunaydin, O. 2011. Estimation of California bearing ratio by using soft computing systems. Expert Syst. Appl. 38(5): 6381– 6391.