Estimation of the most important geomechanical parameter of unsaturated soils using different artificial intelligence methods

مهندسی عمران فردوسی

Article 3, Volume 35, Issue 2 - Serial Number 38, September 2022, Pages 35-48   

Document Type: Original Article

DOI: 10.22067/jfcei.2022.74090.1100

Authors

Hadi Fattahi^{* 1}; Fatemeh Jiryaee²

¹Faculty of Earth Sciences Engineering, Arak University of Technology, Arak

²Faculty of Earth Sciences Engineering, Arak University of Technology, Iran

Abstract

In predicting the behavior of geotechnical structures that are constructed on unsaturated soils, knowing the geomechanical properties, especially effective stress, is of particular importance. The effect of suction in unsaturated soils changes the volumetric and shear behavior of soil. Therefore, in determining the shear strength in unsaturated soils, the effective stress parameter (χ) plays an essential role as a function of suction. Determining this parameter requires a lot of time and money that is spent on laboratory tests. The purpose of this study is to evaluate several intelligent methods for creating models that indirectly accurately estimate parameter (χ). For this purpose, 120 data (which are the results of thriaxial, shear, pressure plate and filter paper tests) and intelligent methods of random forest, support vector machine and k-nearest neighbor were used in WEKA intelligent software. The results show that the models developed by the three intelligent methods of random forest, support vector machine and k-nearest neighbor, have excellent performance and accuracy. But the random forest model is better than the other two models in evaluating the test data with R2 = 0.918 and RMSE = 0.079. In addition, in this study, sensitivity analysis was performed to determine the importance of the parameters affecting parameter (χ). Among the input parameters in modeling, it was found that the volume water content parameter (θ_r/θ_s ) has the greatest effect on parameter (χ).

Keywords

Effective Stress; Random Forest; Support Vector Machine; K-Nearest Neighbor; WEKA Software

References

 Fredlund, D.G., "Unsaturated soil mechanics in engineering practice". Journal of geotechnical geoenvironmental engineering, Vol. 132, No. 3, pp. 286-321, (2006).

2. Aitchison, G.D., Russam, K., and Richards, B., "Engineering concepts of moisture equilibria and moisture changes in soils". Ministry of Transport, Vol., (1966).
3. Sheng, D., "Constitutive modelling of unsaturated soils: Discussion of fundamental principles". Unsaturated soils, Vol. 1, No. pp. 91-112, (2011).
4. Lee, S., Lee, S.R., and Kim, Y., "An approach to estimate unsaturated shear strength using artificial neural network and hyperbolic formulation". Computers Geotechnics, Vol. 30, No. 6, pp. 489-503, (2003).
5. Kayadelen, C., "Estimation of effective stress parameter of unsaturated soils by using artificial neural networks". International journal for numerical analytical methods in geomechanics, Vol. 32, No. 9, pp. 1087-1106, (2008).
6. Ajdari, M., Habibagahi, G., and Ghahramani, A., "Predicting effective stress parameter of unsaturated soils using neural networks". Computers and Geotechnics, Vol. 40, No. pp. 89-96, (2012).
7. Johari, A., Habibagahi, G., and Nakhaee, M., "Prediction of unsaturated soils effective stress parameter using gene expression programming". Scientia Iranica, Vol. 20, No. 5, pp. 1433-1444, (2013).
8. Kanungo, D., Sharma, S., and Pain, A., "Artificial Neural Network (ANN) and Regression Tree (CART) applications for the indirect estimation of unsaturated soil shear strength parameters". Frontiers of earth science, Vol. 8, No. 3, pp. 439-456, (2014).
9. Rahnema, H., Hashemi Jokar, M., and Khabbaz, H., "Predicting the effective stress parameter of unsaturated soils using adaptive neuro-fuzzy inference system". Scientia Iranica, Vol. 26, No. 6, pp. 3140-3158, (2019).
10. Tien Bui, D., Hoang, N.-D., and Nhu, V.-H., "A swarm intelligence-based machine learning approach for predicting soil shear strength for road construction: a case study at Trung Luong National Expressway Project (Vietnam)". Engineering with Computers, Vol. 35, No. 3, pp. 955-965, (2019).
11. Khalili, N. and Khabbaz, M., "A unique relationship for χ for the determination of the shear strength of unsaturated soils". Geotechnique, Vol. 48, No. 5, pp. 681-687, (1998).
12. Cui, Y.J., et al., "Unsaturated soil mechanics". International Society of Soil Mechanics and Geotechnical Engineering, Vol., (2004).
13. Bishop, A.W., "The principle of effective stress". Teknisk ukeblad, Vol. 39, No. pp. 859-863, (1959).
14. Vanapalli, S., et al., "Model for the prediction of shear strength with respect to soil suction". Canadian geotechnical journal, Vol. 33, No. 3, pp. 379-392, (1996).
15. vladimir, et al., "A classification and regression tool for compound classification and qsar modeling svetnik". Journal of Chemical Information Computer Sciences, Vol. 43, No. 6, pp. 1947-1958, (2003).
16. Cortes, C. and Vapnik, V., "Support vector machine". Machine learning, Vol. 20, No. 3, pp. 273-297, (1995).
17. Zhang, D., et al., "Parameter optimization for support vector regression based on genetic algorithm with simplex crossover operator". Journal of Information Computational Science, Vol. 8, No. 6, pp. 911-920, (2011).
18. Shahrabi, J. and Hejazi, T., Data mining 2, Tehran, Industrial university of amirkabir. 2013, Jahad daneshgahi Press.(In Persian).
19. Azmi, M. and Araghinejad, S., "Development of K-Nearest Neighbour Regression Method in Forecasting River Stream Flow". Journal of Water and Wastewater, Vol. 23, No. 2, pp. 108-119, (2012).
20. Witten, I.H., et al. Practical machine learning tools and techniques. in DATA MINING. 2005.
21. Thu, T.M., Rahardjo, H., and Leong, E.-C., Effects of hysteresis on shear strength envelopes from constant water content and consolidated drained triaxial tests, in Unsaturated soils 2006. p. 1212-1222.
22. Russell, A.R. and Khalili, N., "A bounding surface plasticity model for sands exhibiting particle crushing". Canadian Geotechnical Journal, Vol. 41, No. 6, pp. 1179-1192, (2004).
23. Russell, A. and Khalili, N., "A unified bounding surface plasticity model for unsaturated soils". International Journal for Numerical Analytical Methods in Geomechanics, Vol. 30, No. 3, pp. 181-212, (2006).