Determination of effective stress parameter of unsaturated soils: A Gaussian process regression approach

doi:10.1007/s11709-013-0202-1

Front Struc Civil Eng

2013, Vol. 7

Issue (2) : 133-136 https://doi.org/10.1007/s11709-013-0202-1

RESEARCH ARTICLE

Determination of effective stress parameter of unsaturated soils: A Gaussian process regression approach

Pijush Samui(

), Jagan J

Centre for Disaster Mitigation and Management, VIT University, Vellore-632014, India

Download: PDF(146 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

This article examines the capability of Gaussian process regression (GPR) for prediction of effective stress parameter (χ) of unsaturated soil. GPR method proceeds by parameterising a covariance function, and then infers the parameters given the data set. Input variables of GPR are net confining pressure (σ₃), saturated volumetric water content (θ_s), residual water content (θ_r), bubbling pressure (h_b), suction (s) and fitting parameter (λ). A comparative study has been carried out between the developed GPR and Artificial Neural Network (ANN) models. A sensitivity analysis has been done to determine the effect of each input parameter on χ. The developed GPR gives the variance of predicted χ. The results show that the developed GPR is reliable model for prediction of χ of unsaturated soil.

Keywords unsaturated soil effective stress parameter Gaussian process regression (GPR) artificial neural network (ANN) variance

Corresponding Author(s): Samui Pijush,Email:pijush.phd@gmail.com

Issue Date: 05 June 2013

Cite this article:

Pijush Samui,Jagan J. Determination of effective stress parameter of unsaturated soils: A Gaussian process regression approach[J]. Front Struc Civil Eng, 2013, 7(2): 133-136.

URL:

https://academic.hep.com.cn/fsce/EN/10.1007/s11709-013-0202-1
https://academic.hep.com.cn/fsce/EN/Y2013/V7/I2/133

Fig.1 Performance of training data set

Fig.2 Performance of testing data set

Fig.3 Comparisons between ANN and GPR

Fig.4 Sensitivity analysis of the input parameters

Fig.5 Variance of training data set

Fig.6 Variance of testing data set

1	Bishop A W. The principle of effective stress. Teknisk Ukeblad , 1959, 106(39): 859–863
2	Khalili N, Khabbaz M H. A unique relationship for the determination of the shear strength of unsaturated soils. Geotechnique , 1998, 48(5): 681-687 doi: 10.1680/geot.1998.48.5.681
3	Russell A R, Khalili N A. Unified bounding surface plasticity for unsaturated soils. International Journal for Numerical and Analytical Methods in Geomechanics , 2006, 30(3): 181–212 doi: 10.1002/nag.475
4	Garven E N, Vanapalli S K. Evaluation of empirical procedures for predicting the shear strength of unsaturated soils. In: Proceedings of the Unsaturated Soils . ASCE, Sharma and Singhal, 2006, 2570–81
5	Fazeli A, Habibagahi G. Ghahramani A V. Shear strength characteristics of Shiraz unsaturated silty clay. Iranian Journal of Science Technology , 2010, 33(B4): 327–341
6	Ajdari M, Habibagahi G, Ghahramani A. Predicting effective stress parameter of unsaturated soils using neural networks. Computers and Geotechnics , 2012, 40: 89–96 doi: 10.1016/j.compgeo.2011.09.004
7	Park D, Rilett L R. Forecasting freeway link ravel times with a multi-layer feed forward neural network. Computer-Aided Civil and Infrastructure Engineering , 1999, 14: 357–367
8	Kecman V. Learning and Soft Computing: Support Vector Machines, Neural Networks, and Fuzzy Logic Models. Cambridge, MA: MIT Press, 2001
9	A?man K, Kocijan J. Application of Gaussian processes for black-box modelling of biosystems. ISA Transactions , 2007, 46(4): 443–457 doi: 10.1016/j.isatra.2007.04.001
10	Stegle O, Fallert S V, MacKay D J, Brage S. Gaussian process robust regression for noisy heart rate data. IEEE Transactions on Bio-Medical Engineering , 2008, 55(9): 2143–2151 doi: 10.1109/TBME.2008.923118
11	di Sciascio F, Amicarelli A N. Biomass estimation in batch bio-technological processes by Bayesian Gaussian process regression. Computers & Chemical Engineering , 2008, 32(12): 3264–3273 doi: 10.1016/j.compchemeng.2008.05.015
12	Yuan J, Wang K, Yu T, Fang M. Reliable multi-objective optimization of highspeed WEDM process based on Gaussian process regression. International Journal of Machine Tools & Manufacture , 2008, 48(1): 47–60 doi: 10.1016/j.ijmachtools.2007.07.011
13	Pal M, Deswal S. Modelling pile capacity using Gaussian process regression. Computers and Geotechnics , 2010, 37(7-8): 942–947 doi: 10.1016/j.compgeo.2010.07.012
14	Williams K I, Rasmussen C E. Gaussian Processes for Regression, Cambridge, MA: MIT Press, 1996
15	Liong S Y, Lim W H, Paudyal G N. River stage forecasting in Bangladesh: Neural network approach. Journal of Computing in Civil Engineering , 2000, 14(1): 1–8 doi: 10.1061/(ASCE)0887-3801(2000)14:1(1)

[1]	Nabarun DEY, Aniruddha SENGUPTA. Effect of a less permeable stronger soil layer on the stability of non-homogeneous unsaturated slopes[J]. Front. Struct. Civ. Eng., 2020, 14(6): 1462-1475.
[2]	M. Houshmand KHANEGHAHI, M. ALEMBAGHERI, N. SOLTANI. Reliability and variance-based sensitivity analysis of arch dams during construction and reservoir impoundment[J]. Front. Struct. Civ. Eng., 2019, 13(3): 526-541.
[3]	Yasser SHARIFI,Sajjad TOHIDI. Lateral-torsional buckling capacity assessment of web opening steel girders by artificial neural networks – elastic investigation[J]. Front. Struct. Civ. Eng., 2014, 8(2): 167-177.
[4]	Michael PERTL, Matthias HOFMANN, Guenter HOFSTETTER. Coupled solid-fluid FE-analysis of an embankment dam[J]. Front Arch Civil Eng Chin, 2011, 5(1): 53-62.
[5]	Eduardo E. ALONSO, Rafaela CARDOSO, . Behavior of materials for earth and rockfill dams: Perspective from unsaturated soil mechanics[J]. Front. Struct. Civ. Eng., 2010, 4(1): 1-39.
[6]	XU Yongfu, TONG Lixin. Application of fractal theory to unsaturated soil mechanics[J]. Front. Struct. Civ. Eng., 2007, 1(4): 411-421.

Viewed

Full text

Abstract

Cited

Shared

Discussed