Machine learning techniques applied to prediction of residual strength of clay

Abstract

Stability with first time or reactivated landslides depends upon the residual shear strength of soil. This paper describes prediction of the residual strength of soil based on index properties using two machine learning techniques. Different Artificial Neural Network (ANN) models and Support Vector Machine (SVM) techniques have been used. SVM aims at minimizing a bound on the generalization error of a model rather than at minimizing the error on the training data only. The ANN models along with their generalizations capabilities are presented here for comparisons. This study also highlights the capability of SVM model over ANN models for the prediction of the residual strength of soil. Based on different statistical parameters, the SVM model is found to be better than the developed ANN models. A model equation has been developed for prediction of the residual strength based on the SVM for practicing geotechnical engineers. Sensitivity analyses have been also performed to investigate the effects of different index properties on the residual strength of soil.

If the inline PDF is not rendering correctly, you can download the PDF file here.

  • [1] Skempton A.W., The long term stability of clay slopes. Geotechnique, 1964, 14, 77–101 http://dx.doi.org/10.1680/geot.1964.14.2.77

  • [2] Mesri G., Shahien M., Residual Shear Strength Mobilized in First-Time Slope Failures. J. Geotech. Geoenviron. Eng., 2003, 129, 12–31 http://dx.doi.org/10.1061/(ASCE)1090-0241(2003)129:1(12)

  • [3] Bowles J.E., Foundation analysis and design. McGraw-Hill International Edition, Singapore, 1988

  • [4] Mesri G., Cepeda-Diaz A.F., Residual strength of clays and shales. Geotechnique, 1986, 36, 269–274 http://dx.doi.org/10.1680/geot.1986.36.2.269

  • [5] Colotta T., Cantoni R., Pavesi U., Robert E., Moretti P.C., A correlation between residual friction angle, gradation and index properties of cohesive soil. Geotechnique, 1989, 39, 343–346 http://dx.doi.org/10.1680/geot.1989.39.2.343

  • [6] Stark T.D., Eid H.T., Drained residual strength of cohesive soils. J. Geotech. Geoenviron. Eng., 1994, 120, 856–871

  • [7] Wesley L.D., Residual strength of clays and correlations using Atterberg limit. Geotechnique, 2003, 53, 669–672 http://dx.doi.org/10.1680/geot.2003.53.7.669

  • [8] Sridharan A., Rao P.R., Discussion: Residual strength of clays and correlation using Atterberg limits. Geotechnique, 2004, 54, 503–504 http://dx.doi.org/10.1680/geot.2004.54.7.503

  • [9] Tiwari B., Marui H., A new method for the correlation of residual shear strength of the soil with mineralogical composition. J. Geotech. Geoenviron. Eng., 2005, 131, 1139–1150 http://dx.doi.org/10.1061/(ASCE)1090-0241(2005)131:9(1139)

  • [10] Kaya A., Kwong J.K.P., Evaluation of common practice empirical procedures for residual friction angle of soils: Hawaiian amorphous material rich colluvial soil case study. Eng. Geol., 2007, 92, 49–58 http://dx.doi.org/10.1016/j.enggeo.2007.03.002

  • [11] Das S.K., Basudhar P.K., Prediction of residual friction angle of clays using artificial neural network. Eng. Geol., 2008, 100, 142–145 http://dx.doi.org/10.1016/j.enggeo.2008.03.001

  • [12] Demuth H., Beale M., Neural Network Toolbox. The Math Works Inc., USA, 2000.

  • [13] MathWork Inc., Matlab User’s Manual. Version 6.5. Natick MA, 2001

  • [14] Ilonen J., Kamarainen J.K., Lampinen J., Differential Evolution training algorithm for feed-forward neural network. Neural Processing Letters, 2003, 17, 93–105 http://dx.doi.org/10.1023/A:1022995128597

  • [15] Juang C.H., Elton D.J., Prediction of collapse potential of soil with neural networks. Trans. Res. Record, 1997, 1582, 22–28 http://dx.doi.org/10.3141/1582-04

  • [16] Das S.K., Basudhar P.K., Undrained lateral load capacity of piles in clay using artificial neural network. Comput. and Geotech., 2006, 33, 454–459 http://dx.doi.org/10.1016/j.compgeo.2006.08.006

  • [17] Boser B.E., Guyon I.M., Vapnik V.N., A training algorithm for optimal margin classifiers. In: Haussler D (Ed.) 5th Annual ACM workshop on COLT. ACM, Pittsburgh, 1992, 144–152

  • [18] Cristianini N., Shawe-Taylor J., An introduction to support vector machine. University Press, London, Cambridge, 2000

  • [19] Cortes C., Vapnik V.N., Support vector networks. Mach. Learn., 1995, 20, 273–297

  • [20] Gualtieri J.A., Chettri S.R., Cromp R.F., Johnson L.F., Support vector machine classifiers as applied to AVIRIS data. In: The summaries of the 8th JPL airborne earth science workshop, 1999

  • [21] Vapnik V.N., Statistical learning theory. Wiley, New York, 1998

  • [22] Bennett K.P., Mangasarian O.L., Robust linear programming discrimination of two linearly inseparable sets. Optimization Methods and Software, 1992, 1, 23–34 http://dx.doi.org/10.1080/10556789208805504

  • [23] Smola A.J., Scholkopf B., A tutorial on support vector regression. Stat. Comput., 2004, 14, 199–222 http://dx.doi.org/10.1023/B:STCO.0000035301.49549.88

  • [24] Das S.K., Samui P., Sabat A.K., Sitharam T.G., Prediction of swelling pressure of soil using artificial intelligence techniques. Environmental Earth Science, 2010, 61, 393–403 http://dx.doi.org/10.1007/s12665-009-0352-6

  • [25] Olden J.D., Joy M.K., Death R.G., An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data. Eco. Model, 2004, 178, 389–397 http://dx.doi.org/10.1016/j.ecolmodel.2004.03.013

OPEN ACCESS

Journal + Issues

Open Geosciences (formerly Central European Journal of Geosciences - CEJG) is an international, peer-reviewed journal publishing original research results from all fields of Earth Sciences such as: Geology, Geophysics, Geography, Geomicrobiology, Geotourism, Oceanography and Hydrology, Glaciology, Atmospheric Sciences, Speleology, Volcanology, Soil Science, Geoinformatics, Geostatistics. The journal is published in the Open Access model.

Search