A study of slope stability prediction using neural networks

  • M. G. Sakellariou
  • M. D. Ferentinou


The determination of the non-linear behaviour of multivariate dynamic systems often presents a challenging and demanding problem. Slope stability estimation is an engineering problem that involves several parameters. The impact of these parameters on the stability of slopes is investigated through the use of computational tools called neural networks. A number of networks of threshold logic unit were tested, with adjustable weights. The computational method for the training process was a back-propagation learning algorithm. In this paper, the input data for slope stability estimation consist of values of geotechnical and geometrical input parameters. As an output, the network estimates the factor of safety (FS) that can be modelled as a function approximation problem, or the stability status (S) that can be modelled either as a function approximation problem or as a classification model. The performance of the network is measured and the results are compared to those obtained by means of standard analytical methods. Furthermore, the relative importance of the parameters is studied using the method of the partitioning of weights and compared to the results obtained through the use of Index Information Theory.


artificial neural networks back-propagation factor of safety geotechnical parameters slope stability threshold logic units 


  1. Bishop, A.W. 1955The use of slip circle in the stability analysis of earth slopesGeotechnique.5717Google Scholar
  2. Chang, H.-C, Kopaska-Merkel, D.C., Chen, H.C. 2002Identification of lithofacies using Kohonen self-organising mapsComput. Geosci.28223229CrossRefGoogle Scholar
  3. Cilliers P. (1999). Complexity, Postmodernism, Routledge. Taylor & Francis GroupGoogle Scholar
  4. Deng, J.H., Lee, C.F. 2001Displacement back analysis for a steep slope at the Three Gorges Project SiteInt. J. Rock Mech. Min. Sci.38259268CrossRefGoogle Scholar
  5. Duncan M. Soil slope stability analysis, Landslides Investigation and Mitigation, Transportation Research Board Special Report 247, Washington Press, 1996, pp. 337-371Google Scholar
  6. Ferentinou, M.: Investigation of Landslide Hazard estimation with Computational Neural Networks in a Geographical Information System Environment, PhD Thesis, in press.Google Scholar
  7. Ferentinou, M., Sakellariou, M.: Slope stability estimation using GIS, In: Rosenbaum and Turner (eds.), Characterisation of the Shallow Subsurface: Implications for Urban Infrastructureand Environmental Assessment, Springer-Verlag, Duesseldorf, 2003, pp. 135-140.Google Scholar
  8. Gangopadhyay, S., Gautam, T.R., Das Gupta, A. 1999Subsurface characterisation using artificial neural network and GISJ. Comp. Civil Eng.13153161CrossRefGoogle Scholar
  9. Garson G.D. (1991). Interpreting neural-networks connection weights AI. Expert. 6: 47-51Google Scholar
  10. Goh, A.T.C. 1995aBack-Propagation neural networks for modelling complex systemsArtificial Intelligence Eng.9143151CrossRefGoogle Scholar
  11. Goh, A.T.C. 1995bSeismic liquefaction potential Assessed by neural networksJ. Geotech. Eng.12014671480Google Scholar
  12. Hoek, E., Bray, J.W. 1981Rock Slope Engineering3Institution of Mining and MetallurgyLondonGoogle Scholar
  13. Hudson, J.A. 1992aAtlas of rock engineering mechanisms Part 2Slopes. Int. J. Rock Mech. Mining Sci.29157159CrossRefGoogle Scholar
  14. Hudson, J.A. 1992bRock Engineering systems - Theory and PracticeEllis Horwood LimitedWestSussexGoogle Scholar
  15. Hush Don R., Horne B.G. (1999). What’s new since Lippman?. IEEE Signal Process. Magazine. 9-39Google Scholar
  16. Janbu, N.: Application of composite slip circles for stability analysis, In: Proc. fourth European Conference on stability of earth slopes, Vol. 3, 1954, pp. 43-49.Google Scholar
  17. Jing, L. 2003A review of techniques, advances and outstanding issues in numerical modelling for rock mechanics and rock engineeringInt. J. Rock Mech. Mining Sci.40283353CrossRefGoogle Scholar
  18. Jing, L., Hudson, J.A. 2002Numerical methods in rock mechanicsInt. J. Rock Mech. Mining Sci.39409427CrossRefGoogle Scholar
  19. Lin, P.S., Lin M.H., Su M.B., Lee T.M.: An investigation on the failure of a building constructed on hillslope, In: Bonnard (ed.) Landslides, Balkema, Vol. 1, 1988, pp. 445-449Google Scholar
  20. Madzic, E.: Stability of unstable final slope in deep open iron mine, In: Bonnard (ed.) Landslides, Balkema, Vol. 1, 1988, pp. 455-458Google Scholar
  21. Millar, D.L, Hudson, J.A. 1994Performance monitoring of rock engineering systems utilizing neural networksTrans. Inst. Mining Metall. Section A - Mining Ind.103A13A16Google Scholar
  22. Najjar, Y.M., Basheer, I.A. 1996Utilising computational neural networks for evaluating the permeability of compacted clay linersGeotech. Geol. Eng.14193212Google Scholar
  23. Neural Network Toolbox User’s Guide, The Math Works Inc.Nilson, N.J.: Artificial Intelligence a New Synthesis, Morgan Kaufmann Publishers Inc., SanFrancisco, CA, 1998Google Scholar
  24. Rosenblatt, F. 1958The perceptron: A probabilistic model for information storage and organization in the brainPsychol. Rev.65386408PubMedGoogle Scholar
  25. Roussos E. (2000). Neural Networks for Landslide Hazard Estimation. Master Thesis, Kings CollegeGoogle Scholar
  26. Sah, N.K., Sheorey, P.R., Upadhyama, L.W. 1994Maximum likelihood estimation of slope stabilityInt. J. Rock Mech. Min. Sci. Geomech. Abstr.314753CrossRefGoogle Scholar
  27. Sakellariou, M.G., Ferentinou, M.D. 2001GIS-based estimation of slope stabilityNat. Hazard Rev.21221CrossRefGoogle Scholar
  28. Sakellariou, M.G., Ilias P.: Application of neural networks in the estimation of slope stability, In: Proc. Third Hellenic Geotechnical Conference, (in Greek), Vol 2, 1997, pp.269-276.Google Scholar
  29. Sarma, S.K. 1975Seismic stability of earth dams and embankmentsGeotechnique.25743761Google Scholar
  30. Sklavounos, P., Sakellariou, M.: Intelligent classification of rock masses, In: Adey, Rzevski and Tasso (eds.), Applications of Artificial Intelligence in Engineering, X, Proc. of the Tenth International Conference on Applications of artificial Intelligence in Engineering,Udine, July 1995, Computational Mechanics Publications, pp. 387-393.Google Scholar
  31. Spencer, E. 1967A method of analysis of the stability of embankments assuming parallel inter-slice forcesGeotechnique.171126Google Scholar
  32. Stump, D.E., Vallejo L.E., Bazan-Arias N.C.: Analysis of the creeping behavior of a natural slope in Kentucky, In: Keefer and Ho (eds.), Landslides under static and dynamic conditions - Analysis, monitoring and mitigation, ASCE Geotechnical Special Report No.52, 1995, pp. 21-36.Google Scholar
  33. Stegem, J.A., Buenfild, A. 1999Glossary of basic neural network terminology for regression problemsNeural Comp. Appl.8290296CrossRefGoogle Scholar
  34. Taylor, D.W. 1937Stability of earth slopesJ. Boston Soc. Civil Eng.24197Google Scholar
  35. Toll, D.: Artificial Intelligence Systems for geotechnical engineering with specific reference to the ground improvement, In: Proc. Tenth European Young Geotechnical Engineers Conference, Izmir, Turkey, 1996.Google Scholar
  36. Yang, Y., Rosenbaum, M.S. 2001The artificial neural network as a tool for assessing geotechnical propertiesGeotech. Geol. Eng.20149168CrossRefGoogle Scholar

Copyright information

© Springer 2005

Authors and Affiliations

  • M. G. Sakellariou
    • 1
  • M. D. Ferentinou
    • 2
  1. 1.Dr. Civil Engineering, Associate Professor, Laboratory of Structural MechanicsNational Technical University of Athens (NTUA)AthensGreece
  2. 2.Geologist, Graduate StudentNTUAGreece

Personalised recommendations