Geotechnical and Geological Engineering

, Volume 35, Issue 1, pp 445–461 | Cite as

Prediction of Laboratory Peak Shear Stress Along the Cohesive Soil–Geosynthetic Interface Using Artificial Neural Network

  • Prasenjit Debnath
  • Ashim Kanti Dey
Original paper


In general, soil–geosynthetic interface behaviour is modeled by interface element which involves the assumption of stiffness values which are difficult to determine experimentally. Most of the geosynthetic-reinforced earth structures fail at the interface of the geosynthetic and the soil due to slip or plastic yielding of the reinforced soil. Hence, for a proper design of the soil–geosynthetic interface, an artificial neural network (ANN) model can be used as an alternative approach for the prediction of the soil–geosynthetic interface behavior. The present study uses an ANN model to predict the peak shear stress along the cohesive soil–geosynthetic interface. Three-layer feed-forward back-propagation neural networks with 4, 10 and 15 hidden nodes using three different learning algorithms are examined. Out of three learning algorithms, Bayesian regularization learning algorithm with four hidden nodes is used for its highest coefficient of determination (R 2 = 0.988) for the testing set and all of the predicted data falling within the 99% prediction interval. The prediction performance of the ANN model with Bayesian regularization learning algorithm with four hidden nodes is compared with the multi-variable regression analysis. Different sensitivity analyses to quantify the most importance input parameters are also discussed. A neural interpretation diagram to visualize the effect of input parameters on the output is presented. Finally, a predicted model equation is obtained based on the neural network parameters.


Artificial neural network Peak shear stress Sensitivity analysis Multi-variable regression Statistical analysis 


  1. Abdel-Baki MS, Raymond GP (1994) Numerical analysis of geotextile reinforced soil slabs. In: Fifth international conference on geotextiles, geomembranes and related products, SingaporeGoogle Scholar
  2. Ajdari M, Habibagahi G, Ghahramani A (2012) Predicting effective stress parameter of unsaturated soils using neural networks. Comput Geotech 40:89–96. doi: 10.1016/j.compgeo.2011.09.004 CrossRefGoogle Scholar
  3. Andrawes KZ, Mcgown A, Wilson-Fahmy RF, Mashhour MM (1982) The finite element method of analysis applied to soil–geotextile systems. In: Second international conference of geotextiles, Las Vegas, USA, pp 695–700Google Scholar
  4. Basudhar PK, Dixit PM, Gharpure A, Deb K (2008) Finite element analysis of geotextile-reinforced sand-bed subjected to strip loading. Geotext Geomembr 26:91–99. doi: 10.1016/j.geotexmem.2007.04.002 CrossRefGoogle Scholar
  5. Box GEP, Tiao GC (1973) Bayesian inference in statistical analysis. Addison-Wesley, ReadingGoogle Scholar
  6. Burd HJ, Brocklehurst CJ (1990) Finite element studies of the mechanics of reinforced unpaved roads. In: Proceedings of the fourth international conference on geotextiles, geomembranes and related products, The Hauge, Netherlands, pp 217–221Google Scholar
  7. Caudill M (1989) Neural Networks Primer. San Francisco (CA), Miller Freeman PublicationsGoogle Scholar
  8. Caudill M, Butler C (1992) Understanding neural networks: computer explorations, vols 1 and 2. The MIT Press, CambridgeGoogle Scholar
  9. DARPA (1988) Neural network study. M.I.T., Lincoln, Laboratory, LexingtonGoogle Scholar
  10. Das SK, Basudhar PK (2006) Undrained lateral load capacity of piles in clay using artificial neural network. Comput Geotech 33(8):454–459. doi: 10.1016/j.compgeo.2006.08.006 CrossRefGoogle Scholar
  11. Das SK, Basudhar PK (2008) Prediction of residual friction angle of clays using artificial neural network. Eng Geol 100(3–4):142–145. doi: 10.1016/j.enggeo.2008.03.001 CrossRefGoogle Scholar
  12. Das SK, Samui P, Sabat AK (2011) Density and unconfined compressive strength of cement stabilized soil. Geotech Geol Eng 29:329–342. doi: 10.1007/s10706-010-9379-4 CrossRefGoogle Scholar
  13. Farrag K (1995) Effect of moisture content on the interaction properties of geosynthetics. In: Geosynthetics’95, pp 1031–1041Google Scholar
  14. Farrag K, Griffin P (1993) Pull-out testing in cohesive soils, geosynthetic soil reinforcement testing procedures. ASTM STP No. 1190, West Conshohocken, PA, pp 76–89Google Scholar
  15. Farrag K, Morvant M (2003a) Evaluation of interaction properties of geosynthetics in cohesive soils: LTRC reinforced-soil test wall, Rep. No. FHWA/LA 03/379. Louisiana Transportation Research Center, Baton Rouge, LAGoogle Scholar
  16. Farrag K, Morvant M (2003b) Evaluation of interaction properties of geosynthetics in cohesive soils: lab and field pullout tests, Rep. No. FHWA/LA 03/380. Louisiana Transportation Research Center, Baton Rouge, LAGoogle Scholar
  17. Farsakh MA, Coronel J, Tao M (2007) Effect of soil moisture content and dry density on cohesive soil–geosynthetic interactions using large direct shear tests. J Mater Civ Eng ASCE 19:540–549. doi: 10.1061/(ASCE)0899-1561(2007)19:7(540) CrossRefGoogle Scholar
  18. Fletcher R (2000) Practical methods of optimization. Wiley, New YorkCrossRefGoogle Scholar
  19. Garson GD (1991) Interpreting neural-network connection weights. Artif Intell Expert 6(7):47–51Google Scholar
  20. Gens A, Carol I, Alonso EE (1988) An interface element formulation for the analysis of soil–reinforcement interaction. Comput Geotech 7:133–151. doi: 10.1016/0266-352X(89)90011-6 CrossRefGoogle Scholar
  21. Goh ATC (1994) Seismic liquefaction potential assessed by using neural networks. J Geotech E 120(9):1467–1480. doi: 10.1061/(ASCE)0733-9410(1994)120:9(1467) CrossRefGoogle Scholar
  22. Goh ATC (1995) Empirical design in geotechnics using neural networks. Geotechnique 45(4):709–714CrossRefGoogle Scholar
  23. Goh ATC, Kulhawy FH, Chua CG (2005) Bayesian neural network analysis of undrained side resistance of drilled shafts. J Geotech Geoenviron Eng ASCE 131(1):84–93. doi: 10.1061/(ASCE)1090-0241(2005)131:1(84) CrossRefGoogle Scholar
  24. Gull SF (1988) Bayesian inductive inference and maximum entropy. In: Ericson GJ, Smith CR (eds) Maximum entropy and Bayesian methods in science and engineering, vol 1. Kluwer, Norwell, pp 53–74CrossRefGoogle Scholar
  25. Kanayama M, Rohe A, Paassen LA (2014) Using and improving neural network models for ground settlement prediction. Geotech Geol Eng 32:687–697. doi: 10.1007/s10706-014-9745-8 Google Scholar
  26. Khandelwal M, Singh TN (2010) Prediction of macerals contents of Indian coals from proximate and ultimate analyses using artificial neural networks. Fuel 89:1101–1109. doi: 10.1016/j.fuel.2009.11.028 CrossRefGoogle Scholar
  27. Lee IM, Lee JH (1996) Prediction of pile bearing capacity using artificial neural networks. Comput Geotech 18(3):189–200CrossRefGoogle Scholar
  28. Lippman RP (1987) An introduction to computing with neural nets. IEEE ASSP Mag 4:4–22. doi: 10.1109/MASSP.1987.1165576 CrossRefGoogle Scholar
  29. Lopes ML (2002) Soil–geosynthetic interaction. In: Shukla SK (ed) Geosynthetics and their applications. Thomas Telford, LondonGoogle Scholar
  30. Love JP, Burd HJ, Milligan GWE, Houlsby GT (1987) Analytical and model studies of reinforcement of a layer of granular fill on a soft clay subgrade. Can Geotech J 24:611–622CrossRefGoogle Scholar
  31. MacKay DJC (1991) Bayesian methods for adaptive models. Ph.D. Dissertation, California Institute of Technology, CaliforniaGoogle Scholar
  32. Maji VB, Sitharam TG (2008) Prediction of elastic modulus of jointed rock mass using artificial neural networks. Geotech Geol Eng 26:443–452. doi: 10.1007/s10706-008-9180-9 CrossRefGoogle Scholar
  33. Minsky M, Papert S (1969) An introduction to computational geometry. MIT Press, Cambridge. ISBN 0-262-63022-2Google Scholar
  34. Mitchell JK, Seed RB, Seed HB (1990) Kettleman Hills waste landfill slope failure, I: Liner-system properties. J Geotech Eng 116(4):647–668. doi: 10.1061/(ASCE)0733-9410(1990)116:4(647) CrossRefGoogle Scholar
  35. Moller MF (1993) A scaled conjugate gradient algorithm for fast supervised learning. Neural Netw 6:525–533. doi: 10.1016/S0893-6080(05)80056-5 CrossRefGoogle Scholar
  36. Monjezi M, Singh TN, Khandelwal M, Sinha S, Singh V, Hosseini I (2006) Prediction and analysis of blast parameters using artificial neural network. Noise Vib Control Worldw 37:8–16. doi: 10.1260/095745606777630323 CrossRefGoogle Scholar
  37. Monjezi M, Hasanipanah M, Khandelwal M (2013) Evaluation and prediction of blast-induced ground vibration at Shur River Dam, Iran, by artificial neural network. Neural Comput Appl 22:1637–1643. doi: 10.1007/s00521-012-0856-y CrossRefGoogle Scholar
  38. Mozumder RA, Laskar AI (2015) Prediction of unconfined compressive strength of geopolymer stabilized clayey soil using artificial neural network. Comput Geotech 69:291–300. doi: 10.1016/j.compgeo.2015.05.021 CrossRefGoogle Scholar
  39. Neal RM (1992) Bayesian training of back-propagation networks by the hybrid Monte Carlo method. Technical Rep. No. CRG-TG-92-1, Dept. of Computer Science, Univ. of Toronto, TorontoGoogle Scholar
  40. Olden JD, Jackson DA (2002) Illuminating the ‘‘black box’’: a randomization approach for understanding variable contributions in artificial neural networks. Ecol Model 154:135–150. doi: 10.1016/S0304-3800(02)00064-9 CrossRefGoogle Scholar
  41. Ozesmi SL, Ozesmi U (1999) An artificial neural network approach to spatial modeling with inter specific interactions. Ecol Model 116:15–31. doi: 10.1016/S0304-3800(98)00149-5 CrossRefGoogle Scholar
  42. Park HI, Lee SR (2011) Evaluation of the compression index of soils using an artificial neural network. Comput Geotech 38:472–481. doi: 10.1016/j.compgeo.2011.02.011 CrossRefGoogle Scholar
  43. Poran CJ, Herrmann LR, Romstad KM (1989) Finite element analysis of footings on geogrid-reinforced soil. In: Proceedings of geosynthetics, San Diego, USA, pp 231–242Google Scholar
  44. Poulos HJ, Davis EH (1974) Elastic solution for the soil and rock mechanisms. Wiley, New YorkGoogle Scholar
  45. Rumelhart DE, Hinton GE, Williams RJ (1986) Learning internal representation by error propagation. In: Rumelhart DE, McCleland JL (eds) Parallel distribution processing: explorations in the microstructure of cognition, vol 1. MIT Press, Cambridge, pp 318–362Google Scholar
  46. Sakellariou MG, Ferentinou MD (2005) A study of slope stability prediction using neural networks. Geotech Geol Eng 23:419–445. doi: 10.1007/s10706-004-8680-5 CrossRefGoogle Scholar
  47. Sarkar K, Tiwary A, Singh TN (2010) Estimation of strength parameters of rock using artificial neural networks. Bull Eng Geol Environ 69:599–606. doi: 10.1007/s10064-010-0301-3 CrossRefGoogle Scholar
  48. Shahin MA, Maier HR, Jaksa MB (2004) Data division for developing neural networks applied to geotechnical engineering. J Comput Civ Eng 18(2):105–114. doi: 10.1061/(ASCE)0887-3801(2004)18:2(105) CrossRefGoogle Scholar
  49. Singh TN, Kanchan R, Verma AK, Saigal K (2005) A comparative study of ANN and neuro-fuzzy for the prediction of dynamic constant of rockmass. J Earth Syst Sci 114:75–86CrossRefGoogle Scholar
  50. Sinha SK, Wang MC (2008) Artificial neural network prediction models for soil compaction and permeability. Geotech Geol Eng 26:47–64. doi: 10.1007/s10706-007-9146-3 CrossRefGoogle Scholar
  51. Sivapullaiah PV, Guru Prasad B, Allam MM (2009) Modeling sulfuric acid induced swell in carbonate clays using artificial neural networks. Geomech Eng 1(4):307–321. doi: 10.12989/gae.2009.1.4.307 CrossRefGoogle Scholar
  52. Sobhani J, Najimi M, Pourkhorshidi AR, Parhizkar T (2010) Prediction of the compressive strength of no-slump concrete: a comparative study of regression, neural network and ANFIS models. Constr Build Mater 24:709–718. doi: 10.1016/j.conbuildmat.2009.10.037 CrossRefGoogle Scholar
  53. Sonmez H, Gokceoglu C, Nefeslioglu HA, Kayabasi A (2006) Estimation of rock modulus: for intact rocks with an artificial neural network and for rock masses with a new empirical equation. Int J Rock Mech Min 43:224–235. doi: 10.1016/j.ijrmms.2005.06.007 CrossRefGoogle Scholar
  54. Verschuuren G (2007) Excel 2007 for scientists and engineers. Holy Macro! Books, UniontownGoogle Scholar
  55. Wilson-Fahmy RF, Koerner RM (1993) Finite element modeling of soil geogrid interface with application to the behavior of geogrids in a pullout loading conditions. Geotext Geomembr 12:479–501. doi: 10.1016/0266-1144(93)90023-H CrossRefGoogle Scholar
  56. Yamamoto K, Otani J (2002) Bearing capacity and failure mechanism of reinforced foundations based on rigid-plastic finite element formulation. Geotext Geomembr 20:367–393. doi: 10.1016/S0266-1144(02)00031-6 CrossRefGoogle Scholar
  57. Yaprak H, Karaci A, Demir I (2013) Prediction of the effect of varying cure conditions and w/c ratio on the compressive strength of concrete using artificial neural networks. Neural Comp Appl 22:133–141. doi: 10.1007/s00521-011-0671-x CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.Department of Civil EngineeringNIT SilcharSilcharIndia

Personalised recommendations