Abstract
Application of artificial neural networks (ANN) in various aspects of geotechnical engineering problems such as site characterization due to have difficulty to solve or interrupt through conventional approaches has demonstrated some degree of success. In the current paper a developed and optimized five layer feed-forward back-propagation neural network with 4-4-4-3-1 topology, network error of 0.00201 and R2 = 0.941 under the conjugate gradient descent ANN training algorithm was introduce to predict the clay sensitivity parameter in a specified area in southwest of Sweden. The close relation of this parameter to occurred landslides in Sweden was the main reason why this study is focused on. For this purpose, the information of 70 piezocone penetration test (CPTu) points was used to model the variations of clay sensitivity and the influences of direct or indirect related parameters to CPTu has been taken into account and discussed in detail. Applied operation process to find the optimized ANN model using various training algorithms as well as different activation functions was the main advantage of this paper. The performance and feasibility of proposed optimized model has been examined and evaluated using various statistical and analytical criteria as well as regression analyses and then compared to in situ field tests and laboratory investigation results. The sensitivity analysis of this study showed that the depth and pore pressure are the two most and cone tip resistance is the least effective factor on prediction of clay sensitivity.
Similar content being viewed by others
References
Aas G, Lacasse S, Lunne T, Hoeg K (1986) Use of in situ tests for foundation design on clay. Use of in situ tests in geotechnical engineering (GSP 6). ASCE, New York, pp 1–30
Åhnberg H, Larsson R (2012) Strength degradation of clay due to cyclic loadings and enforced deformation. Report No 75, Swedish Geotechnical Institute (SGI), Linköping, Sweden
Anagnostopoulosi A, Koukis G, Sabatakakis N, Tsliambaos G (2003) Empirical correlations of soil parameters based on Cone Penetration Tests (CPT) for Greek soils. Geotech Geol Eng 21:377–387
Baligh MM, Vivatrat V, Ladd CC (1980) Cone penetration in soil profiling. J Geotech Eng 112(7):727–745
Bar-Yam Y (1997) Dynamics of complex systems. Addison-Wesley, Boston
Basheer IA, Reddi LN, Najjar YM (1996) Site characterization by neuronets: an application to the landfill sitting problem. Ground Water 34:610–617
Baziar MH, Ghorbani A (2005) Evaluation of lateral spreading using artificial neural networks. Soil Dyn Earthq Eng 25(1):1–9
Bertsekas DP (1995) Nonlinear programming. Athena Scientific, Belmont
Cai GJ, Liu SY, Tong LY (2010) Field evaluation of deformation characteristics of a lacustrine clay deposit using seismic piezocone tests. Eng Geol 116(3):251–260
Cal Y (1995) Soil classification by neural-network. Adv Eng Softw 22(2):95–97
Canadian Geotechnical Society (2006) Canadian foundation engineering manual, 4th edn. p 506
Celik S, Tan O (2005) Determination of pre-consolidation pressure with artificial neural network. Civil Eng Environ Syst 22(4):217–231
Cevik A, Sezer EA, Cabalar AF, Gokceoglu C (2011) Modeling of the uniaxial compressive strength of some clay-bearing rocks using neural network. Appl Soft Comput 11:2587–2594
Das SK (2005) Applications of genetic algorithm and artificial neural network to some geotechnical engineering problems. Ph.D. Thesis, Indian Institute of Technology Kanpur, Kanpur, India
Erzin Y (2007) Artificial neural networks approach for swell pressure versus soil suction behavior. Can Geotech J 44(10):1215–1223
Fahlman SE (1988) Faster learning variations on back propagation: an empirical study. In: Sejnowski TJ, Hinton GE, Touretzky DS (eds) Connectionist models summer school. Proceedings of the 1988 connectionist summer school, San Mateo, USA
Fahlman SE, Lebiere C (1990) The cascade-correlation learning architecture. In: Touretzky DS (ed) Advances in neural information processing systems 2. Morgan Kaufman, San Mateo, pp 524–532
Fausett L (1994) Fundamentals of neural networks: architectures, and applications. Prentice-Hall, Englewood Cliffs
Fernandez-Steeger TM, Rohn J, Czurda K (2002) Identification of landslide areas with neural nets for hazard analysis. In: Rybar J, Stemnerk J, Wagner P (eds) Landslides. Proceedings of the IECL, Prague, Cz. Rep. June 24–26, 2002. Balkema, The Netherland, pp 163–168
Goh AT (2002) Probabilistic neural network for evaluating seismic liquefaction potential. Can Geotech J 39(1):219–232
Gribb MM, Gribb GW (1994) Use of neural networks for hydraulic conductivity determination in unsaturated soil. In: Proceedings of the 2nd international conference on ground water ecology, Bethesda, pp 155–163
Hanna AM, Ural D, Saygili G (2007) Neural network model for liquefaction potential in soil deposits using Turkey and Taiwan earthquake data. Soil Dyn Earthq Eng 27(6):521–540
Hong S, Lee M, Kim J, Lee W (2010) Evaluation of undrained shear strength of Busan clay using CPT, 2nd international symposium on Cone Penetration Testing, CPT’10. In: Proceedings of 2nd international symposium on Cone Penetration Testing, CPT’10, online, 2010. Paper No. 2–23
Hubick KT (1992) Artificial neural networks in Australia. Department of Industry, Technology and Commerce, Commonwealth of Australia, Canberra
Ishihara K (1993) Liquefaction and flow failure during earthquakes. Geotechnique 43(3):351–415
Jaksa MB (1995) The influence of spatial variability on the geotechncial design properties of a stiff, overconsolidated clay. Ph.D. dissertation, The University of Adelaide, Adelaide
Jamiolkowski M, Lancellotta R, Tordella L, Battaglio M (1982) Undrained Strength from CPT. In: Proceedings of 2nd European symposium on penetration testing, Amsterdam, pp 599–606
Jong YH, Lee CI (2004) Influence of geological conditions on the powder factor for tunnel blasting. Int J Rock Mech Min Sci 41(Supplement 1):533–538
Karlsrud K, Lunne T, Brattlieu K (1996) Improved CPTu correlations based on block samples. Nordisk Geoteknikermote, Reykjavik
Karlsson R, Hansbo S (1989) Soil classification and identification. Byggforskningsrådet Doc D 8:1989
Kim Y, Kim B (2006) Use of artificial neural networks in the prediction of liquefaction resistance of sands. J Geotech Geoenviron Eng 132(11):1502–1504
Kim KK, Prezzi M, Salgado R (2006) Interpretation of cone penetration tests in cohesive soils. Publication FHWA/IN/JTRP-2006/22. Joint transportation research program, Indiana Department of Transportation and school of Civil Engineering Purdue University, West Lafayette, Indiana. doi:10.5703/1288284313387
Klingberg F (2010) Bottenförhållanden i Göta Älv: SGU-rapport 2010:7. Sveriges Geologiska Undersökning, Göteborg
La Rochelle P, Zebdi PM, Leroueil S, Tavenas F, Virely D (1988) Piezocone tests in sensitive clays of eastern Canada. In: Proceedings of the international symposium on penetration testing, ISOPT-1, Orlando, 2, Balkema Pub., Rotterdam, pp 831–841
Le Bihan JP, Leroueil S (1981) The fall cone and behavior of remoulded clay. Terratech Ltd, Research report, Montreal
Lee SJ, Lee SR, Kim YS (2003) An approach to estimate unsaturated shear strength using artificial neural network and hyperbolic formulation. Comput Geotech 30(6):489–503
Levenberg K (1944) A method for the solution of certain non-linear problems in least squares. Q Appl Math 2:164–168
Lindskog G (1983) Brief report of the investigation of the slope stability along the river in Göta River valley. Statens Geotekniska Institut, Linköping
Lourakis MIA (2005) A brief description of the Levenberg-Marquardt algorithm implemented by levmar. Technical Report, Institute of Computer Science, Foundation for Research and Technology—Hellas
Lundström K, Larsson R, Dahlin T (2009) Mapping of quick clay formations using geotechnical and geophysical methods. Landslides 6:1–15
Lunne T, Kleven A (1981) Role of CPT in North Sea foundation engineering. In: Symposium on cone penetration engineering division, ASCE, pp 49–75
Lunne T, Robertson PK, Powell JJM (1997) Cone penetration testing in geotechnical practice. Blackie Academic, EF Spon/Routledge Publ, New York, p 312
Lunne T, Christoffersen H, Tjelta T (1985) Engineering use of piezocone data in North Sea clays, In: Proceedings of ICSMFE–11; San Francisco, 2, 1985, pp 907–912
Lunne T, Eidsmoen T, Gillespie D, Howland JD (1986) Laboratory and field evaluation of cone penetrometer. In: Proceedings of in situ ‘86, use of in situ tests in geotechnical engineering. ASCE GSP 6, Blacksburg, Virginia, pp 714–729
Maier HR, Dandy GC (2000) Neural networks for prediction and forecasting of water resource variables: a review of modeling issues and applications. Environ Model softw 15:101–123
Marquardt DW (1963) An algorithm for least-squares estimation of nonlinear parameters. SIAM J Appl Math 11:431–441
Maulenkamp F, Grima MA (1999) Application of neural networks for the prediction of the unconfined compressive strength (UCS) from equotip hardness. Int J Rock Mech Min Sci 36(1):29–39
Mayoraz F, Cornu T, Vuillet L (1996) Using neural networks to predict slope movements. In: Proceedings of VII international symposium on landslides, Trondheim, June 1966, 1. Balkema, Rotterdam, pp 295–300
McCulloch WS, Pitts WH (1943) A logical calculus of ideas immanent in nervous activity. Bull Math Biophys 5(4):115–133
Mitchell JK, Brandon TL (1998) Analysis and Use of CPT in earthquake and environmental engineering. In: Keynote lecture, proceedings of ICS’98, vol 1, pp 69–97
Nadim F, Pedersen SAS, Schmidt-Thomé P, Sigmundsson F, Engdahl M (2008) Natural hazards in Nordic Countries. Episodes 31(1):176–184
Nielson B (1999) Damping parameter In Marquardt’s method. Technical Report IMM-REP-1999- 05, Dept. of Mathematical Modeling, Technical University Denmark
Park HL (2011) Study for application of artificial neural networks in geotechnical problems. In: Hui CLP (ed) Artificial neural networks-application. InTech, Croatia, pp 303–336. doi:10.5772/2052. ISBN 978-953-307-188-6
Rad NS, Lunne T (1988) Direct correlations between piezocone test results and undrained shear strength of clay. In: Proceedings of 1st international symposium on penetration testing, Orlando, vol 2, pp 911–917
Rankka K, Andersson-Sköld Y, Hultén C, Larsson R, Leroux V, Dahlin T (2004) Quick clay in Sweden. Report 65. Swedish Geotechnical Institute, Linköping
Rémai Z (2013) Correlation of undrained shear strength and CPT resistance. Period Polytech Civil Eng 57(1):39–44. doi:10.3311/PPci.2140
Robertson PK (1990) Soil classification using the cone penetration test. Can Geotech J 27(1):151–158
Robertson PK (1999) Estimation of minimum undrained shear strength for flow liquefaction using the CPT. In: Seco e Pinto (ed) Earthquake geotechnical engineering. Balkema, Rotterdam
Robertson PK (2008) Discussion of ‘liquefaction of silts from CPTu. Can Geotech J 44:140–141
Robertson PK, Campanella RG, Gillespie D, Greig J (1986) Use of piezometer cone data. In-situ’86 use of in-situ testing in geotechnical engineering, GSP 6, ASCE, Reston, VA, Specialty Publication, pp 1263–1280
Robitaille D, Demers D, Potvin J, Pellerin F (2002) Mapping of landslide-prone areas in the Saguenay region, Qubec, Canada. In: Instability-planning and management. Tomas Tellford, London
Rojas R (1996) Neural networks—a systematic introduction, chapter 7, the back propagation algorithm. http://www.inf.fu-berlin.de/~rojas/neural/chap7.p.s
Rosenquist IT (1953) Considerations on the sensitivity of Norwegian quick-clays. Geotechnique 3:195–200
Rumelhart DE, Hinton GE, Williams RJ (1986) Chapter 8, learning internal representation by error propagation parallel distribution processing: exploration in the microstructure of cognition, vol 1. MIT Press, Cambridge
Sayadi A, Monjezi M, Talebi N, Khandelwal M (2013) A comparative study on the application of various artificial neural networks to simultaneous prediction of rock fragmentation and backbreak. J Rock Mech Geotech Eng 5:318–324
Schmertmann JH (1975) Measurement of in situ shear strength. In: Proceedings of specialty conference on in situ measurement of soil properties: ASCE, Raleigh, vol 2, pp 57–138
Seed RB, Harder LF Jr (1990) SPT-based analysis of cyclic pore pressure generation and undrained residual strength. In: Duncan JM (ed) Proceedings, seed memorial symposium, BiTech Publishers, Vancouver, pp 351–376
Shahin MA, Jaksa MB, Maier HR (2001) Artificial neural network applications in geotechnical engineering. Aust Geomech 36(1):49–62
Shahin MA, Jaksa MB, Maier HR (2008) State of the art of artificial neural networks in geotechnical engineering. Electron J Geotech Eng Bouquet 08:1–26
Shahri AA, Malehmir A, Juhlin C (2015) Soil classification analysis based on piezocone penetration test data—a case study from a quick-clay landslide site in southwestern Sweden. Eng Geol 189:32–47
Shewchuk JR (1994) An introduction to the conjugate gradient method without the agonizing pain, 1 1/4 edn. School of Computer Science, Carnegie Mellon University, Pittsburgh
Sinha SK, Wang MC (2008) Artificial neural network prediction models for soil compaction and permeability. Geotech Eng J 26(1):47–64
Skempton AW, Northey RD (1952) The sensitivity of clays. Geotechnique 3:30–53
Soderblom R (1969) Salt in Swedish clays and its importance for quick clay formation. In: Swedish Geotechnical Institute, Proceedings, vol 22
Solheim A, Berg K, Forsberg CF, Bryn P (2005) The storegga slide complex: repetitive large scale sliding with similar cause and development. Mar Pet Geol 22:97–107
Stark TD, Juhrend JE (1989) Undrained shear strength from cone penetration tests. In: Proceedings of the 12th international conference on soil mechanics and foundation engineering, Rio de Janeiro, vol 1, pp 327–330
Stark TD, Mesri G (1992) Undrained shear strength of sands for stability analysis. J Geotech Eng Div ASCE 118(11):1727–1747
Terzaghi K (1944) Ends and means in soil mechanics. Eng J 27:608–613
Torrance JK (1983) Towards a general model of quick clay development. Sedimentology 30:547–555
Transtrum MK, Sethna JP (2012) Improvements to the Levenberg-Marquardt algorithm for nonlinear least-squares minimization. Preprint submitted to Journal of Computational Physics, Cornell University Library. arXiv:1201.5885
Tumay MT, Boggess RL, Acar Y (1981) Subsurface investigation with piezocone penetrometer. ASCE GSP Cone Penetr Test Exp, St Louis, pp 325–342
Worth CP (1984) The interpretation of in situ soil tests. Geotechnique 34(4):449–489
Wride CE, McRoberts EC, Robertson PK (1999) Reconsideration of case histories for estimating undrained shear strength in sandy soils. Can Geotech J 36:907–933
Yang Y, Rosenbaum MS (2002) The artificial neural network as a tool for assessing geotechnical properties. Geotech Eng J 20(2):149–168
Yoshimine M, Robertson PK, Wride CE (1999) Undrained shear strength of clean sands to trigger flow liquefaction. Can Geotech J 36:891–906
Zaheer I, Bai CG (2003) Application of artificial neural network for water quality management. Int J Lowland Technol 5(2):10–15
Zhou Y, Wu X (1994) Use of neural networks in the analysis and interpretation of site investigation data. Comput Geotech 16:105–122
Zuidberg HM, Schaap LHJ, Beringen FL (1982) A penetrometer for simultaneously measuring of cone resistance, sleeve friction and dynamic pore pressure. In: Proceedings of the second European symposium on penetration testing, Amsterdam, vol 2, pp 963–970
Zurada JM (1992) Introduction to artificial neural systems. West Publishing Company, St. Paul
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Abbaszadeh Shahri, A. An Optimized Artificial Neural Network Structure to Predict Clay Sensitivity in a High Landslide Prone Area Using Piezocone Penetration Test (CPTu) Data: A Case Study in Southwest of Sweden. Geotech Geol Eng 34, 745–758 (2016). https://doi.org/10.1007/s10706-016-9976-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10706-016-9976-y