Environmental Earth Sciences

, Volume 70, Issue 3, pp 1263–1276 | Cite as

Calculation of surface settlements caused by EPBM tunneling using artificial neural network, SVM, and Gaussian processes

  • Ibrahim Ocak
  • Sadi Evren Seker
Original Article


Increasing demand on infrastructures increases attention to shallow soft ground tunneling methods in urbanized areas. Especially in metro tunnel excavations, due to their large diameters, it is important to control the surface settlements observed before and after excavation, which may cause damage to surface structures. In order to solve this problem, earth pressure balance machines (EPBM) and slurry balance machines have been widely used throughout the world. There are numerous empirical, analytical, and numerical analysis methods that can be used to predict surface settlements. But substantially fewer approaches have been developed for artificial neural network-based prediction methods especially in EPBM tunneling. In this study, 18 different parameters have been collected by municipal authorities from field studies pertaining to EPBM operation factors, tunnel geometric properties, and ground properties. The data source has a preprocess phase for the selection of the most effective parameters for surface settlement prediction. This paper focuses on surface settlement prediction using three different methods: artificial neural network (ANN), support vector machines (SVM), and Gaussian processes (GP). The success of the study has decreased the error rate to 13, 12.8, and 9, respectively, which is relatively better than contemporary research.


Twin tunnel Prediction of surface settlement EPBM Artificial neural network Gaussian processes Support vector machine 



This study was supported by Scientific Research Projects Coordination Unit of Istanbul University. Project numbers are 24410 and YADOP-16728. The authors are grateful to Istanbul Metropolitan Municipality for supplying the data.


  1. Alpaydın E (2010) Introduction to machine learning, 2nd edn. MIT Press, LondonGoogle Scholar
  2. Attewell PB, Yeates J, Selby AR (1986) Soil movement induced by tunneling and their effects on pipelines and structures. Chapman and Hall, New YorkGoogle Scholar
  3. Bishop CM (2006) Pattern recognition and machine learning. Springer, New YorkGoogle Scholar
  4. Cartwright KV (2007) Determining the effective or RMS voltage of various waveforms without calculus. Ph.D. Thesis, School of Sciences and Technology College of the Bahamas, BahamasGoogle Scholar
  5. Cheng MY, Tsai HC, Ko CH, Chang WT (2008) Evolutionary fuzzy neural inference system for decision making in geotechnical engineering. J Comput Civil Eng 22(4):272–280CrossRefGoogle Scholar
  6. Chiorboli MA, Marcheselli PP (1996) Analysis and control of subsidence due to earth pressure shield tunneling in Passante Ferroviario of Milano. In: Proceedings of International Conference on North American Tunneling96. Balkema, Rotterdam, pp 97–106Google Scholar
  7. Clough GW, Leca E (1993) EPB shield tunneling in mixed face conditions. J Geotech Geoenviron 119(10):1640–1656Google Scholar
  8. Ding L, Ma L, Luo H, Yu M, Wu X (2011) Wavelet Analysis for tunneling-induced ground settlement based on a stochastic model. Tunn Undergr Space Technol 26(5):619–628CrossRefGoogle Scholar
  9. Ercelebi S, Copur H, Ocak I (2011) Surface settlement predictions for Istanbul Metro Tunnels excavated by EPB-TBM. Environ Earth Sci 62(2):357–365CrossRefGoogle Scholar
  10. Finno RJ, Clough GW (1985) Evaluation of soil response to EPB shield tunneling. J Geotech Geoenviron 111(2):155–173Google Scholar
  11. Gunn SR (1998) Support vector machines for classification and regression, University of Southamtpon, Technical ReportGoogle Scholar
  12. Hecht NR (1987) Kolmogorov’s mapping neural network existence theorem. In: Proceedings of the first international conference on neural networks. San Diego, USA, pp 11–14Google Scholar
  13. Jancsecz S, Steiner W (1994) Face support for a large Mix-Shield in heterogeneous ground conditions. Tunneling, LondonGoogle Scholar
  14. Leca E (1989) Analysis of NATM and shield tunneling in soft ground, Ph.D. Thesis, Virginia Institute and State University, Blacksburg, VAGoogle Scholar
  15. Mackay DJC (1997) Gaussian processes: a replacement for supervised neural networks, Lecture NotesGoogle Scholar
  16. Matsushita Y, Hashimoto T, Iwasaki Y, Imanishi H (1995) Behavior of subway tunnel driven by large slurry shield. In: Proceedings of International Conference on Underground Construction in Soft Ground. Balkema, Rotterdam, pp 253–256Google Scholar
  17. Mitchell TM (1997) Machine learning. McGraw Hill, New YorkGoogle Scholar
  18. Neal RM (1996) Bayesian learning for neural networks. Springer, New YorkCrossRefGoogle Scholar
  19. Neaupane KM, Adhikari NR (2006) Prediction of tunneling-induced ground movement with the multi-layer perceptron. Tunn Undergr Sp Tech 21(2):151–159CrossRefGoogle Scholar
  20. Nellessen P (2007) Using neurofuzzy systems to predict settlements for slurry shield drives based on an evaluation of the process data synchronous to the advance. In: EURO:TUN (2007) Thematic conference on computational methods in tunnelling. Austria, ViennaGoogle Scholar
  21. Ocak I (2008a) Estimating the modulus of elasticity of the rock material from compressive strength and unit weight. J S Afr Inst Min Metall 108(10):621–626Google Scholar
  22. Ocak I (2008b) Control of surface settlements with umbrella arch method in second stage excavations of Istanbul Metro. Tunn Undergr Sp Tech 23(6):674–681CrossRefGoogle Scholar
  23. Ocak I (2008c) Comparison of machine utilization time and performance for road header and impact hammer in Kadikoy–Kartal metro tunnels (Istanbul). In: 8th international scientific conference, modern management of mine producing, geology and environmental protection, vol 1. Varna, Bulgaria, pp 269–276Google Scholar
  24. Ocak I (2009a) Empirical estimation of intact rock elastic modulus, The 21st International mining congress of Turkey. Antalya, Turkey, pp 165–172Google Scholar
  25. Ocak I (2009b) Environmental problems caused by Istanbul subway excavation and suggestions for remediation, environmental geology. Environ Geol 58(7):1557–1566CrossRefGoogle Scholar
  26. Ocak I (2009c) Environmental effects of tunnel excavation in soft and shallow ground with EPBM: the case of Istanbul. Environ Earth Sci 59(2):347–352CrossRefGoogle Scholar
  27. Ocak I (2011) Overview to ongoing metro projects in Istanbul, Turkey. In: 22nd world mining congress and expo. Istanbul, Turkey, pp 161–168Google Scholar
  28. Ocak I (2012a) Interaction of deformation for twin tunnels in shallow and soft grounds excavated by EPBM. Istanbul University 24410 numbered scientific research projectGoogle Scholar
  29. Ocak I (2012b) Interaction of longitudinal surface settlement profile in soft metro tunneling with EPBM. ITA-AITAS World Tunnel Congress and General Assembly, ThailandGoogle Scholar
  30. Ocak I (2012c) Discussion on article ‘‘Surface subsidence induced by twin subway tunneling in soft ground conditions in Istanbul’’ by Yılmaz Mahmutoglu, Bulletin of Engineering Geology and the Environment, 2011, 70(1), pp 115–131. B Eng Geol Environ 71(2):399–400CrossRefGoogle Scholar
  31. Ocak I, Bilgin N (2010) Comparative studies on the performance of a road header, impact hammer and drilling and blasting method in the excavation of metro station tunnels in Istanbul. Tunn Undergr Sp Tech 25(2):181–187CrossRefGoogle Scholar
  32. Ocak I, Seker SE (2012) Estimation of elastic modulus of intact rocks by artificial neural network. Rock Mech Rock Eng 45(6):1047–1054CrossRefGoogle Scholar
  33. Ovidio J, Santos JR, Tarcisio BC (2008) Artificial neural networks analysis of Sao Paulo subway tunnel settlement data. Tunn Undergr Sp Tech 23:481–491CrossRefGoogle Scholar
  34. Press WH, Teukolsky SA, Vetterling WT, Flannery BP (2007) Numerical recipes: the art of scientific computing. Cambridge University Press, New YorkGoogle Scholar
  35. Qureshi SA, Mirza SM, Arif M (2006) Fitness function evaluation for image reconstruction using binary genetic algorithm for parallel ray transmission tomography, emerging technologies. In: ICET’06 international conference. Islamabad, Pakistan, pp 196–201Google Scholar
  36. Rasmussen CE, Williams CKI (2007) Gaussian processes for machine learning. The MIT Press, CambridgeGoogle Scholar
  37. Rigol-Snachez JP, Chica-Olmo M, Abarca-Hernanderz F (2003) Artificial neural networks as a tool for mineral potential mapping with GIS. Int J Remote Sens 24(5):1151–1156CrossRefGoogle Scholar
  38. Rohmer J, Foerster E (2011) Global sensitivity analysis of large-scale numerical landslide models based on Gaussian-Process meta-modeling. Comput Geosci 37(7):917–927CrossRefGoogle Scholar
  39. Rosenblatt FX (1962) Principles of neurodynamics: perceptrons and the theory of brain mechanisms. Spartan Books, WashingtonGoogle Scholar
  40. Sakar CO, Kursun O (2010) Telediagnosis of Parkinson’s disease using measurements of dysphonia. J Med Syst 34(4):591–599CrossRefGoogle Scholar
  41. Schalkoff RJ (1997) Artificial neural network. McGraw Hill, New YorkGoogle Scholar
  42. Seyfi M, Muhaidat S, Liang J (2012) Amplify-and-forward selection cooperation over Rayleigh fading channels with imperfect CSI. IEEE T Wirel Commun 11(1):199–209CrossRefGoogle Scholar
  43. Shi J, Ortigao JAR, Bai JJ (1998) Modular neural networks for predicting settlements during tunneling. J Getech Geoenviron Eng 124(05):389–395CrossRefGoogle Scholar
  44. Stein ML (1999) Statistical interpolation of spatial data: some theory for Kriging. Springer, ChicagoCrossRefGoogle Scholar
  45. Suwansawat S (2002) Earth pressure balance (EPB) shield tunneling in Bangkok: Ground Response and Prediction of Surface Settlements Using Artificial Neural Networks. Ph.D. Thesis, Massachusetts Institute of Technology, Cambridge, MAGoogle Scholar
  46. Suwansawat S, Einstein HH (2006) Artificial neural networks for predicting the maximum surface settlement caused by EPB shield tunneling. Tunn Undergr Sp Technol 21(2):133–150CrossRefGoogle Scholar
  47. Tipping ME (2001) Sparse bayesian learning and the relevance vector machine. J Mach Learn Res 1:211–244Google Scholar
  48. Wang DD, Qiu GQ, Xie WB, Wang Y (2012) Deformation prediction model of surrounding rock based on GA-LSSVM-markov. Nat Sci 4(2):85–90Google Scholar
  49. Wasserman PD, Schwartz T (1988) Neural networks II. What are they and why is everybody so interested in them now? IEEE Expert 3(1):10–15CrossRefGoogle Scholar
  50. Xu J, Xu Y (2011) Grey correlation-hierarchical analysis for metro-caused settlement. Environ Earth Sci 64(5):1246–1256CrossRefGoogle Scholar
  51. Yang L, Zifeng W, Jun W, Richard AF, Robert KN, Ellsworth JW (2011) The effect of aerosol vertical profiles on satellite-estimated surface particle sulfate concentrations. Remote Sens Environ 115(2):508–513CrossRefGoogle Scholar
  52. Yao BZ, Yang CY, Yao JB, Sun J (2010) Tunnel surrounding rock displacement prediction using support vector machine. Int J Comput Int Sys 3(6):843–852CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  1. 1.Mining Engineering Department, Engineering FacultyIstanbul UniversityIstanbulTurkey
  2. 2.Computer Engineering Department, Engineering FacultyIstanbul UniversityIstanbulTurkey

Personalised recommendations