Estimation of Groundwater Seepage Risks into Tunnel Using Radial Basis Function Networks

Document Type : Research Paper


1 Department of Mining Engineering, Faculty of Engineering, University of Birjand, Birjand, Iran.

2 Department of surveying and Geomatics Engineering, College of Engineering, University of Tehran, Tehran, Iran.


In this study, Site Groundwater Rating (SGR) in the Amirkabir tunnel has been estimated using Radial Basis Function Networks (RBFNs). SGR is the first rating method that by considering the parameters like joint frequency, joint aperture, schistosity, crashed zones, karstification, soil permeability coefficient, tunnel location in the water table or piezometric surface, and the amount and intensity of annual raining in the area, classifies the tunnel path from the risk of groundwater seepage point of view. In this article, using an RBFN, an estimation of SGR along the Amirkabir tunnel path was performed. Field data obtained from primary studies in the tunnel was used to train and test the prepared network. For the testing set, modeling results showed that SGR could be predicted with the mean error of 3.57% and 4.76% using radial basis network and exact radial basis network functions, respectively. A High correlation between the SGR of the tunnel path and the network answers, confirmed the prepared RBFN.


Main Subjects

  • Agatonovic-Kustrin S, and Beresford R. 2000. Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research. Journal of pharmaceutical and biomedical analysis, 22(5), pp.717-727.


  • Bishop C.M. 1995. Neural Networks for Pattern Recognition. Oxford University Press, Oxford.


  • Brantberger M., Dalmalm T., Eriksson M., Stille H. 1998. Steering factors of tightness around a pregrouted tunnel. Royal Institute of Technology, Stockholm, Sweden. In Swedish.


  • Brizzotti M.M., Carvalho A.C.P.L.F. 1999. The influence of clustering techniques in the RBF networks generalization: Proceedings of the Seventh International Conference on Image. Processing and Its Applications 1, pp. 87–92.


  • Broomhead D.S., Lowe D. 1988. Multivariable functional interpolation and adaptive networks. Complex Sys. 2, pp. 321-335


  • Bruzzone L., Prieto D.F. 1999. A technique for the selection of kernel-function parameters in RBF neural networks for classification of remote-sensing images. Trans. Vol. Geosci. & Remote Sen. 37 (2), pp. 1179–1184.


  • Butscher, C., 2012. Steady-state groundwater inflow into a circular tunnel. Tunnelling and Underground Space Technology, 32, pp.158-167.


  • Cesano D. 1999. Prediction of Groundwater flows into Underground Constructions in Hard Rocks. Royal Institute of Technology, Stockholm, Sweden.


  • Cesano D., Olofsson B., Bagtzoglou A.C. 2000. Parameters Regulating Groundwater inflows into Hard Rock Tunnels - a Statistical Study of the Bolmen Tunnel in Southern Sweden. Tunneling and Underground Space Technology, 15(2):153-165.


  • Daliakopoulos, I.N., Coulibaly, P. and Tsanis, I.K., 2005. Groundwater level forecasting using artificial neural networks. Journal of hydrology309(1-4), pp.229-240.


  • De Castro, M.C.F., De Castro, C.C. and Arantes, D.S., 1999, July. RBF neural networks with centers assignment via Karhunen-Loeve transform. In IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No. 99CH36339)(Vol. 2, pp. 1265-1270). IEEE.


  • Demuth H., Beale M. 1998. Neural Network Toolbox for Use with Matlab, Fifth ed. Math works.


  • Deng Y., Zhou X., Shen J., Xiao G., Hong H., Lin H., Wu F. and Liao B.Q. 2021. New methods based on back propagation (BP) and radial basis function (RBF) artificial neural networks (ANNs) for predicting the occurrence of haloketones in tap water. Science of The Total Environment, 772, p.145534.
  • El Tani M. 1999. Water inflow into tunnels. Proceedings of the World Tunnel Congress ITA- ITES 1999, Oslo, pp. 61–70, Balkema.


  • El Tani M. 2003. Circular tunnel in a semi-infinite aquifer. Undergr. Space Technol. 18 (1), pp. 49-55.


  • Farhadian H. and Nikvar-Hassani A. 2019. Water flow into tunnels in discontinuous rock: a short critical review of the analytical solution of the art. Bulletin of Engineering Geology and the Environment, 78(5), pp.3833-3849.


  • Farhadian, H., Aalianvari, A. and Katibeh, H., 2012. Optimization of analytical equations of groundwater seepage into tunnels: A case study of Amirkabir tunnel. Journal of the Geological Society of India80(1), pp.96-100.


  • Farhadian H., Katibeh H., 2015a. Groundwater Seepage Estimation into Amirkabir Tunnel Using Analytical Methods and DEM and SGR Method. World Academy of Science, Engineering and Technology, International Journal of Civil, Structural, Construction and Architectural Engineering, 9(3):296-301.


  • Farhadian H., Katibeh H., 2015b. Effect of Model Dimension in Numerical Simulation on Assessment of Water Inflow to Tunnel in Discontinues Rock. World Academy of Science, Engineering and Technology, International Journal of Environmental, Chemical, Ecological, Geological and Geophysical Engineering, 9(4):350-353.


  • Farhadian H., Katibeh H., Huggenberger P., Butscher C. 2016a. Optimum model extent for numerical simulation of tunnel inflow in fractured rock. Tunnelling and Underground Space Technology, 60:21-29.


  • Farhadian, H., Katibeh, H. and Huggenberger, P., 2016b. Empirical model for estimating groundwater flow into tunnel in discontinuous rock masses. Environmental Earth Sciences, 75(6), pp.1-16.


  • Farhadian, H., Nikvar Hassani, A. and Katibeh, H., 2017. Groundwater inflow assessment to Karaj Water Conveyance tunnel, northern Iran. KSCE Journal of Civil Engineering, 21(6), pp.2429-2438.


  • Farhadian, H., Salehzadeh, M.H. and Nikvar-Hassani, A., 2021, June. Model dimension effect in DEM and FEM simulations for assessment of water inflow into a tunnel. In 55th US Rock Mechanics/Geomechanics Symposium. OnePetro.


  • Fausett, L., 1994. Fundamentals of Neural Networks. Prentic Hall Intenational. : Upper Saddle River, NJ, USA.


  • Feng X.T., Zhao H. and Li S. 2004. Modeling non-linear displacement time series of geo-materials using evolutionary support vector machines. International journal of rock mechanics and mining sciences, 41(7), pp.1087-1107.


  • Fernandez G., Moon J. 2010. Excavation-induced hydraulic conductivity reduction around a tunnel, part 1: guideline for estimate of ground water inflow rate. Tunn Undergr Space Technol 25(5):560-566.


  • Freeze R.A., Cherry J.A. 1979. Groundwater: Prentice-Hall, Englewood Cliffs, New Jersey.


  • Gattinoni, P., Scesi, L.T.G. and Terrana, S., 2008. Hydrogeological risk analysis for tunneling in anisotropic rock masses. In ITA-AITES World Tunnel Congress(pp. 1736-1747).


29- Goodman, R.E., Moye, D.G., Van Schalkwyk, A. and Javandel, I., 1964. Ground water inflows during tunnel driving. College of Engineering, University of California.


30- Grelle, G. and Guadagno, F.M., 2013. Regression analysis for seismic slope instability based on a double phase viscoplastic sliding model of the rigid block. Landslides10(5), pp.583-597.


31- Xiaohui, G.U.O. and Xiaoping, M.A., 2010. Mine water discharge prediction based on least squares support vector machines. Mining Science and Technology (China)20(5), pp.738-742.


32- Gunnink J.L., Bosch J.H.A., Siemon B., Roth B., Auken E. 2012. Combining ground-based and airborne EM through Artificial Neural Networks for modelling glacial till under saline groundwater conditions. Hydrology & Earth System Sciences, 16 (8), pp, 3061-3074. 14p.


  • Hardy, R.L., 1971. Multiquadric equations of topography and other irregular surfaces. Journal of geophysical research76(8), pp.1905-1915.


  • Harpham, C. and Dawson, C.W., 2006. The effect of different basis functions on a radial basis function network for time series prediction: A comparative study. Neurocomputing69(16-18), pp.2161-2170.


  • Haykin, S., 1994. Neural networks: MacMillan College Publ. , New York.


  • Imrie, C.E., Durucan, S. and Korre, A., 2000. River flow prediction using artificial neural networks: generalisation beyond the calibration range. Journal of hydrology233(1-4), pp.138-153.


  • Karlsrud K. 2001.Water control when tunnelling under urban areas in the Olso region. NFF publication No. 12, 4, 27–33, NFF.


  • Katibeh, H. and Aalianvari, A., 2009. Development of a New Method for Tunnel Site Rating from. Journal of Applied Sciences9(8), pp.1496-1502.


  • Kiernan, L., Mason, J.D. and Warwick, K., 1996. Robust initialisation of gaussian radial basis function networks using partitioned k-means clustering. Electronics letters32(7), pp.671-673.


  • Klerfors, D. and Huston, T.L., 1998. Artificial neural networks.  Louis University, St. Louis, Mo.


  • Kohonen T. 1990. The self-organizing map: Proc. IEEE. 78 (9), pp. 1464–1480.


  • Kompani-Zare, M. and Zhan, H., 2006. Steady flow to a horizontal drain in an unconfined aquifer with variable thickness. Journal of hydrology327(1-2), pp.174-185.


  • Kubat, M., 1998. Decision trees can initialize radial-basis function networks. IEEE Transactions on Neural Networks9(5), pp.813-821.


  • Kung, S.Y., 1993. Digital neural networks. PTR Prentice Hall Englewood Cluffs.


  • Lallahem, S., Mania, J., Hani, A. and Najjar, Y., 2005. On the use of neural networks to evaluate groundwater levels in fractured media. Journal of hydrology307(1-4), pp.92-111.


  • Lei, S., 1999. An analytical solution for steady flow into a Ttonnel. Groundwater37(1), pp.23-26.


  • Li L., Lei T., Li S., Zhang Q., Xu Z., Shi S. and Zhou, Z. 2015. Risk assessment of water inrush in karst tunnels and software development. Arabian Journal of Geosciences, 8(4), pp.1843-1854.


  • Li, S.C., Zhou, Z.Q., Li, L.P., Xu, Z.H., Zhang, Q.Q. and Shi, S.S., 2013. Risk assessment of water inrush in karst tunnels based on attribute synthetic evaluation system. Tunnelling and underground space technology38, pp.50-58.


  • Lin, G.F. and Chen, L.H., 2004. A non-linear rainfall-runoff model using radial basis function network. Journal of Hydrology289(1-4), pp.1-8.


  • Lombardi G. 2002. Private communication.


  • Mai-Duy, N. and Tran-Cong, T., 2003. Approximation of function and its derivatives using radial basis function networks. Applied Mathematical Modelling27(3), pp.197-220.


  • Mak, M.W. and Cho, K.W., 1998, May. Genetic evolution of radial basis function centers for pattern classification. In 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No. 98CH36227)(Vol. 1, pp. 669-673). IEEE.
  • Maleki, M.R., 2018. Groundwater Seepage Rate (GSR); a new method for prediction of groundwater inflow into jointed rock tunnels. Tunnelling and Underground Space Technology, 71, pp.505-517.


  • Maleki, Z., Farhadian, H. and Nikvar-Hassani, A., 2021. Geological hazards in tunnelling: the example of Gelas water conveyance tunnel, Iran. Quarterly Journal of Engineering Geology and Hydrogeology, 54(1).


  • Mendoza, O., Melin, P. and Licea, G., 2009. A hybrid approach for image recognition combining type-2 fuzzy logic, modular neural networks and the Sugeno integral. Information Sciences179(13), pp.2078-2101.


  • Moeini, H., Farhadian, H. and Nikvar-Hassani, A., 2018. Determination of the optimum sealing method for Azad pumped storage dam considering seepage analysis. Arabian Journal of Geosciences, 11(14), pp.1-13.


  • Moody, J.E., 1991, September. Note on generalization, regularization and architecture selection in nonlinear learning systems. In Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop(pp. 1-10). IEEE.
  • Moody, J. and Darken, C.J., 1989. Fast learning in networks of locally-tuned processing units. Neural computation1(2), pp.281-294.


  • Moon, J. and Fernandez, G., 2010. Effect of excavation-induced groundwater level drawdown on tunnel inflow in a jointed rock mass. Engineering Geology110(3-4), pp.33-42.


  • Moon, J. and Jeong, S., 2011. Effect of highly pervious geological features on ground-water flow into a tunnel. Engineering Geology117(3-4), pp.207-216.


  • Morshed, J. and Kaluarachchi, J.J., 1998. Application of artificial neural network and genetic algorithm in flow and transport simulations. Advances in Water Resources22(2), pp.145-158.


  • Musavi, M.T., Ahmed, W., Chan, K.H., Faris, K.B. and Hummels, D.M., 1992. On the training of radial basis function classifiers. Neural networks5(4), pp.595-603.


  • Hassani, A.N., Farhadian, H. and Katibeh, H., 2018. A comparative study on evaluation of steady-state groundwater inflow into a circular shallow tunnel. Tunnelling and Underground Space Technology73, pp.15-25.


  • Nikvar Hassani A., Katibeh H., Farhadian H. 2016. Numerical analysis of steady-state groundwater inflow into Tabriz line 2 metro tunnel, northwestern Iran, with special consideration of model dimensions. Bulletin of Engineering Geology and the Environment. 75(4):1617-27.


  • Ocak, I. and Seker, S.E., 2012. Estimation of elastic modulus of intact rocks by artificial neural network. Rock Mechanics and Rock Engineering45(6), pp.1047-1054.


  • Ovidio J., Santos J.R., Tarcisio B.C. 2008. Artificial neural networks analysis of Sao Paulo subway tunnel settlement data. Tunn. Undergr. Space Technol. 23, 481–491.


  • Palmstrom, A. and Stille, H., 2007. Ground behaviour and rock engineering tools for underground excavations. Tunnelling and Underground Space Technology22(4), pp.363-376.


  • Park, K.H., Owatsiriwong, A. and Lee, J.G., 2008. Analytical solution for steady-state groundwater inflow into a drained circular tunnel in a semi-infinite aquifer: a revisit. Tunnelling and Underground Space Technology23(2), pp.206-209.


  • Perrochet, P. and Dematteis, A., 2007. Modeling transient discharge into a tunnel drilled in a heterogeneous formation. Groundwater45(6), pp.786-790.


  • Polla, J. and Ritola, J., 1989. Large rock caverns. Drainage and sealing of rock caverns. Technical Research Centre of Finland, Research notes1000.
  • Rajurkar, M.P., Kothyari, U.C. and Chaube, U.C., 2004. Modeling of the daily rainfall-runoff relationship with artificial neural network. Journal of Hydrology285(1-4), pp.96-113.


  • Ren, R. and Xu, M., 2011. Using BP network to predict tunnel water-inrush in partition style anticlinal belt. Xiandai Suidao Jishu48(6), pp.47-52.


  • Ripley, B.D., 2007. Pattern recognition and neural networks. Cambridge university press.
  • Sato Y. 1996. On artificial neural networks as a statistical mode: Proc. Inst. Statist. Math. 44, pp. 85-98.


  • SCE Company 2006. Geological and Engineering Geological Report for Amirkabir Water Conveyance Tunnel Project (Lot1), unpublished report.
  • Shirzad, Tabesh M. and Farmani R. 2014. A comparison between performance of support vector regression and artificial neural network in prediction of pipe burst rate in water distribution networks. KSCE Journal of Civil Engineering, 18(4), pp.941-948.


  • Sievanen U. 2001. Leakage and groutability. Working Report 2001-06.


  • Suwansawat, S. and Einstein, H.H., 2006. Artificial neural networks for predicting the maximum surface settlement caused by EPB shield tunneling. Tunnelling and underground space technology21(2), pp.133-150.


  • Tabesh M., Soltani J., Farmani, R. and Savic D. 2009. Assessing pipe failure rate and mechanical reliability of water distribution networks using data-driven modeling. Journal of Hydroinformatics, 11(1), pp.1-17.


  • Tarassenko L. 2004. A guide to neural computing applications: John Wiley & Sons.


  • Tolppanen, P., 1997. Water Leakage amounts in excavations, literature study. Memorandum T-2000-18/97 (based on a memorandum of 1996). Consulting Engineers Saanio & Riekkola Oy, Helsinki, Finland (in Finnish).


  • Vogt, M., 1993, March. Combination of radial basis function neural networks with optimized learning vector quantization. In IEEE International Conference on Neural Networks(pp. 1841-1846). IEEE.


  • Wang Y., Yang W., Li M. and Liu X. 2012. Risk assessment of floor water inrush in coal mines based on secondary fuzzy comprehensive evaluation. International Journal of Rock Mechanics and Mining Sciences, 52, pp.50-55.


  • Webb A. 1999. Statistical Pattern Recognition. Arnold, London.


  • West, D. and Dellana, S., 2009. Diversity of ability and cognitive style for group decision processes. Information Sciences179(5), pp.542-558.


  • Yoo J.H., Sethi I.K. 1995. Design of radial basis function networks using decision trees: Proceedings of the IEEE International Conference on Neural Networks 3, pp. 1269–1272.
Volume 45, Issue 2
June 2022
Pages 109-124
  • Receive Date: 24 May 2021
  • Revise Date: 10 September 2022
  • Accept Date: 11 September 2022
  • Publish Date: 22 June 2022