Natural Hazards

, Volume 84, Issue 3, pp 2145–2162 | Cite as

Design of a support vector machine with different kernel functions to predict scour depth around bridge piers

  • Hassan Sharafi
  • Isa Ebtehaj
  • Hossein Bonakdari
  • Amir Hossein Zaji
Original Paper


Scour depth is a vital subject in bridge pier design. The exact estimation of scour depth can prevent damage caused by bridge failure and facilitate optimal bridge pier design. In this article, the support vector machine (SVM) method is applied to predict scour depth around bridge piers. The SVM technique is developed using six kernel functions, including polynomial, sigmoid, exponential, Gaussian, Laplacian and rational quadratic. Scour depth is modeled as a function of three dimensionless variables, namely geometric characteristics, flow and bed materials. The performance of SVM (in training and testing) is evaluated using dimensionless variables gathered from a wide range of field datasets. The SVM designed using the polynomial kernel function produced the most accurate results compared with the other kernel functions (RMSE = 0.078, MRE = −0.181, MARE = 0.332, MSRE = 0.025). Sensitivity analysis is performed to identify the effect of each dimensionless parameter on predicting scour depth around bridge piers. The testing results of SVM-polynomial are compared with that of the artificial neural networks (ANN), adaptive neuro-fuzzy inference systems (ANFIS) and nonlinear regression-based methods presented in this study and in the literature. Evidently, SVM-polynomial predicted scour depth with higher accuracy and lower error than when using ANN, ANFIS and nonlinear regression-based equations. Moreover, as an alternative method, a simple program is presented by the SVM-polynomial to calculate scour depth around bridge piers.


Bridge pier Scour depth Support vector machine (SVM) Sensitivity analysis Traditional equation 


  1. Aminossadati SM, Kargar A, Ghasemi B (2012) Adaptive network-based fuzzy inference system analysis of mixed convection in a two-sided lid-driven cavity filled with a nanofluid. Int J Therm Sci 52:102–111. doi: 10.1016/j.ijthermalsci.2011.09.004 CrossRefGoogle Scholar
  2. Azamathulla HM, Ghani AA (2010) ANFIS-based approach for predicting the scour depth at culvert outlets. J Pipeline Syst Eng Pract 2(1):35–40. doi: 10.1061/(ASCE)PS.1949-1204.0000066 CrossRefGoogle Scholar
  3. Azamathullah HM, Ghani AA, Zakaria NA, Guven A (2010) Genetic programming to predict bridge pier scour. J Hydraul Eng 136(3):165–169. doi: 10.1061/(ASCE)HY.1943-7900.0000133 CrossRefGoogle Scholar
  4. Bateni SM, Borghei SM, Jeng DS (2007) Neural network and neuro-fuzzy assessments for scour depth around bridge piers. Eng Appl Artif Intell 20(3):401–414. doi: 10.1016/j.engappai.2006.06.012 CrossRefGoogle Scholar
  5. Bonakdari H, Baghalian S, Nazari F, Fazli M (2011) Numerical analysis and prediction of the velocity field in a curved open channel using artificial neural network and genetic algorithm. Eng Appl Comput Fluid Mech 5(3):384–396. doi: 10.1080/19942060.2011.11015380 Google Scholar
  6. Ch S, Anand N, Panigrahi BK, Mathur S (2013) Streamflow forecasting by SVM with quantum behaved particle swarm optimization. Neurocomputing 101:18–23. doi: 10.1016/j.neucom.2012.07.017 CrossRefGoogle Scholar
  7. Chiew Y (1992) Scour protection at bridge piers. J Hydraul Eng 118(9):1260–1269. doi: 10.1061/(ASCE)0733-9429(1992)118:9(1260) CrossRefGoogle Scholar
  8. Cimen M (2008) Estimation of daily suspended sediments using support vector machines. Hydrol Sci J 53(3):656–666. doi: 10.1623/hysj.53.3.656 CrossRefGoogle Scholar
  9. Ebtehaj I, Bonakdari H (2013) Evaluation of sediment transport in sewer using artificial neural network. Eng Appl Comput Fluid Mech 7(3):82–392. doi: 10.1080/19942060.2013.11015479 Google Scholar
  10. Ebtehaj I, Bonakdari H (2014) Performance evaluation of adaptive neural fuzzy inference system for sediment transport in sewers. Water Resour Manag 28(13):4765–4779. doi: 10.1007/s11269-014-0774-0 CrossRefGoogle Scholar
  11. Ebtehaj I, Bonakdari H (2016) Bed load sediment transport estimation in a clean pipe using multilayer perceptron with different training algorithms. KSCE J Civ Eng 20(2):581–589. doi: 10.1007/s12205-015-0630-7 CrossRefGoogle Scholar
  12. Ebtehaj I, Bonakdari H, Zaji AH, Azimi H, Sharifi A (2015) Gene expression programming to predict the discharge coefficient in rectangular side weirs. Appl Soft Comput. doi: 10.1016/j.asoc.2015.07.003 Google Scholar
  13. Ettema R, Melville BW, Barkdoll B (1998) Scale effect of pier-scour experiments. J Hydraul Eng 124(6):639–642. doi: 10.1061/(ASCE)0733-9429(1998)124:6(639) CrossRefGoogle Scholar
  14. Grigorievskiy A, Miche Y, Ventelä AM, Séverin E, Lendasse A (2014) Long-term time series prediction using OP-ELM. Neural Netw 51:50–56. doi: 10.1016/j.neunet.2013.12.002 CrossRefGoogle Scholar
  15. Guven A, Azamathulla HM, Zakaria NA (2009) Linear genetic programming for prediction of circular pile scour. Ocean Eng 39(12–13):985–991. doi: 10.1016/j.oceaneng.2009.05.010 CrossRefGoogle Scholar
  16. Johnson PA (1992) Reliability-based pier scour engineering. J Hydraul Eng 118(10):1344–1357. doi: 10.1061/(ASCE)0733-9429(1992)118:10(1344) CrossRefGoogle Scholar
  17. Kamatchi P, Rao KB, Iyer NR, Arunachalam S (2012) Neural network-based methodology for inter-arrival times of earthquakes. Nat Hazards 64(2):1291–1303. doi: 10.1007/s11069-012-0297-z CrossRefGoogle Scholar
  18. Kazeminezhad MH, Etemad-Shahidi A, Bakhtiary AY (2010) An alternative approach for investigation of the wave-induced scour around pipelines. J. Hydroinform 12(1):51–65. doi: 10.2166/hydro.2010.042 CrossRefGoogle Scholar
  19. Khan M, Azamathulla HM, Tufail M, Ab Ghani A (2012) Bridge pier scour prediction by gene expression programming. Proc ICE Water Manag 165(9):481–493. doi: 10.1680/wama.11.00008 Google Scholar
  20. Landers MN, Mueller DS (1999) U.S. geological survey field measurements of pier scour. In: Compendium of papers on ASCE water resources engineering conference 1991 to 1998, Virginia, USA, pp 585–607Google Scholar
  21. Laursen EM, Toch A (1956) Scour around bridge piers and abutments. Iowa Highway Research Board, Washington, DCGoogle Scholar
  22. Liao R, Zheng H, Grzybowski S, Yang L (2011) Particle swarm optimization-least squares support vector regression based forecasting model on dissolved gases in oil-filled power transformers. Electr Power Syst Res 81(12):2074–2080. doi: 10.1016/j.epsr.2011.07.020 CrossRefGoogle Scholar
  23. Lv F, Kang F, Sun H (2014) The predictive method of power load based on SVM. TELKOMNIKA Indones J Electr Eng 12(4):3068–3077Google Scholar
  24. Melville BW, Chiew YM (1999) Time scale for local scour depth at bridge piers. J Hydraul Eng 125(1):59–65. doi: 10.1061/(ASCE)0733-9429(1999)125:1(59) CrossRefGoogle Scholar
  25. Melville BW, Sutherland AJ (1988) Design method for local scour at bridge piers. J Hydraul Eng 114(10):1210–1226. doi: 10.1061/(ASCE)0733-9429(1988)114:10(1210) CrossRefGoogle Scholar
  26. Mohammadpour R, Shaharuddin S, Chang CK, Zakaria NA, Ghani AA, Chan NW (2014) Prediction of water quality index in constructed wetlands using support vector machine. Environ Sci Pollut Res 22(2):6208–6219. doi: 10.1007/s11356-014-3806-7 Google Scholar
  27. Mohammadpour R, Ghani AA, Vakili M, Sabzevari T (2016) Prediction of temporal scour hazard at bridge abutment. Nat Hazards 80(3):1891–1911. doi: 10.1007/s11069-015-2044-8 CrossRefGoogle Scholar
  28. Mohammed TH, Noor MJMM, Ghazali AH, Huat BBK (2005) Validation of some bridge pier scour formulate using field and laboratory data. Am J Environ Sci 1(2):119–125. doi: 10.3844/ajessp.2005.119.125 CrossRefGoogle Scholar
  29. Najafzadeh M, Lim SY (2015) Application of improved neuro-fuzzy GMDH to predict scour depth at sluice gates. Earth Sci Inform 8(1):187–196. doi: 10.1007/s12145-014-0144-8 CrossRefGoogle Scholar
  30. Najafzadeh M, Sattar AM (2015) Neuro-fuzzy GMDH approach to predict longitudinal dispersion in water networks. Water Resour Manag 29(7):2205–2219. doi: 10.1007/s11269-015-0936-8 CrossRefGoogle Scholar
  31. Najafzadeh M, Barani GA, Hessami Kermani MR (2013) Abutment scour in clear-water and live-bed conditions by GMDH network. Water Sci Technol 67(5):1121–1128. doi: 10.2166/wst.2013.670 CrossRefGoogle Scholar
  32. Najafzadeh M, Barani GA, Hessami Kermani MR (2014) Estimation of pipeline scour due to waves by GMDH. J Pipeline Syst Eng Pract 5(3):06014002. doi: 10.1061/(ASCE)PS.1949-1204.0000171 CrossRefGoogle Scholar
  33. Nguyen PKT, Chua LHC, Son LH (2014) Flood forecasting in large rivers with data-driven models. Nat Hazards 71(1):767–784. doi: 10.1007/s11069-013-0920-7 CrossRefGoogle Scholar
  34. Pearson K (1895) Notes on regression and inheritance in the case of two parents. Proc R Soc Lond 58:240–242CrossRefGoogle Scholar
  35. Rahman MM, Antani SK, Thoma GR (2011) A learning-based similarity fusion and filtering approach for biomedical image retrieval using SVM classification and relevance feedback. IEEE Trans Inf Technol Biomed 15(4):640–646. doi: 10.1109/TITB.2011.2151258 CrossRefGoogle Scholar
  36. Richardson EV, Davis SR (2001) Evaluating scour at bridges, hydraulic engineering circular no. 18 (HEC-18). US Department of Transportation, Federal Highway, USAGoogle Scholar
  37. Samadi M, Jabbari E, Azamathulla HM (2014) Assessment of M5′ model tree and classification and regression trees for prediction of scour depth below free overfall spillways. Neural Comput Appl 24(2):357–366. doi: 10.1007/s00521-012-1230-9 CrossRefGoogle Scholar
  38. Sathiya S, Balasubramanian M, Palanivel S (2014) Pattern recognition based detection recognition of traffic sign using SVM. Int J Eng Technol 6(2):1147–1157Google Scholar
  39. Sattar AM (2014a) Gene expression models for the prediction of longitudinal dispersion coefficients in transitional and turbulent pipe flow. J Pipeline Syst Eng Pract 5(1):04013011. doi: 10.1061/(ASCE)PS.1949-1204.0000153 CrossRefGoogle Scholar
  40. Sattar AM (2014b) Gene expression models for prediction of dam breach parameters. J Hydroinform 16(3):550–571. doi: 10.2166/hydro.2013.084 CrossRefGoogle Scholar
  41. Sattar AM, Gharabaghi B (2015) Gene expression models for prediction of longitudinal dispersion coefficient in streams. J Hydrol 524:587–596. doi: 10.1016/j.jhydrol.2015.03.016 CrossRefGoogle Scholar
  42. Shen HW, Schneider VR, Karaki S (1969) Local scour around bridge piers. J Hydraul Div 95(6):1919–1940Google Scholar
  43. Smola AJ (1996) Regression estimation with support vector learning machines. Ph.D. Thesis, Technical University of Munich, Munich, GermanyGoogle Scholar
  44. Štěpnička M, Cortez DonateJP, Štěpničková L (2013) Forecasting seasonal time series with computational intelligence: on recent methods and the potential of their combinations. Expert Syst Appl 40(6):1981–1992. doi: 10.1016/j.eswa.2012.10.001 CrossRefGoogle Scholar
  45. Sun Y, Tang D, Sun Y, Cui Q (2016) Comparison of a fuzzy control and the data-driven model for flood forecasting. Nat Hazards. doi: 10.1007/s11069-016-2220-5 Google Scholar
  46. Tang Y, Zhang YQ, Chawla NV, Krasser S (2009) SVMs modeling for highly imbalanced classification. IEEE Trans Syst Man Cybern 39(1):281–288. doi: 10.1109/TSMCB.2008.2002909 CrossRefGoogle Scholar
  47. Thompson J, Sattar AM, Gharabaghi B, Richard W (2016) Event based total suspended sediment particle size distribution model. J Hydrol 536:236–246. doi: 10.1016/j.jhydrol.2016.02.056 CrossRefGoogle Scholar
  48. Tsai AC, Luh JJ, Lin TT (2015) A novel STFT-ranking feature of multi-channel EMG for motion pattern recognition. Expert Syst Appl 42(7):3327–3341. doi: 10.1016/j.eswa.2014.11.044 CrossRefGoogle Scholar
  49. Vapnik V (2000) The nature of statistical learning theory. Springer, BerlinCrossRefGoogle Scholar
  50. You SH, Seo JW (2009) Storm surge prediction using an artificial neural network model and cluster analysis. Nat Hazards 51(1):97–114. doi: 10.1007/s11069-009-9396-x CrossRefGoogle Scholar
  51. Zaji AH, Bonakdari H (2015) Efficient methods for prediction of velocity fields in open channel junctions based on the artificial neural network. Eng Appl Comput Fluid Mech 9(1):220–232. doi: 10.1080/19942060.2015.1004821 Google Scholar
  52. Zounemat-Kermani M, Beheshti AA, Ataie-Ashtiani B, Sabbagh-Yazdi SR (2009) Estimation of current-induced scour depth around pile groups using neural network and adaptive neuro-fuzzy inference system. Appl Soft Comput 9(2):746–755. doi: 10.1016/j.asoc.2008.09.006 CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2016

Authors and Affiliations

  • Hassan Sharafi
    • 1
  • Isa Ebtehaj
    • 1
  • Hossein Bonakdari
    • 1
  • Amir Hossein Zaji
    • 1
  1. 1.Department of Civil EngineeringRazi UniversityKermanshahIran

Personalised recommendations