Improving prediction of soil liquefaction using hybrid optimization algorithms and a fuzzy support vector machine

  • Alireza Rahbarzare
  • Mohammad AzadiEmail author
Original Paper


The phenomenon of soil liquefaction is one of the most complex and interesting fields in geotechnical earthquakes that has drawn the attention of many researchers in recent years. The present study used hybrid particle swarm optimization and genetic algorithms with a fuzzy support vector machine (FSVM) as the classifier for the soil liquefaction prediction problem. Fuzzy logic is used to decrease the outlier sensitivity of the system by inferring the importance of each sample in the training phase to increase the ability of the classifier’s generalization. Using the appropriate combination of optimization algorithms, we can find the best parameters for the classifier during the training phase without the need for trial and error by the user due to the high accuracy of the classifier. The proposed approach was tested on 109 CPT-based field data from five major earthquakes between 1964 and 1983 recorded in Japan, China, the USA and Romania. Good results have been demonstrated for the proposed algorithm. Classification accuracy is 100% for the combination of the optimization algorithms with the FSVM classifier. The results show that the best kernel used in the training of the FSVM classifier is a radial basis function (RBF). According to the experimental results, the proposed algorithm can improve classification accuracy and that it is a feasible method for predicting soil liquefaction using the optimal parameters of the classifier with no user interface.


Soil liquefaction FSVM Genetic algorithm PSO 


  1. Hosseini, Majd al. (2010) Soil dynamic, International society of Seismology and Earthquake Engineering. Iran (in Persian)Google Scholar
  2. Ardakani A, Kohestani VR (2015) Evaluation of liquefaction potential based on CPT results using C4. 5 decision tree. J AI Data Min 3(1):85–92Google Scholar
  3. Avci E (2009) Selecting of the optimal feature subset and kernel parameters in digital modulation classification by using hybrid genetic algorithm–support vector machines: HGASVM. Expert Syst Appl 36(2):1391–1402CrossRefGoogle Scholar
  4. Boyd R, Richerson PJ (1988) Culture and the evolutionary process. University of Chicago pressGoogle Scholar
  5. Burges CJ (1998) A tutorial on support vector machines for pattern recognition. Data Min Knowl Disc 2(2):121–167CrossRefGoogle Scholar
  6. Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297Google Scholar
  7. Das SK, Muduli PK (2011) Evaluation of liquefaction potential of soil using genetic programming. In Proceedings of the Golden Jubilee Indian Geotechnical Conference, Kochi, India (Vol. 2, pp. 827–830)Google Scholar
  8. Dobry R (1985) Liquefaction of soils during earthquakes, National Research Council (NRC), Committee on Earthquake Engineering. Report No. CETS-EE-001. Washington, DC: National Academy PressGoogle Scholar
  9. Dobry R, Ladd RS, Yokel FY, Chung RM, Powell D (1982) Prediction of pore water pressure buildup and liquefaction of sands during earthquakes by the cyclic strain method, vol. 138. Gaithersburg: National Bureau of StandardsGoogle Scholar
  10. Du S, Li W, Cao K (2006) A learning algorithm of artificial neural network based on GA-PSO. In Intelligent Control and Automation, 2006. WCICA 2006. The Sixth World Congress on (Vol. 1, pp. 3633–3637). IEEEGoogle Scholar
  11. Eberhart R, Kennedy J (1995) A new optimizer using particle swarm theory. In Micro Machine and Human Science, 1995. MHS’95. Proceedings of the Sixth International Symposium on (pp. 39–43). IEEEGoogle Scholar
  12. Filali K, Sbartai B (2017) A comparative study between simplified and nonlinear dynamic methods for estimating liquefaction potential. Journal of Rock Mechanics and Geotechnical Engineering. 955–966Google Scholar
  13. Goh AT (1996) Neural-network modeling of CPT seismic liquefaction data. J Geotech Eng 122(1):70–73CrossRefGoogle Scholar
  14. Goh AT, Zhang WG (2014) An improvement to MLR model for predicting liquefaction-induced lateral spread using multivariate adaptive regression splines. Eng Geol 170:1–0Google Scholar
  15. Goh AT, Zhang Y, Zhang R, Zhang W, Xiao Y (2017) Evaluating stability of underground entry-type excavations using multivariate adaptive regression splines and logistic regression. Tunn Undergr Space Technol 1(70):148–154CrossRefGoogle Scholar
  16. Goharzay M, Noorzad A, Ardakani AM, Jalal M (2017a) A worldwide SPT-based soil liquefaction triggering analysis utilizing gene expression programming and Bayesian probabilistic method. J Rock Mech Geotech Eng 9(4):683–693CrossRefGoogle Scholar
  17. Goharzay M, Noorzad A, Ardakani AM, Jalal M (2017b) A worldwide SPT-based soil liquefaction triggering analysis utilizing gene expression programming and Bayesian probabilistic method. J Rock Mech Geotech Eng 9(4):683–693CrossRefGoogle Scholar
  18. Green RA, Mitchell JK (2004) Energy-based evaluation and remediation of liquefiable soils. In Geotechnical engineering for transportation projects, pp 1961–1970Google Scholar
  19. Han J, Pei J, Kamber M (2011) Data mining: concepts and techniques. Elsevier.(book)Google Scholar
  20. 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):521–540CrossRefGoogle Scholar
  21. Hu JL, Tang XW, Qiu JN (2016) Assessment of seismic liquefaction potential based on Bayesian network constructed from domain knowledge and history data. Soil Dyn Earthq Eng 89:49–60CrossRefGoogle Scholar
  22. Idriss IM, Boulanger RW (2010) SPT-based liquefaction triggering procedures. Rep. UCD/CGM-10, 2Google Scholar
  23. Ishihara K (1996) Soil Behavior in Earthquake Geotechnics Oxford Science Publication UKGoogle Scholar
  24. Javdanian H, Heidari A, Kamgar R (2017) Energy-based estimation of soil liquefaction potential using GMDH algorithm. Iranian journal of science and technology, transactions of. Civ Eng 41(3):283–295Google Scholar
  25. Jha SK, Suzuki K (2009) Reliability analysis of soil liquefaction based on standard penetration test. Comput Geotech 36(4):589–596CrossRefGoogle Scholar
  26. Juang CF (2004) A hybrid of genetic algorithm and particle swarm optimization for recurrent network design. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) 34(2):997–1006CrossRefGoogle Scholar
  27. Juang CH, Ching J, Luo Z, Ku CS (2012) New models for probability of liquefaction using standard penetration tests based on an updated database of case histories. Eng Geol 133:85–93CrossRefGoogle Scholar
  28. Kaboodiyan J, Moradi MH (2004) A new fuzzy support vector machine with two step of fuzzyfication, Proc 12th conference of electrical engineering , Ferdosi Mashhad university, Iran. (in persian)Google Scholar
  29. Kao YT, Zahara E (2008) A hybrid genetic algorithm and particle swarm optimization for multimodal functions. Appl Soft Comput 8(2):849–857CrossRefGoogle Scholar
  30. Karimy M, Haery M (1999) The use of neural networks in the evaluation of liquefaction potential. Third International Conference on seismology and Earthquake Engineering 173–184, Tehran, I. R. Iran (in Persian) Google Scholar
  31. Kayadelen C (2011) Soil liquefaction modeling by genetic expression programming and neuro-fuzzy. Expert Syst Appl 38(4):4080–4087CrossRefGoogle Scholar
  32. Kennedy J, Eberhart RC (1997) A discrete binary version of the particle swarm algorithm. In Systems, Man, and Cybernetics, 1997. Computational Cybernetics and Simulation. 1997 IEEE International Conference on (Vol. 5, pp. 4104–4108). IEEEGoogle Scholar
  33. Keshavarz A, Nourozi Mohamad J (2013) Evaluation of soil liquefaction potential , using the results of standard penetration test by Gene Expression Programming , first national conference on geotechnique Engineering,Ardebil,Iran, (in Persian)Google Scholar
  34. Lin CF, Wang SD (2002) Fuzzy support vector machines. IEEE Trans Neural Netw 13(2):464–471CrossRefGoogle Scholar
  35. Ornek M (2014) Estimation of ultimate loads of eccentric-inclined loaded strip footings rested on sandy soils. Neural Comput Applic 25(1):39–54CrossRefGoogle Scholar
  36. Rezania M, Javadi AA (2007) A new genetic programming model for predicting settlement of shallow foundations. Can Geotech J 44(12):1462–1473CrossRefGoogle Scholar
  37. Robinson J, Sinton S, Rahmat-Samii Y (2002) Particle swarm, genetic algorithm, and their hybrids: optimization of a profiled corrugated horn antenna. In Antennas and Propagation Society International Symposium, 2002. IEEE (Vol. 1, pp. 314–317). IEEEGoogle Scholar
  38. Sabbar AS, Chegenizadeh A, Nikraz H (2017) Prediction of Liquefaction Susceptibility of Clean Sandy Soils Using Artificial Intelligence Techniques. Indian Geotechn J 1–12Google Scholar
  39. Seed HB, Idriss IM (1971) Simplified procedure for evaluating soil liquefaction potential. J Soil Mech Found DivGoogle Scholar
  40. Trifunac MD, Todorovska MI (2004) Maximum distance and minimum energy to initiate liquefaction in water saturated sands. Soil Dyn Earthq Eng 24(2):89–101CrossRefGoogle Scholar
  41. Xue X, Xiao M (2016) Application of genetic algorithm-based support vector machines for prediction of soil liquefaction. Environmental Earth Sciences 75(10):874CrossRefGoogle Scholar
  42. Xue X, Yang X (2016) Seismic liquefaction potential assessed by support vector machines approaches. Bull Eng Geol Environ 75(1):153–162CrossRefGoogle Scholar
  43. Xue X, Yang X, Li P (2017) Application of a probabilistic neural network for liquefaction assessment. Neural Network World 27(6):557–567CrossRefGoogle Scholar
  44. Yilmaz I, Marschalko M, Bednarik M, Kaynar O, Fojtova L (2012) Neural computing models for prediction of permeability coefficient of coarse-grained soils. Neural Comput Applic 21(5):957–968CrossRefGoogle Scholar
  45. Zhang W, Goh AT (2013) Multivariate adaptive regression splines for analysis of geotechnical engineering systems. Comput Geotech 48:82–95CrossRefGoogle Scholar
  46. Zhang W , Goh AT ( 2016a ) Evaluating seismic liquefaction potential using multivariate adaptive regression splines and logistic regression. Geomech Eng 10(3):269–80Google Scholar
  47. Zhang W, Goh AT (2016b) Multivariate adaptive regression splines and neural network models for prediction of pile drivability. Geosci Front 7(1):45–52Google Scholar
  48. Zhang W, Goh AT, Zhang Y, Chen Y, Xiao Y (2015) Assessment of soil liquefaction based on capacity energy concept and multivariate adaptive regression splines. Engineering Geology 7 188:29–37CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Department of Civil Engineering, Qazvin BranchIslamic Azad UniversityQazvinIran

Personalised recommendations