A Hybrid GMDH Neural Network-Genetic Algorithm Approach for Predicting Shear Wave Velocity Profiles

Document Type : Original Article

Author

Department of Geography and Urban Planning, University of Mazandaran, Babolsar, Iran

Abstract

Shear wave velocity (Vs) is a fundamental parameter in geotechnical earthquake engineering and seismic site characterization; however, direct in-situ measurement remains expensive and spatially limited. This study proposes an interpretable hybrid group method of data handling-genetic algorithm (GMDH-GA) framework for predicting shear wave velocity profiles in heterogeneous alluvial deposits. A comprehensive geotechnical-geophysical database comprising 1991 records from 226 boreholes in Mashhad, Iran, was compiled using downhole measurements and standard penetration test (SPT) data. Depth (Z), SPT blow count (N), and upper-layer shear wave velocity (Vsu) were selected as predictor variables. Separate soil-specific models were developed for clay, silt, sand, gravel, and combined soil datasets using a 70/30 training-testing strategy. The proposed models generated explicit polynomial equations while maintaining high predictive capability. Statistical evaluation demonstrated strong agreement between measured and predicted Vs values, with testing-stage coefficients of determination reaching 0.98-0.99 and low prediction errors across all soil groups. Comparative analyses showed that the proposed GMDH-GA models substantially outperform widely used empirical correlations in terms of accuracy and generalization capability. Sensitivity analysis indicated that Vsu is the dominant predictor, followed by SPT resistance and depth. The results demonstrate that the proposed framework provides a reliable and interpretable alternative for estimating shear wave velocity profiles in regions where direct geophysical measurements are unavailable.

Keywords

Main Subjects

References

  1. Ohta, Y., Goto, N. Empirical shear wave velocity equations in terms of characteristic soil indexes. Earthquake Engineering & Structural Dynamics, 1978; 6: 167–187. doi:10.1002/eqe.4290060205.
  2. Imai, T., Tonouchi, K. Correlation of N-value with S-wave velocity and shear modulus. In: Proceedings of the 2nd European Symposium on Penetration Testing (ESOPT II); 1982 May 24‒27; Amsterdam, Netherlands. p. 67–72.
  3. Seed, H. B., Idriss, I. M., Arango, I. Evaluation of Liquefaction Potential Using Field Performance Data. Journal of Geotechnical Engineering, 1983; 109: 458–482. doi:10.1061/(ASCE)0733-9410(1983)109:3(458).
  4. Sykora, D. E., H., S. K. Correlations of in-situ measurements in sands of shear wave velocity with standard penetration test resistance. Geotechnical Testing Journal, 1983; 6: 107–114. doi:10.1520/GTJ10700J.
  5. Jafari, M. K., Asghari, A., Rahmani, I. Empirical correlation between shear wave velocity (Vs) and SPT-N value for south of Tehran soils. In: Proceedings of 4th International Conference on Civil Engineering; 1997 May 04‒06; Tehran, Iran.
  6. Ohsaki, Y., Iwasaki, R. On Dynamic Shear Moduli and Poisson’s Ratio of Soil Deposits. Soils and Foundations. Soils and Foundations, 1973; 13: 61–73. doi:10.3208/sandf1972.13.4_61.
  7. Imai, T. P- and S-Wave Velocities of the Ground in Japan. In: 9th International Conference on Soil Mechanics and Foundation Engineering; 1977 Jul 10‒15; Tokyo, Japan. p. 257–260.
  8. Seed, H. B., Idriss, I. M. Evaluation of Liquefaction Potential Sand Deposits Based on Observation of Performance in Previous Earthquakes. ASCE National Convention (MO), 481-544.
  9. Lee Shannon, H.-H. Analysis of the multicollinearity of regression equations of shear wave velocities. Soils and Foundations, 1992; 32: 205–214. doi:10.3208/sandf1972.32.205.
  10. Iyisan, R. Correlations between shear wave velocity and in-situ penetration test results. Teknik Dergi-tmmob Insaat Muhendisleri Odas, 1996; 7: 371–374.
  11. Hasancebi, N., Ulusay, R. Empirical correlations between shear wave velocity and penetration resistance for ground shaking assessments. Bulletin of Engineering Geology and the Environment, 2007; 66: 203–213. doi:10.1007/s10064-006-0063-0.
  12. Dikmen, Ü. Statistical correlations of shear wave velocity and penetration resistance for soils. Journal of Geophysics and Engineering, 2009; 6: 61. doi:10.1088/1742-2132/6/1/007.
  13. Maheswari, R. U., Boominathan, A., Dodagoudar, G. R. Use of Surface Waves in Statistical Correlations of Shear Wave Velocity and Penetration Resistance of Chennai Soils. Geotechnical and Geological Engineering, 2010; 28: 119–137. doi:10.1007/s10706-009-9285-9.
  14. Hafezi, M. N., Azadi, A., Amanian, M. Assessment of shear wave velocity based on standard penetration and accuracy of the results in the range of Mashhad City. In: Fourteenth Conference of Iran Geophysics, Geophysical Institute (in Persian); 2010 May 13; Tehran, Iran.
  15. Chatterjee, K., Choudhury, D. Variations in shear wave velocity and soil site class in Kolkata city using regression and sensitivity analysis. Natural Hazards, 2013; 69: 2057–2082. doi:10.1007/s11069-013-0795-7.
  16. Fatehnia, M., Hayden, M., Landschoot, M. Correlation between Shear Wave Velocity and SPT-N Values for North Florida Soils. Electronic Journal of Geotechnical Engineering, 2015; 20: 12421–12430.
  17. Kirar, B., Maheshwari, B. K., Muley, P. Correlation Between Shear Wave Velocity (Vs) and SPT Resistance (N) for Roorkee Region. International Journal of Geosynthetics and Ground Engineering, 2016; 2: 9. doi:10.1007/s40891-016-0047-5.
  18. Sarkar, A., Mazumdar, A., Bhowmik, D. Application of Soft Computing Techniques for Prediction of Seismic Wave Velocity. In: 9th International Conference on Control, Decision and Information Technologies (CoDIT); 2023 Jul 03‒06; Rome, Italy. p. 2532–2537. doi:10.1109/CoDIT58514.2023.10284120.
  19. Mousavi, Z., Bayat, M., Yang, J., Feng, W.-Q. Evaluation of empirical and machine learning models for predicting shear wave velocity of granular soils based on laboratory element tests. Soil Dynamics and Earthquake Engineering, 2024; 183: 108805. doi:10.1016/j.soildyn.2024.108805.
  20. Jin, L., Fuggle, A., Roberts, H., Armstrong, C., Pua, L.-M. Estimating In Situ Shear Wave Velocity Using Machine Learning Techniques. In: Geo-Congress 2024; 2024 Feb 25‒28; Vancouver, Canada. p. 436–444. doi:10.1061/9780784485347.044.
  21. Joshi, A., Raman, B., Mohan, C. K., Cenkeramaddi, L. R. A new machine learning approach for estimating shear wave velocity profile using borelog data. Soil Dynamics and Earthquake Engineering, 2024; 177: 108424. doi:10.1016/j.soildyn.2023.108424.
  22. Zhong, K., Tan, X., Liu, S., Lu, Z., Hou, X., Wang, Q. Prediction of slope failure probability based on machine learning with genetic-ADASYN algorithm. Engineering Geology, 2025; 346: 107885. doi:10.1016/j.enggeo.2024.107885.
  23. Tabari, M. M. R., Azari, T., Dehghan, V. A supervised committee neural network for the determination of aquifer parameters: a case study of Katasbes aquifer in Shiraz plain, Iran. Soft Computing, 2021; 25: 4785–4798. doi:10.1007/s00500-020-05487-2.
  24. Farahani, S. A Data-Driven Seismic Design Framework for RC Frames Using Wavelet Transforms and Machine Learning. Civil Engineering and Applied Solutions, 2027; 3: 1–24. doi:10.22080/ceas.2026.30950.1073.
  25. Sadeghpour Haji, M., Niknam, R., Shayanfar, J. ANN-Based Modeling of Shear Behavior of Reinforced Concrete Columns under Constant Axial Loads. Civil Engineering and Applied Solutions, 2026; 2: 28–48. doi:10.22080/ceas.2025.30228.1050.
  26. Ivakhnenko, A. G. Polynomial Theory of Complex Systems. IEEE Transactions on Systems, Man, and Cybernetics, 1971; SMC-1: 364–378. doi:10.1109/TSMC.1971.4308320.
  27. Gandomi, A. H., Roke, D. A. Assessment of artificial neural network and genetic programming as predictive tools. Advances in Engineering Software, 2015; 88: 63–72. doi:10.1016/j.advengsoft.2015.05.007.
  28. MolaAbasi, H., Khajeh, A., Jamshidi Chenari, R. Use of GMDH-type neural network to model the mechanical behavior of a cement-treated sand. Neural Computing and Applications, 2021; 33: 15305–15318. doi:10.1007/s00521-021-06157-6.
  29. Kordnaeij, A., Kalantary, F., Kordtabar, B., Mola-Abasi, H. Prediction of recompression index using GMDH-type neural network based on geotechnical soil properties. Soils and Foundations, 2015; 55: 1335–1345. doi:10.1016/j.sandf.2015.10.001.
  30. Kalantary, F., Ardalan, H., Nariman-Zadeh, N. An investigation on the Su–NSPT correlation using GMDH type neural networks and genetic algorithms. Engineering Geology, 2009; 104: 144–155. doi:10.1016/j.enggeo.2008.09.006.
  31. MolaAbasi, H., Saberian, M., Kordnaeij, A., Omer, J., Li, J., Kharazmi, P. Predicting the stress-strain behaviour of zeolite-cemented sand based on the unconfined compression test using GMDH type neural network. Journal of Adhesion Science and Technology, 2019; 33: 945–962. doi:10.1080/01694243.2019.1571659.
  32. Farrokhi, F., Firoozfar, A., Maghsoudi, M. S. Evaluation of liquefaction-induced lateral displacement using a GMDH-type neural network optimized by genetic algorithm. Arabian Journal of Geosciences, 2019; 13: 4. doi:10.1007/s12517-019-4980-1.
  33. Javdanian, H., Heidari, A., Kamgar, R. Energy-Based Estimation of Soil Liquefaction Potential Using GMDH Algorithm. Iranian Journal of Science and Technology, Transactions of Civil Engineering, 2017; 41: 283–295. doi:10.1007/s40996-017-0061-4.
  34. Building & housing research center (BHRC). standard No. 2800: Iranian code of practice for seismic resistant design of buildings. Tehran (IR): BHRC; 2007 (in Persian).
  35. Koopialipoor, M., Armaghani, D. J., Hedayat, A., Marto, A., Gordan, B. Applying various hybrid intelligent systems to evaluate and predict slope stability under static and dynamic conditions. Soft Computing, 2019; 23: 5913–5929. doi:10.1007/s00500-018-3253-3.
  36. Nguyen, M. D., Costache, R., Sy, A. H., Ahmadzadeh, H., Van Le, H., Prakash, I., Pham, B. T. Novel approach for soil classification using machine learning methods. Bulletin of Engineering Geology and the Environment, 2022; 81: 468. doi:10.1007/s10064-022-02967-7.
  37. Jiawei, H., Micheline, K., Jian, P. Data mining: Concepts and techniques. Waltham: Morgan Kaufmann; 2006. p. 559–569.
  38. Lee, S., Kim, J., Kang, H., Kang, D.-Y., Park, J. Genetic algorithm based deep learning neural network structure and hyperparameter optimization. Applied Sciences, 2021; 11: 744. doi:10.3390/app11020744.
  39. Kumar, A., Satyannarayana, R., Rajesh, B. G. Correlation between SPT-N and shear wave velocity (VS) and seismic site classification for Amaravati city, India. Journal of Applied Geophysics, 2022; 205: 104757. doi:10.1016/j.jappgeo.2022.104757.
  40. Daag, S., Halasan, O. P., Magnaye, A., Grutas, R., Solidum, R. Empirical Correlation between Standard Penetration Resistance (SPT-N) and Shear Wave Velocity (Vs) for Soils in Metro Manila, Philippines. Applied Sciences, 2022; 12: 8067. doi:10.3390/app12168067.
  41. Cheng, J., Sun, J., Yao, K., Xu, M., Cao, Y. A variable selection method based on mutual information and variance inflation factor. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2022; 268: 120652. doi:10.1016/j.saa.2021.120652.
  42. Sugiyama, M. Introduction to Statistical Machine Learning. 1st ed. Waltham (MA): Morgan Kaufmann; 2016. doi:10.1016/B978-0-12-802121-7.00012-1.
  43. Ivakhnenko, A., Müller, J. A. Self-organization of nets of active neurons. Systems Analysis Modelling Simulation, 1995; 20: 93–106.
  44. Madala, H. R. Inductive Learning Algorithms for Complex Systems Modeling. 1st ed. Boca Raton (FL): CRC Press; 1993. doi:10.1201/9781351073493.
  45. Lemke, F., Müller, J. A. Self-Organising Data Mining. Systems Analysis Modelling Simulation, 2003; 43: 231–240. doi:10.1080/0232929031000136135.
  46. Taheri, A., Makarian, E., Manaman, N. S., Ju, H., Kim, T.-H., Geem, Z. W., RahimiZadeh, K. A Fully-Self-Adaptive Harmony Search GMDH-Type Neural Network Algorithm to Estimate Shear-Wave Velocity in Porous Media. Applied Sciences, 2022; 12: 6339. doi:10.3390/app12136339.
  47. Katoch, S., Chauhan, S. S., Kumar, V. A review on genetic algorithm: past, present, and future. Multimedia Tools and Applications, 2021; 80: 8091–8126. doi:10.1007/s11042-020-10139-6.
  48. Hastie, T., Tibshirani, R., Friedman, J. The Elements of Statistical Learning. 2nd ed. New York (NY): Springer; 2009. doi:10.1007/978-0-387-84858-7.
  49. Arlot, S., Celisse, A. A survey of cross-validation procedures for model selection. Statistics Surveys, 2010; 4: 40–79. doi:10.1214/09-SS054.
  50. Chai, T., Draxler, R. R. Root mean square error (RMSE) or mean absolute error (MAE)?– Arguments against avoiding RMSE in the literature. Geoscientific Model Development, 2014; 7: 1247–1250. doi:10.5194/gmd-7-1247-2014.
  51. Botchkarev, A. Performance Metrics (Error Measures) in Machine Learning Regression, Forecasting and Prognostics: Properties and Typology. Interdisciplinary Journal of Information, Knowledge, and Management, 2019; 14: 45–76. doi:10.28945/4184.
  52. Asteris, P. G., Rizal, F. I., Koopialipoor, M., Roussis, P. C., Ferentinou, M., Armaghani, D. J., Gordan, B. Slope Stability Classification under Seismic Conditions Using Several Tree-Based Intelligent Techniques. Applied Sciences, 2022; 12: 1753. doi:10.3390/app12031753.
  53. Onyelowe, K. C., Mojtahedi, F. F., Ebid, A. M., Rezaei, A., Osinubi, K. J., Eberemu, A. O., Salahudeen, B., Gadzama, E. W., Rezazadeh, D., Jahangir, H., Yohanna, P., Onyia, M. E., Jalal, F. E., Iqbal, M., Ikpa, C., Obianyo, I. I., Rehman, Z. U. Selected AI optimization techniques and applications in geotechnical engineering. Cogent Engineering, 2023; 10: 2153419. doi:10.1080/23311916.2022.2153419.
  54. Jolfaei, S., Lakirouhani, A. Sensitivity analysis of effective parameters in borehole failure, using neural network. Advances in Civil Engineering, 2022; 2022: 4958004. doi:10.1155/2022/4958004.
Civil Engineering and Applied Solutions
Volume 3, Issue 2
April 2027
Pages 144-160

Files

History

  • Receive Date: 12 May 2026
  • Revise Date: 16 June 2026
  • Accept Date: 07 August 2026
  • First Publish Date: 28 August 2026

Share

How to cite

Statistics