A Deep Learning–Enhanced Framework for Predicting Lique-faction Susceptibility of Sandy Soils Using SPT-Based Geotech-nical Data
الموضوعات : Soil-Structure Interaction
shima aghakasiri
1
,
ghodratollah mohammadi
2
,
amir taban
3
,
mohammad emami kourandeh
4
1 - Department of Civil Engineering, ST.C , Islamic Azad University, Teharn, Iran.
2 - Department of Civil Engineering, S.T.C., Islamic Azad University, Tehran, Iran
3 - 3 Department of Civil Engineering, KH.A.C, Islamic Azad University, Khorramabad (Iran)
4 - Department of Civil Engineering, S.T.C., Islamic Azad University, Tehran, Iran.
الکلمات المفتاحية: Liquefaction, Deep Learning, CNN–MVO, SPT, Geotechnical Engineering, Soft Computing.,
ملخص المقالة :
Soil liquefaction remains one of the most critical challenges in geotechnical earthquake engineering, often resulting in severe ground deformation, settlement, and infrastructure failure during strong seismic events. Traditional empirical methods, while widely used, are limited in their ability to capture the nonlinear and complex interactions among soil parameters. This study introduces a hybrid deep learning framework based on a Convolutional Neural Network (CNN) optimized using the Multi-Verse Optimizer (MVO) to predict liquefaction potential and post-liquefaction settlement. A comprehensive geotechnical database consisting of 300 borehole records from the northern provinces of Iran—including SPT data, groundwater level, soil type, fine content, and liquefiable depth—was used for model training and evaluation. The hybrid CNN–MVO model demonstrated high predictive capability, achieving regression coefficients exceeding 90% and Mean Squared Error (MSE) values below 0.5 across training, testing, and validation sets. Sensitivity analysis revealed that fine content (FP) had the strongest influence on liquefaction potential, followed by SPT-N and soil type. The results confirm that combining CNN with MVO significantly enhances model accuracy and parameter interpretability, offering a robust alternative to traditional liquefaction assessment methods. The proposed model can support engineers in developing more reliable seismic risk evaluations and mitigation strategies in liquefaction-prone regions.
Bahrainy, H. and A. Bakhtiar, Manjil Earthquake of June 20, 1990, The Lessons Learned, in Urban Design in Seismic-Prone Regions. 2022, Springer International Publishing: Cham. p. 49-95.
2. Uyanık, O., Soil liquefaction analysis based on soil and earthquake parameters. Journal of applied geophysics, 2020. 176: p. 104004.
3. Matsuoka, M., et al., Evaluation of liquefaction potential for large areas based on geomorphologic classification. Earthquake Spectra, 2015. 31(4): p. 2375-2395.
4. Kia Darbandsari, S. and A. Hojatkashani, A critical review on structure-soil-structure interaction. Journal of Structural Engineering and Geo-Techniques, 2018. 8(2): p. 57-68.
5. Hassani, R., A. Hojatkashani, and R. Basirat, Nonlinear seismic analysis of ground structure to evaluate the capacity of a permanent tunnel lining. Structural Engineering International, 2024. 34(1): p. 102-113.
6. Kherad, S., M. Hosseini, and A. Hojatkashani, Seismic Performance of Low Rise Buildings with Elastic Materials Energy Absorbing System at the Foundation. 2018.
7. Kumar, D.R., et al., Liquefaction susceptibility using machine learning based on SPT data. Intelligent Systems with Applications, 2023. 20: p. 200281.
8. Zhang, Y., et al., The adoption of deep neural network (DNN) to the prediction of soil liquefaction based on shear wave velocity. Bulletin of Engineering Geology and the Environment, 2021. 80(6): p. 5053-5060.
9. Ahmad, M., et al., Application of machine learning algorithms for the evaluation of seismic soil liquefaction potential. Frontiers of Structural and Civil Engineering, 2021. 15(2): p. 490-505.
10. Geyin, M. and B.W. Maurer, Fragility functions for liquefaction-induced ground failure. Journal of Geotechnical and Geoenvironmental Engineering, 2020. 146(12): p. 04020142.
11. Geyin, M., Evaluation and Development of Liquefaction Occurrence and Consequence Analytics Driven by Emerging Data and Technologies. 2021: University of Washington.
12. Zhou, J., et al., Performance evaluation of hybrid GA–SVM and GWO–SVM models to predict earthquake-induced liquefaction potential of soil: a multi-dataset investigation. Engineering with Computers, 2022. 38(Suppl 5): p. 4197-4215.
13. Zhang, Y., et al., The adoption of a support vector machine optimized by GWO to the prediction of soil liquefaction. Environmental Earth Sciences, 2021. 80(9): p. 360.
14. Choi, Y. and K. Kumar. A machine learning approach to predicting pore pressure response in liquefiable sands under cyclic loading. in Geo-Congress 2023. 2023.
15. Kumar, K., P. Samui, and S. Choudhary, State parameter based liquefaction probability evaluation. International Journal of Geosynthetics and Ground Engineering, 2023. 9(6): p. 76.
16. Bi, C., et al., Machine learning based fast multi-layer liquefaction disaster assessment. World Wide Web, 2019. 22(5): p. 1935-1950.
17. Jas, K. and G. Dodagoudar, Liquefaction potential assessment of soils using machine learning techniques: a state-of-the-art review from 1994–2021. International Journal of Geomechanics, 2023. 23(7): p. 03123002.
18. Li, L., et al., Soil seismic response modeling of KiK-net downhole array sites with CNN and LSTM networks. Engineering Applications of Artificial Intelligence, 2023. 121: p. 105990.
19. Kayen, R., et al., Shear-wave velocity–based probabilistic and deterministic assessment of seismic soil liquefaction potential. Journal of Geotechnical and Geoenvironmental Engineering, 2013. 139(3): p. 407-419.
20. Idriss, I. and R.W. Boulanger, SPT-based liquefaction triggering procedures. Rep. UCD/CGM-10, 2010. 2: p. 4-13.
21. Bhattacharya, S., et al., Liquefaction of soil in the Tokyo Bay area from the 2011 Tohoku (Japan) earthquake. Soil Dynamics and Earthquake Engineering, 2011. 31(11): p. 1618-1628.
22. Robertson, P.K. and C. Wride, Evaluating cyclic liquefaction potential using the cone penetration test. Canadian geotechnical journal, 1998. 35(3): p. 442-459.
23. Seed, H.B. and I.M. Idriss, Simplified procedure for evaluating soil liquefaction potential. Journal of the Soil Mechanics and Foundations division, 1971. 97(9): p. 1249-1273.
24. Maurer, B.W., et al., Evaluation of the liquefaction potential index for assessing liquefaction hazard in Christchurch, New Zealand. Journal of Geotechnical and Geoenvironmental Engineering, 2014. 140(7): p. 04014032.
25. Yang, Y. and E. Kavazanjian, Newmark analysis of lateral spreading induced by liquefaction. Journal of Earthquake Engineering, 2022. 26(6): p. 3034-3053.
26. Zhang, W., et al., A deep learning approach for rapid detection of soil liquefaction using time–frequency images. Soil Dynamics and Earthquake Engineering, 2023. 166: p. 107788.
27. Şehmusoğlu, E.H., T.F. Kurnaz, and C. Erden, Estimation of soil liquefaction using artificial intelligence techniques: an extended comparison between machine and deep learning approaches. Environmental Earth Sciences, 2025. 84(5): p. 1-22.
28. Bai, R., et al., The Analysis of the Correlation between SPT and CPT Based on CNN-GA and Liquefaction Discrimination Research. CMES-Computer Modeling in Engineering & Sciences, 2024. 138(2).
29. Ghani, S., et al., Revealing the nature of soil liquefaction using machine learning. Earth Science Informatics, 2025. 18(2): p. 198.
30. Ghani, S., et al., Soil categorization and liquefaction prediction using deep learning and ensemble learning algorithms. Transportation Infrastructure Geotechnology, 2025. 12(1): p. 22.
31. Chou, J.-S. and T.-B.-Q. Pham, Enhancing soil liquefaction risk assessment with metaheuristics and hybrid learning techniques. Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards, 2024: p. 1-19.
32. Kumar, D.R., P. Samui, and A. Burman, Suitability assessment of the best liquefaction analysis procedure based on SPT data. Multiscale and Multidisciplinary Modeling, Experiments and Design, 2023. 6(2): p. 319-329.
33. Shafiei, P., M. Azadi, and M.S. Razzaghi, A novel liquefaction prediction framework for seismically-excited tunnel lining. Earthquakes and Structures, 2022. 22(4): p. 401-419.
34. Chen, Q., C. Wang, and C.H. Juang, Probabilistic and spatial assessment of liquefaction-induced settlements through multiscale random field models. Engineering Geology, 2016. 211: p. 135-149.
35. Shahir, H., et al., Evaluation of variation of permeability in liquefiable soil under earthquake loading. Computers and Geotechnics, 2012. 40: p. 74-88.
36. Samui, P. and R. Hariharan, A unified classification model for modeling of seismic liquefaction potential of soil based on CPT. Journal of advanced research, 2015. 6(4): p. 587-592.
37. Muduli, P.K. and S.K. Das, Model uncertainty of SPT-based method for evaluation of seismic soil liquefaction potential using multi-gene genetic programming. Soils and Foundations, 2015. 55(2): p. 258-275.
38. Javadi, A.A., T.P. Tan, and A. Elkassas, Intelligent finite element method and application to simulation of behavior of soils under cyclic loading, in Foundations of Computational Intelligence Volume 5: Function Approximation and Classification. 2009, Springer. p. 317-338.
39. Seed, H.B., I.M. Idriss, and I. Arango, Evaluation of liquefaction potential using field performance data. Journal of geotechnical engineering, 1983. 109(3): p. 458-482.
40. Mirjalili, S., S.M. Mirjalili, and A. Hatamlou, Multi-verse optimizer: a nature-inspired algorithm for global optimization. Neural computing and applications, 2016. 27(2): p. 495-513.
41. Ansary, M.A. and M. Ansary, USE OF CPT AND OTHER PARAMETERS FOR ESTIMATING SPT-N VALUE USING OPTIMISED MACHINE LEARNING MODELS. Journal of GeoEngineering, 2024. 19(2).
42. Chithuloori, P. and J.-M. Kim, Soft voting ensemble classifier for liquefaction prediction based on SPT data. Artificial Intelligence Review, 2025. 58(8): p. 228.
