Geomechanics and Engineering

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Prediction of dynamic soil properties coupled with machine learning algorithms

  • Dae-Hong Min (Department of Construction and Disaster Prevention Engineering, Daejeon University) ;
  • Hyung-Koo Yoon (Department of Construction and Disaster Prevention Engineering, Daejeon University)
  • Received : 2024.03.09
  • Accepted : 2024.04.19
  • Published : 2024.05.10
⟨ Previous Next ⟩

Abstract

Dynamic properties are pivotal in soil analysis, yet their experimental determination is hampered by complex methodologies and the need for costly equipment. This study aims to predict dynamic soil properties using static properties that are relatively easier to obtain, employing machine learning techniques. The static properties considered include soil cohesion, friction angle, water content, specific gravity, and compressional strength. In contrast, the dynamic properties of interest are the velocities of compressional and shear waves. Data for this study are sourced from 26 boreholes, as detailed in a geotechnical investigation report database, comprising a total of 130 data points. An importance analysis, grounded in the random forest algorithm, is conducted to evaluate the significance of each dynamic property. This analysis informs the prediction of dynamic properties, prioritizing those static properties identified as most influential. The efficacy of these predictions is quantified using the coefficient of determination, which indicated exceptionally high reliability, with values reaching 0.99 in both training and testing phases when all input properties are considered. The conventional method is used for predicting dynamic properties through Standard Penetration Test (SPT) and compared the outcomes with this technique. The error ratio has decreased by approximately 0.95, thereby validating its reliability. This research marks a significant advancement in the indirect estimation of the relationship between static and dynamic soil properties through the application of machine learning techniques.

Keywords

Acknowledgement

This research was supported by the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (NRF-2020R1A2C2012113).

References

  1. Anbazhagan, P., Kumar, A. and Sitharam, T.G. (2013), "Seismic site classification and correlation between standard penetration test N value and shear wave velocity for Lucknow City in Indo-Gangetic Basin", Pure Appl. Geophys., 170, 299-318. https://doi.org/10.1007/s00024-012-0525-1.
  2. Ataee, O., Moghaddas, N.H. and Lashkaripour, G.R. (2019), "Estimating shear wave velocity of soil using standard penetration test (SPT) blow counts in Mashhad city", J. Earth Syst. Sci., 128(3), 66. https://doi.org/10.1007/s12040-019-1077-x.
  3. Benemaran, R.S. and Esmaeili-Falak, M. (2023), "Predicting the Young's modulus of frozen sand using machine learning approaches: State-of-the-art review", Geomech. Eng., 34(5), 507-527. https://doi.org/10.12989/gae.2023.34.5.507.
  4. Do, T.M., Laue, J., Mattsson, H. and Jia, Q. (2023), "Excess pore water pressure generation in fine granular materials under undrained cyclic triaxial loading", Int. J. Geo-Eng., 14(1), 8. https://doi.org/10.1186/s40703-023-00185-y.
  5. Fauzi, A., Irsyam, M. and Fauzi, U.J. (2014), "Empirical correlation of shear wave velocity and N-SPT value for Jakarta", GEOMATE J., 7(13), 980-984. https://doi.org/10.21660/2014.13.3263.
  6. Fereidooni, D. and Karimi, Z. (2023), "Predicting rock brittleness indices from simple laboratory test results using some machine learning methods", Geomech. Eng., 34(6), 697-726. https://doi.org/10.12989/gae.2023.34.6.697.
  7. Ghazi, A., Moghadas, N.H., Sadeghi, H., Ghafoori, M. and Lashkaripur, G.R. (2015), "Empirical relationships of shear wave velocity, SPT-N value and vertical effective stress for different soils in Mashhad", Iran. Annal. Geophys., 58(3), 2015. https://doi.org/10.4401/ag-6635.
  8. Gomaa, A.E., Hasan, A.M., Mater, Y.M. and AbdelSalam, S.S. (2023), "Shell folded footings using different angles and EPS cavity filling: experimental study", Int. J. Geo-Eng., 14(1), 10. https://doi.org/10.1186/s40703-023-00187-w.
  9. Heo, G., Kim, J., Jeong, S. and Kwak, D. (2023), "Evaluation of shear wave velocity prediction models from standard penetration test N values depending on geologic attributes: A case study in Busan", South Korea. Geotechnics, 3(4), 1004-1016. https://doi.org/10.3390/geotechnics3040054.
  10. Hong, W.T., Lee, J.S., Lee, D. and Yoon, H.K. (2022), "Estimation of bulk electrical conductivity in saline medium with contaminated lead solution through TDR coupled with machine learning", Process Saf. Environ. Protection, 161, 58-66. https://doi.org/10.1016/j.psep.2022.03.018.
  11. Ihsan, S., Saqib, S., Rashid, H.M.A., Niazi, F.S. and Qureshi, M.U. (2023), "Predicting blast-induced ground vibrations at limestone quarry from artificial neural network optimized by randomized and grid search cross-validation, and comparative analyses with blast vibration predictor models", Geomech. Eng., 35(2), 121-133. https://doi.org/10.12989/gae.2023.35.2.121.
  12. Kim, S. and Yoon, H.K. (2023), "Application of classification coupled with PCA and SMOTE, for obtaining safety factor of landslide based on HRA", Bull. Eng. Geol. Environ., 82(10), 381. https://doi.org/10.1007/s10064-023-03403-0.
  13. Lee, D.G., Lee, S.Y. and Song, K.I. (2023), "Development of stability evaluation system for retaining walls: Differential evolution algorithm-artificial neural network", Geomech. Eng., 34(3), 329-339. https://doi.org/10.12989/gae.2023.34.3.329.
  14. Lee, J.S., Park, J., Kim, J. and Yoon, H.K. (2022), "Study of oversampling algorithms for soil classifications by field velocity resistivity probe", Geomech. Eng., 30(3), 247-258. https://doi.org/10.12989/gae.2022.30.3.247.
  15. Lee, S.J. and Choi, S.O. (2023), "Mean fragmentation size prediction in an open-pit mine using machine learning techniques and the Kuz-Ram model", Geomech. Eng., 34(5), 547-559. https://doi.org/10.12989/gae.2023.34.5.547.
  16. Madhushani, C., Dananjaya, K., Ekanayake, I.U., Meddage, D.P. P., Kantamaneni, K. and Rathnayake, U. (2024), "Modeling streamflow in non-gauged watersheds with sparse data considering physiographic, dynamic climate, and anthropogenic factors using explainable soft computing techniques", J. Hydrology, 130846. https://doi.org/10.1016/j.jhydrol.2024.130846.
  17. Meddage, P., Ekanayake, I., Perera, U.S., Azamathulla, H.M., Md Said, M.A. and Rathnayake, U. (2022). Interpretation of machine-learning-based (black-box) wind pressure predictions for low-rise gable-roofed buildings using Shapley additive explanations (SHAP)", Buildings, 12(6), 734. https://doi.org/10.3390/buildings12060734.
  18. Menze, B.H., Kelm, B.M., Masuch, R., Himmelreich, U., Bachert, P., Petrich, W. and Hamprecht, F.A. (2009), "A comparison of random forest and its Gini importance with standard chemometric methods for the feature selection and classification of spectral data", BMC Bioinformatics, 10, 1-16. https://doi.org/10.1186/1471-2105-10-213.
  19. Min, D.H. and Yoon, H.K. (2021), "Suggestion for a new deterministic model coupled with machine learning techniques for landslide susceptibility mapping", Scientific Reports, 11(1), 1-24. https://doi.org/10.1038/s41598-021-86137-x.
  20. Min, D.H., Kim, Y., Kim, S. and Yoon, H.K. (2023), "Strategy of oversampling geotechnical parameters through geostatistical, SMOTE, and CTGAN methods for assessing susceptibility of landslide", Landslides, 1-17. https://doi.org/10.1007/s10346-023-02166-9.
  21. Nguyen, A.D., Nguyen, V.T. and Kim, Y.S. (2023), "Finite element analysis on dynamic behavior of sheet pile quay wall dredged and improved seaside subsoil using cement deep mixing", Int. J. Geo-Eng., 14(1), 9. https://doi.org/10.1186/s40703-023-00186-x.
  22. Park, J., Lee, J.S., Jang, B.S., Min, D.H. and Yoon, H.K. (2022), "A comprehensive laboratory compaction study: Geophysical assessment", Geomech. Eng., 30(2), 211-218. https://doi.org/10.12989/gae.2022.30.2.211.
  23. Park, J., Lee, J.S. and Yoon, H.K. (2023), "Geoacoustic and geophysical data-driven seafloor sediment classification through machine learning algorithms with property-centered oversampling techniques", Comput.-Aided Civil Infrastruct. Eng., https://doi.org/10.1111/mice.13126.
  24. Rajabian, A. (2023), "Effect of initial failure geometry on the progress of a retrogressive seepage-induced landslide", Int. J. Geo-Eng., 14(1), 11. https://doi.org/10.1186/s40703-023-00189-8.
  25. Saarela, M. and Jauhiainen, S. (2021), "Comparison of feature importance measures as explanations for classification models", SN Appl. Sci., 3(2), 272. https://doi.org/10.1007/s42452-021-04148-9.
  26. Thisovithan, P., Aththanayake, H., Meddage, D.P.P., Ekanayake, I. U. and Rathnayake, U. (2023), "A novel explainable AI-based approach to estimate the natural period of vibration of masonry infill reinforced concrete frame structures using different machine learning techniques", Results in Eng., 19, 101388. https://doi.org/10.1016/j.rineng.2023.101388.
  27. Yazdandoust, M., Jamnani, A.R. and Sabermahani, M. (2023), "The role of wall configuration and reinforcement type in selecting the pseudo-static coefficients for reinforced soil walls", Geomech. Eng., 35(5), 555-570. https://doi.org/10.12989/gae.2023.35.5.555.
  28. Yoon, H.K., Lee, J.S. and Yu, J.D. (2022), "Correlation of granite rock properties with longitudinal wave velocity in rock bolt", Int. J. Rock Mech. Min. Sci., 159, 105200. https://doi.org/10.1016/j.ijrmms.2022.105200.
  29. Yu, J.D., Lee, J.S. and Yoon, H.K. (2021), "Effects of rock weathering on guided wave propagation in rock bolts", Tunn. Undergr. Sp. Tech., 115, 104069. https://doi.org/10.1016/j.tust.2021.104069.
  30. Zhang, J., Zhou, X., Huang, X., Liu, X., Yuan, J., Liang, X. and Li, J. (2023), "Study on the root interaction characteristics and nonlinear deformation prediction of root piles", Geomech. Eng., 35(3), 221-239. https://doi.org/10.12989/gae.2023.35.3.221.