Geomechanics and Engineering

  • 제35권1호
  • /
  • Pages.67-80
  • /
  • 2023
  • /
  • 2005-307X(pISSN)
  • /
  • 2092-6219(eISSN)
테크노프레스 (Techno-Press)
권호 표지
DOI QR코드

DOI QR Code

A study on data mining techniques for soil classification methods using cone penetration test results

  • Junghee Park (Department of Civil and Environmental Engineering, Incheon National University) ;
  • So-Hyun Cho (Department of Civil and Environmental Engineering, Kookmin University) ;
  • Jong-Sub Lee (School of Civil, Environmental and Architectural Engineering, Korea University) ;
  • Hyun-Ki Kim (Department of Civil and Environmental Engineering, Kookmin University)
  • 투고 : 2022.12.20
  • 심사 : 2023.08.26
  • 발행 : 2023.10.10
⟨ 이전 논문 다음 논문 ⟩

초록

Due to the nature of the conjunctive Cone Penetration Test(CPT), which does not verify the actual sample directly, geotechnical engineers commonly classify the underground geomaterials using CPT results with the classification diagrams proposed by various researchers. However, such classification diagrams may fail to reflect local geotechnical characteristics, potentially resulting in misclassification that does not align with the actual stratification in regions with strong local features. To address this, this paper presents an objective method for more accurate local CPT soil classification criteria, which utilizes C4.5 decision tree models trained with the CPT results from the clay-dominant southern coast of Korea and the sand-dominant region in South Carolina, USA. The results and analyses demonstrate that the C4.5 algorithm, in conjunction with oversampling, outlier removal, and pruning methods, can enhance and optimize the decision tree-based CPT soil classification model.

키워드

과제정보

This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. 2019R1A2C1088527).

참고문헌

  1. Arifuzzaman and Anisuzzaman, M., (2022), "An initiative to correlate the SPT and CPT data for an alluvial deposit of Dhaka city", Int. J. Geo-Eng., 13(1), 5. https://doi.org/10.1186/s40703-021-00170-3.
  2. Bai, X.D., Cheng, W.C., Ong, D.E. and Li, G. (2021), "Evaluation of geological conditions and clogging of tunneling using machine learning", Geomech. Eng., 25(1), 59-73. https://doi.org/10.12989/gae.2021.25.1.059.
  3. Begemann, H.K.S. (1965), "The friction jacket cone as an aid in determining the soil profile", Proceedings of the 6th International Conference on Soil Mechanics and Foundation Engineering, ICSMFE, 1, 17-20.
  4. Bhargavi, P. and Jyothi, S. (2011), "Soil classification using data mining techniques: a comparative study". Int. J. Eng. Trends Technol., 2(1), 55-59.
  5. Bhattacharya, B. and Solomatine, D.P. (2006), "Machine learning in soil classification", Neural Networks, 19(2), 186-195. https://doi.org/10.1016/j.neunet.2006.01.005.
  6. Cai, Y., Li, J., Li, X., Li, D. and Zhang, L. (2018), "Estimating soil resistance at unsampled locations based on limited CPT data", B. Eng. Geol. Environ., 78, 3637-3648. https://doi.org/10.1007/s10064-018-1318-2.
  7. Cal, Y. (1995), "Soil classification by neural-network", Adv. Eng. Softw., 22(2), 95-97. https://doi.org/10.1016/0965-9978(94)00035-H
  8. Cao, Z. and Wang, Y. (2013), "Bayesian approach for probabilistic site characterization using cone penetration tests", J. Geotech. Geoenviron. Eng., 139(2), 267-276. https://doi.org/10.1061/(ASCE)GT.1943-5606.0000765.
  9. Cao, Z., Zheng, S., Li, D. and Phoon, K. (2018), "Bayesian identification of soil stratigraphy based on soil behaviour type index". Can. Geotech. J., 56(4), 570-586. https://doi.org/10.1139/cgj-2017-0714.
  10. Cho, S. (2021), "A study on data mining techniques for soil classification method using cone penetration test results", Master's thesis, Kookmin University, South Korea.
  11. Cho, S., Kim, H.S. and Kim, H. (2023). "Locally specified CPT soil classification based on machine learning techniques", Sustainability, 15(4), 2914.
  12. Das, S.K. and Basudhar, P.K. (2009), "Utilization of self-organizing map and fuzzy clustering for site characterization using piezocone data", Comput. Geotech., 36(1-2), 241-248. https://doi.org/10.1016/j.compgeo.2008.02.005.
  13. Farhadi, M.S. (2019), "An integrated optimization-game theory model for CPT-based subground stratification", 2019 TC304 Student Contest.
  14. Demir, S. and Sahin, E.K. (2022). "Comparison of tree-based machine learning algorithms for predicting liquefaction potential using canonical correlation forest, rotation forest, and random forest based on CPT data", Soil Dyn. Earthq. Eng., 154, 107130. https://doi.org/10.1016/j.soildyn.2021.107130.
  15. Douglas, B.J. and Olsen, R.S. (1981), "Soil classification using electric cone penetrometer", Symposium on Cone Penetration Testing and Experience, Geotechnical Engineering Division, ASCE, St. Louis, Missouri, (Missouri, 1981), 209-227
  16. Juang, C.H., Jiang, T. and Christopher, R.A. (2001), "Three-dimensional site characterization: neural network approach", Geotechnique, 51(9), 799-809. https://doi.org/10.1680/geot.2001.51.9.799.
  17. Kwak, N.S. and Ko, T.Y. (2022), "Machine learning-based regression analysis for estimating Cerchar abrasivity index", Geomech. Eng., 29(3), 219-228. https://doi.org/10.12989/gae.2022.29.3.219.
  18. Kim, C.H., Im, J.C. and Kim, Y.S. (2008), "Study on the applicability of CPT based soil classification chart", KSCE J. Civil Environ. Eng. Res., 28(5), 293-301 (in Korean).
  19. Kim, C.H., Im, J.C., Kim, Y.S. and Joo, N.A. (2008). "New soil classification system using cone penetration test", J. Korean Geotech. Soc., 24(10), 57-70.
  20. Kim, H.S. and Kim, H.K. (2019). "Optimizing site-specific geostatistics to improve geotechnical spatial information in Seoul, South Korea", Arab. J. Geosci., 12, 1-20. https://doi.org/10.1007/s12517-018-4171-5.
  21. Kim, Y., Hong, J., Shin, J. and Kim, B. (2022), "Shield TBM disc cutter replacement and wear rate prediction using machine learning techniques", Geomech. Eng., 29(3), 249-258. https://doi.org/10.12989/gae.2022.29.3.249.
  22. 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.
  23. Ma, Y. and He, H. (2013), "Imbalanced learning: foundations, algorithms, and applications", University of Rhode Island: Kingston, RI, USA, 2013.
  24. Najjar, Y.M. and Basheer, I.A. (1996), "Neural network approach for site characterization and uncertainty prediction", Geotechnical Special Publication, ASCE, 58(1), 134-148.
  25. Odeh, I.O.A., Chittleborough, D.J. and McBratney, A.B. (1992), "Soil pattern recognition with fuzzy-c-means: application to classification and soil-landform interrelationships", Soil Sci. Soc. Am. J., 56(2), 505-516.
  26. 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.
  27. Quinlan, J.R. (1986), "Induction of decision trees. Machine Learning", 1(1), 81-106
  28. Quinlan, J.R. (2008), "Top 10 algorithms in data mining", Knowl. Inf. Syst., 14(1), 1-37. https://doi.org/10.1007/s10115-007-0114-2.
  29. Rizzo, D.M., Lillys, T.P. and Dougherty, D.E. (1996), "Comparisons of site characterization methods using mixed data", Geotechnical Special Publication, ASCE, 58(1), 157-179.
  30. Robertson, P.K. (1990), "Soil classification using the cone penetration test". Can. Geotech. J., 27(1), 151-158. https://doi.org/10.1139/t90-014.
  31. Robertson, P.K. (2009), "Interpretation of cone penetration tests - a unified approach", Can. Geotech. J., 46(11), 1337-1355. https://doi.org/10.1139/T09-065.
  32. Robertson, P.K. (2016), "Cone penetration test -based soil behaviour type classification system - an updated". Can. Geotech. J., 53(12), 1910-1927. https://doi.org/10.1139/cgj2016-0044.
  33. Robertson, P.K. and Cabal, K.L. (2014), Guide to Cone Penetration Testing 6th Edition.
  34. Robertson, P.K. and Campanella, R.G. (1983), "SPT-CPT correlations", J. Geotech. Div. ASCE, 109(11), 1449-1460. https://doi.org/10.1061/(ASCE)0733-9410(1983)109:11(1449)
  35. Robertson, P.K. and Wride, C.E. (1998), "Evaluating cyclic liquefaction potential using the cone penetration test". Can. J. Geotech., 35(3), 442-459. https://doi.org/10.1139/t98-017.
  36. Robertson, P.K., Campanella, R.G., Gillespie, D. and Greig, J. (1986), "Use of piezometer cone data", Proceedings of the America Society of Civil Engineers, In-Situ 86 Specialty Conference, Blacksburg, Virginia.
  37. Soleimani Fard, H. and Goudarzy, M. (2021), "Influence of surcharge on cone penetration test results and the inspection of various approaches for capturing its effect: a case study", Int. J. Geo-Eng., 12(1), 17. https://doi.org/10.1186/s40703-021-00146-3.