Machine Learning–Based Organic Soil Classification Using Cone Penetrometer Tests
Publication: Journal of Geotechnical and Geoenvironmental Engineering
Volume 150, Issue 9
Abstract
Soil classification methods currently rely on soil borings or cone/piezocone penetrometer tests (CPT/CPTu). Literature provides several methods that classify soils based on two parameters (typically tip resistance and friction sleeve/porewater pressure) obtained from CPTu data, defining a soil behavior type. However, these methods face challenges in reliably classifying certain soils, such as organic soils. Robust and complex analyses are required to classify organic soils accurately. In this study, a random forest (RF) based method is developed to predict the presence and depth of organic soils. The RF model utilized features from CPTu soundings including tip resistance, sleeve friction, and pore pressure. The true location of organic soils, derived from index properties obtained from soil borings, served as the model’s outputs. Unseen CPTu data was used to predict organic soils throughout the entire project alignment, serving as validation for the model. The model achieved an F1 score of 0.89. Settlement analyses were conducted to evaluate the practical implications of the model’s predictions on levee fill costs. The RF-based model yielded settlement predictions that closely matched those obtained through boring predictions. In contrast, traditional classification methods underestimated settlements, resulting in lower estimates for levee fill costs.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
Support for this research was provided by the Louisiana Coastal Protection and Restoration Authority (CPRA) and administered by Louisiana Sea Grant (LSG) through its Coastal Science Assistantship Program (CSAP). The contents and views in this paper are those of the authors and do not necessarily reflect those of any consultant, regulatory agency or personnel, or anyone else knowledgeable about the case study referenced. In particular, the contents of this paper/publication are the personal opinions of the author(s) and may not reflect the opinions, conclusions, policies, or procedures of the US Army Corps of Engineers and Louisiana Coastal Protection and Restoration Authority.
References
Agaiby, S. S., and P. W. Mayne. 2021. “CPTU identification of regular, sensitive, and organic clays towards evaluating preconsolidation stress profiles.” AIMS GeoSci. 7 (4): 553–573. https://doi.org/10.3934/geosci.2021032.
Baligh, M. M., and J.-N. Levadoux. 1980. Pore pressure dissipation after cone penetration. Rep. No. MIT-T-80-003. Washington, DC: National Oceanic and Atmospheric Administration.
Biau, G., and E. Scornet. 2016. “A random forest guided tour.” Test 25 (2): 197–227. https://doi.org/10.1007/s11749-016-0481-7.
Breiman, L. 2001. “Random forests.” Mach. Learn. 45 (1): 5–32. https://doi.org/10.1023/A:1010933404324.
Carvalho, L., and D. Ribeiro. 2019. “Soil classification system from cone penetration test data applying distance-based machine learning algorithms.” Soils Rocks 42 (2): 167–178. https://doi.org/10.28927/SR.422167.
Carvalho, L. O., and D. B. Ribeiro. 2021. “A multiple model machine learning approach for soil classification from cone penetration test data.” Soils Rocks 44 (Nov): e2021072121. https://doi.org/10.28927/SR.2021.072121.
Cho, S., H.-S. Kim, and H. Kim. 2023. “Locally specified CPT soil classification based on machine learning techniques.” Sustainability 15 (4): 2914. https://doi.org/10.3390/su15042914.
Demir, S., and E. K. Sahin. 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. Earthquake Eng. 154 (Mar): 107130. https://doi.org/10.1016/j.soildyn.2021.107130.
Deubert, R. E. 1982. “Correlation of compression index and soil properties of New Orleans area clays.” Master’s thesis, Dept. of Civil and Environmental Engineering, Tulane Univ.
Douglas, B. J. 1981. “Soil classification using electric cone penetrometer.” In Proc., Symp. on Cone Penetration Testing and Experience. New York: Geo-Technical Engineering Division, ASCE.
Erharter, G. H., S. Oberhollenzer, A. Fankhauser, R. Marte, and T. Marcher. 2021. “Learning decision boundaries for cone penetration test classification.” Comput.-Aided Civ. Infrastruct. Eng. 36 (4): 489–503. https://doi.org/10.1111/mice.12662.
Fisk, H. N. 1944. Geological investigation of the alluvial valley of the lower Mississippi River. Vicksburg, MS: Mississippi River Commission.
Huang, P.-T., M. Patel, M. C. Santagata, and A. Bobet. 2009. Classification of organic soils. West Lafayette, IN: Indiana DOT and Purdue Univ.
Jafari, N. H., and T. D. Stark. 2017. “Field scale hydraulic conductivity and compressibility of organic clays.” Eng. Geol. 220 (Mar): 52–64. https://doi.org/10.1016/j.enggeo.2017.01.015.
Jas, K., and G. Dodagoudar. 2023. “Liquefaction potential assessment of soils using machine learning techniques: A state-of-the-art review from 1994–2021.” Int. J. Geomech. 23 (7): 03123002. https://doi.org/10.1061/IJGNAI.GMENG-7788.
Jefferies, M., and M. Davies. 1991. “Soil classification by the cone penetration test: Discussion.” Can. Geotech. J. 28 (1): 173–176. https://doi.org/10.1139/t91-023.
Jones, G. 1982. “Piezometer penetration testing CUPT.” In Proc., 2nd European Symp. on Penetration Testing. EH Leiden, Netherlands: CRC Press.
Kolb, C. 1962. Distribution of soils bordering the Mississippi River from Donaldsonville to head of passes. Vicksburg, MS: US Army Engineers Waterways Experiment Station.
Kolb, C. R., and J. R. Van Lopik. 1958. Geology of the Mississippi River deltaic plain Southeastern Louisiana. Washington, DC: USEPA.
Kulhawy, F. H., and P. W. Mayne. 1990. Manual on estimating soil properties for foundation design. Palo Alto, CA: Electric Power Research Institute.
Lengkeek, H., and R. Brinkgreve. 2022. “CPT-based classification of soft organic clays and peat.” In Cone penetration testing 2022, 509–514. Boca Raton, FL: CRC Press.
Li, A., N. H. Jafari, and F. T.-C. Tsai. 2020. “Modelling and comparing 3-D soil stratigraphy using subsurface borings and cone penetrometer tests in coastal Louisiana, USA.” Georisk: Assess. Manage. Risk Eng. Syst. Geohazards 14 (2): 158–176. https://doi.org/10.1080/17499518.2019.1637528.
Liu, Y. 2014. “Random forest algorithm in big data environment.” Comput. Modell. New Technol. 18 (12A): 147–151. https://doi.org/10.3390/app12105100.
Lunne, T., T. Berre, and S. Strandvik. 1997. “Sample disturbance effects in soft low plastic Norwegian clay.” In Proc., Symp. on Recent Developments in Soil and Pavement Mechanics. Rotterdam, Netherlands: A. A. Balkema.
Mesri, G., and M. Ajlouni. 2007. “Engineering properties of fibrous peats.” J. Geotech. Geoenviron. Eng. 133 (7): 850–866. https://doi.org/10.1061/(ASCE)1090-0241(2007)133:7(850).
Mitchell, J. K., and K. Soga. 2005. Fundamentals of soil behavior. Hoboken, NJ: Wiley.
Ng, A. 2000. In Vol. 1 of CS229 lecture notes, 1–3. Stanford, CA: Stanford Univ.
Pedregosa, F., G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, and V. Dubourg. 2011. “Scikit-learn: Machine learning in Python.” J. Mach. Learn. Res. 12 (Nov): 2825–2830.
Rauter, S., and F. Tschuchnigg. 2021. “CPT data interpretation employing different machine learning techniques.” Geosciences 11 (7): 265. https://doi.org/10.3390/geosciences11070265.
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.
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.
Robertson, P. K. 2010. “Soil behaviour type from the CPT: An update.” In Proc., 2nd Int. Symp. on Cone Penetration Testing. London: International Society for Soil Mechanics and Geotechnical Engineering.
Robertson, P. K. 2016. “Cone penetration test (CPT)-based soil behaviour type (SBT) classification system—An update.” Can. Geotech. J. 53 (12): 1910–1927. https://doi.org/10.1139/cgj-2016-0044.
Robertson, P. K., and R. Campanella. 1983. “Interpretation of cone penetration tests. Part I: Sand.” Can. Geotech. J. 20 (4): 718–733. https://doi.org/10.1139/t83-078.
Robertson, P. K., R. G. Campanella, D. Gillespie, and J. Greig. 1986. “Use of piezometer cone data.” In Use of in situ tests in geotechnical engineering. Reston, VA: ASCE.
Rocscience. 2023. Settle3, soil settlement and consolidation analysis. Toronto: Rocscience.
Saeedi Azizkandi, A., A. Kashkooli, and M. Baziar. 2014. “Prediction of uplift pile displacement based on cone penetration tests (CPT).” Geotech. Geol. Eng. 32 (4): 1043–1052. https://doi.org/10.1007/s10706-014-9779-y.
Saucier, R. T. 1994. Geomorphology and quaternary geologic history of the lower Mississippi Valley. Vicksburg, MS: US Army Engineer Waterways Experiment Station.
Saye, S. R., J. Santos, S. M. Olson, and R. D. Leigh. 2017. “Linear trendlines to assess soil classification from cone penetration test data.” J. Geotech. Geoenviron. Eng. 143 (9): 04017060. https://doi.org/10.1061/(ASCE)GT.1943-5606.0001729.
Schmertmann, J. H. 1978. Guidelines for cone penetration test: Performance and design, United States. Washington, DC: Federal Highway Administration.
Schonlau, M., and R. Y. Zou. 2020. “The random forest algorithm for statistical learning.” Stata J. 20 (1): 3–29. https://doi.org/10.1177/1536867X20909688.
Senneset, K., N. Janbu, and G. Svanø. 1982. Strength and deformation parameters from cone penetration tests. Rotterdam, Netherlands: A. A. Balkema.
Straż, G., and A. Borowiec. 2020. “Estimating the unit weight of local organic soils from laboratory tests using artificial neural networks.” Appl. Sci. 10 (7): 2261. https://doi.org/10.3390/app10072261.
Terzaghi, K., R. B. Peck, and G. Mesri. 1996. Soil mechanics in engineering practice. New York: Wiley.
Tumay, M., Y. Hatipkarasulu, E. Marx, and B. Cotton. 2013. “CPT/PCPT-based organic material profiling.” In Proc., 18th Intl. Conf. on Soil Mechanics & Geotechnical Engineering. London: International Society for Soil Mechanics and Geotechnical Engineering.
USACE. 2012. Hurricane and storm damage risk reduction system design guidelines, New Orleans district engineering division. Washington, DC: USACE.
USACE. 2022. West shore lake Pontchartrain, hurricane and storm damage risk reduction system project—Contract 107 (STA: 326 + 00 to STA: 411 + 00). Washington, DC: USACE.
Zhu, L., Q. Liao, Z. Wang, J. Chen, Z. Chen, Q. Bian, and Q. Zhang. 2022. “Prediction of soil shear strength parameters using combined data and different machine learning models.” Appl. Sci. 12 (10): 5100. https://doi.org/10.3390/app12105100.
Information & Authors
Information
Published In
Journal of Geotechnical and Geoenvironmental Engineering
Volume 150 • Issue 9 • September 2024
Copyright
© 2024 American Society of Civil Engineers.
History
Received: Sep 23, 2023
Accepted: Apr 22, 2024
Published online: Jul 12, 2024
Published in print: Sep 1, 2024
Discussion open until: Dec 12, 2024
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.