Published

2026-05-27

Comparative Analysis of Traditional and Machine Learning Approaches for Estimating Undrained Shear Strength from SCPT Data

DOI:

https://doi.org/10.15446/esrj.v30n1.121762

Keywords:

Undrained shear strength, seismic piezocone test, sensitive clay, shear wave velocity, field vane shear test, machine learning (en)
Resistencia al corte no drenada, ensayo de piezocono sísmico, arcilla sensible, velocidad de onda de corte, ensayo de veleta de campo, Aprendizaje automático no supervisado (es)

Downloads

Authors

  • Rama Vara Prasad Chavali NIT Hamirpur
  • Ali Saeidi Université du Québec à Chicoutimi: Chicoutimi https://orcid.org/0000-0001-6954-5453
  • Swamy Naga Ratna Giri Department of Civil Engineering, School of Engineering, SR University, Warangal-506371, Telangana, India
  • Mohammad Salsabili University of Western Ontario

This study compares traditional empirical methods and machine learning (ML) models for estimating the undrained shear strength (su) of sensitive clays in the Saguenay region of Canada using SCPTu measurements from six sites, with penetration depths ranging from 10 to 40 m. SCPTu parameters (qt, fs, u2, and Vs) were recorded at 0.5 m intervals up to 20 m depth, while field vane shear tests (FVT) were conducted at 1 m intervals between 2 and 20 m, co-located with SCPTu points to ensure direct comparability. These paired datasets enabled the development of region-specific empirical correlations between SCPTu parameters and su, as well as the training and evaluation of multiple ML regression models. Among the six algorithms considered, Random Forest and XGBoost demonstrated the highest predictive accuracy (R2  up to 0.95), outperforming classical approaches. The findings highlight the effectiveness of integrating SCPTu data with ML techniques to enhance su estimation in overconsolidated, sensitive clays and emphasize the importance of region-focused calibration for geotechnical design.

Este estudio compara métodos empíricos tradicionales y modelos de aprendizaje automático (ML) para estimar la resistencia al corte no drenada (su) de arcillas sensibles en la región de Saguenay, Canadá, utilizando mediciones SCPTu de seis sitios, con profundidades de penetración de 10 a 40 m. Los parámetros SCPTu (qt, fs, u2, y Vs) se registraron a intervalos de 0,5 m hasta los 20 m de profundidad, mientras que los ensayos de corte con veleta de campo (FVT) se realizaron a intervalos de 1 m entre 2 y 20 m, en los mismos puntos que las mediciones SCPTu para asegurar la comparabilidad directa. Estos conjuntos de datos emparejados permitieron el desarrollo de correlaciones empíricas específicas de la región entre los parámetros SCPTu y su, así como el entrenamiento y la evaluación de varios modelos de regresión ML. Entre los seis algoritmos considerados, Random Forest y XGBoost demostraron la mayor precisión predictiva (R² de hasta 0,95), superando a los enfoques clásicos. Los resultados destacan la efectividad de integrar datos SCPTu con técnicas de ML para mejorar la estimación de su en arcillas sensibles sobreconsolidadas y enfatizan la importancia de la calibración enfocada en la región para el diseño geotécnico.

References

Agaiby, S. S., & Mayne, P. W. (2015). Relationship between undrained shear strength and shear wave velocity for clays. 6th Symp. on Deformation Characteristics of Geomaterials (pp. 358-365). IOS Press, Argentina.

Alshibli, K. A., Okeil, A. M., Alramahi, B., & Zhang, Z. (2011). Reliability analysis of CPT measurements for calculating undrained shear strength. ASTM International.

ASTM. (2015). Standard test method for field vane shear test in saturated fine-grained soils. West Conshohocken, PA: ASTM.

Bol, E., Önalp, A., Özocak, A., & Sert, S. (2019). Estimation of the undrained shear strength of Adapazari fine grained soils by cone penetration test. Engineering Geology, 261, 105277.

Bouchard, R., Dion, D. J., & Tavenas, F. (1983). Origine de la préconsolidation des argiles du Saguenay, Québec. Canadian Geotechnical Journal, 20(2), 315-328.

Breiman, L. (2001). Random forests. Machine learning, 45, 5-32.

Breiman, L., Friedman, J., Olshen, R.A., & Stone, C.J. (1984). Classification and Regression Trees (1st ed.). Chapman and Hall/CRC.

Cai, G. J., Liu, S. Y., Tong, L. Y., & Du, G. Y. (2010). Field evaluation of undrained shear strength from piezocone penetration tests in soft marine clay. Marine Georesources and Geotechnology, 28(2), 143-153.

Cai, G., Liu, S., Tong, L., & Du, G. (2009). Assessment of direct CPT and CPTU methods for predicting the ultimate bearing capacity of single piles. Engineering Geology, 104(3-4), 211-222.

Chen, T., & Guestrin, C. (2016, August). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on knowledge discovery and data mining (pp. 785-794).

Daigneault, R-A., Cousineau, P., Leduc, E., Beaudoin, G., Milette, S., Horth, N., Roy, D.W., Lamothe, M. and Allard, G. (2011). Rapport final sur les travaux de cartographie des formations superficielles realises dans le territoire municipalise du Saguenay-Lac-Saint-Jean. Quebec City, QC, Canada. Ministère des Ressources naturelles et de la Faune du Quebec.

Demers, D., & Leroueil, S. (2002). Evaluation of preconsolidation pressure and the overconsolidation ratio from piezocone tests of clay deposits in Quebec. Canadian Geotechnical Journal, 39(1), 174-192.

Duan, W., Cai, G., Liu, S., Puppala, A. J., & Chen, R. (2019). In-situ evaluation of undrained shear strength from seismic piezocone penetration tests for soft marine clay in Jiangsu, China. Transportation Geotechnics, 20, 100253.

Ebrahimian, B., Movahed, V., & Pasha, A. Y. (2012). Evaluation of undrained shear strength of marine clay using cone penetration resistance at South Pars field in Iran. Ocean engineering, 54, 182-195.

El-Bosraty, A. H., Ebid, A. M., & Fayed, A. L. (2020). Estimation of the undrained shear strength of east Port-Said clay using the genetic programming. Ain Shams Engineering Journal, 11(4), 961-969.

Fournier, T., Locat, P., Therrien, J., Poulin-Leboeuf, L., Paradis, S., & Demers, D. (2022). La coulée argileuse de la Grande rivière de la Baleine du 22 avril 2021. Geohazards, 8.

Golestani Dariani, A. A., & Ahmadi, M. M. (2018). Undrained shear strength and in situ horizontal effective stress from piezocone penetration test measurements in clayey soils: New approach. International Journal of Geomechanics, 18(9), 04018097.

Gylland, A. S., Sandven, R., Montafia, A., Pfaffhuber, A. A., Kåsin, K., & Long, M. (2017). CPTU classification diagrams for identification of sensitive clays. Landslides in Sensitive Clays: From Research to Implementation, 57-66.

Hong, S. J., Lee, M., Kim, J., & Lee, W. (2010). Evaluation of undrained shear strength of Busan clay using CPT. In Proceedings of the 2nd International Symposium on Cone Penetration Testing, CPT (Vol. 10).

Kim, C., Kim, S., & Lee, J. (2009). Estimating clay undrained shear strength using CPTu results. Proceedings of the Institution of Civil Engineers-Geotechnical Engineering, 162(2), 119-127.

Knuuti, M., & Länsivaara, T. (2019). Variation of CPTu-based transformation models for undrained shear strength of Finnish clays. Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards, 13(4), 262-270.

Kulhawy, F. H. (1992). Some thoughts on the evaluation of undrained shear strength for design. In Predictive soil mechanics: Proceedings of the Wroth Memorial Symposium held at St Catherine's College, Oxford, 27-29 July 1992 (pp. 394-403). Thomas Telford Publishing.

Kulkarni, M. P., Patel, A., & Singh, D. N. (2010). Application of shear wave velocity for characterizing clays from coastal regions. KSCE Journal of Civil Engineering, 14, 307-321.

L’Heureux, J. S., & Long, M. (2017). Relationship between shear-wave velocity and geotechnical parameters for Norwegian clays. Journal of geotechnical and Geoenvironmental engineering, 143(6), 04017013.

Länsivaara, T. T., Farhadi, M. S., & Samui, P. (2023). Performance of traditional and machine learning-based transformation models for undrained shear strength. Arabian Journal of Geosciences, 16(3), 183.

Lefebvre, G., Ladd, C. C., & Pare, J. J. (1988). Comparison of field vane and laboratory undrained shear strength in soft sensitive clays. Vane Shear Strength Testing in Soils: Field and Laboratory Studies, ASTM STP, 1014, 233-246.

Liu, L., Cai, G., Liu, X., Li, X., Liu, S., & Puppala, A. J. (2021). Estimation of undrained shear strength of overconsolidated clay using a maximum excess pore pressure method based on Piezocone Penetration Test (CPTU). Geotechnical Testing Journal, 44(4), 1153-1162.

Liu, S., Zou, H., Cai, G., Zhang, L., & Puppala, A. J. (2020). Piezocone penetration test-based site characterisation of Chong–Qi Bridge project, China. Proceedings of the Institution of Civil Engineers-Forensic Engineering, 173(1), 25-34.

Long, M., & Quigley, P. (2013). Undrained shear strength and stiffness of lrish glacial till from shear wave velocity. Ground Engineering, 46 (11), 26–27.

Low, H. E., Lune, T., Andersen, K. H., Sjursen, M. A., Li, X., & Randolph, M. F. (2010). Estimation of intact and remoulded undrained shear strengths from penetration tests in soft clays. Géotechnique, 60(11), 843-859.

Lunne, T., Powell, J. J., & Robertson, P. K. (2002). Cone penetration testing in geotechnical practice. CRC Press.

Mantaras, F. M., Odebrecht, E., & Schnaid, F. (2015). Using piezocone dissipation test to estimate the undrained shear strength in cohesive soil. Canadian Geotechnical Journal, 52(3), 318-325.

Mayne, P. W., Peuchen, J., & Baltoukas, D. (2015). Piezocone evaluation of undrained strength in soft to firm offshore clays. In Frontiers in Offshore Geotechnics III: Proceedings of the 3rd International Symposium on Frontiers in Offshore Geotechnics (ISFOG 2015) (Vol. 1, pp. 1091-1096). Taylor & Francis Books Ltd.

Miao, Y., Liu, S., Wang, H., & Wang, S. (2011). Predicting the vertical bearing capacity of single piles based on SCPTU test. In 2011 International Conference on Remote Sensing, Environment and Transportation Engineering (pp. 2306-2309). IEEE.

Miura, S., Yagi, K., & Asonuma, T. (2003). Deformation-strength evaluation of crushable volcanic soils by laboratory and in-situ testing. Soils and Foundations, 43(4), 47-57.

Mohammed, M. M., Roslan, H., & Firas, S. (2013). Assessment of rapid impact compaction in ground improvement from in-situ testing. Journal of Central South University, 20(3), 786-790.

Nakamura, A., Tanaka, H., & Fukasawa, T. (2009). Applicability of T-bar and ball penetration tests to soft clayey grounds. Soils and foundations, 49(5), 729-738.

Oh, T. M., Bang, E. S., Cho, G. C., & Park, E. S. (2017). Estimation of undrained shear strength for saturated clay using shear wave velocity. Marine Georesources & Geotechnology, 35(2), 236-244.

Rémai, Z. (2013). Correlation of undrained shear strength and CPT resistance. Periodica Polytechnica Civil Engineering, 57(1), 39-44.

Rezania, M., Javadi, A. A., & Giustolisi, O. (2010). Evaluation of liquefaction potential based on CPT results using evolutionary polynomial regression. Computers and Geotechnics, 37(1-2), 82-92.

Robertson, P. K. (1990). Soil classification using the cone penetration test. Canadian Geotechnical Journal, 27(1), 151-158.

Robertson, P. K. (2009). Interpretation of cone penetration tests—a unified approach. Canadian Geotechnical Journal, 46(11), 1337-1355.

Robertson, P. K. (2016). Cone penetration test (CPT)-based soil behavior type (SBT) classification system—an update. Canadian Geotechnical Journal, 53(12), 1910-1927.

Robertson, P. K., & Cabal, K. L. (2015). Guide to cone penetration testing for geotechnical engineering. Gregg Drilling & Testing, Inc, 6.

Saye, S. R., Santos, J., Olson, S. M., & Leigh, R. D. (2017). Linear trendlines to assess soil classification from cone penetration test data. Journal of Geotechnical and Geoenvironmental Engineering, 143(9), 04017060.

Schneider, J. A., Randolph, M. F., Mayne, P. W., & Ramsey, N. R. (2008). Analysis of factors influencing soil classification using normalized piezocone tip resistance and pore pressure parameters. Journal of Geotechnical and Geoenvironmental Engineering, 134(11), 1569-1586.

Shin, Y. J., & Kim, D. (2011). Assessment of undrained shear strength based on Cone Penetration Test (CPT) for clayey soils. KSCE Journal of Civil Engineering, 15(7), 1161.

Tavenas, F., Chagnon, J. Y., & Rochelle, P. L. (1971). The Saint-Jean-Vianney landslide: observations and eyewitnesses accounts. Canadian Geotechnical Journal, 8(3), 463-478.

Torrance, J. K. (2014). Chemistry, sensitivity and quick-clay landslide amelioration. Landslides in Sensitive Clays: From Geosciences to Risk Management, 15-24.

Trafford, A., & Long, M. (2020). Relationship between shear-wave velocity and undrained shear strength of peat. Journal of Geotechnical and Geoenvironmental Engineering, 146(7), 04020057.

Tran, Q. A., Ho, L. S., Le, H. V., Prakash, I., & Pham, B. T. (2022). Estimation of the undrained shear strength of sensitive clays using optimized inference intelligence system. Neural Computing and Applications, 34(10), 7835-7849.

Vapnik, V. N. (1999). An overview of statistical learning theory. IEEE transactions on neural networks, 10(5), 988-999.

Wride, C. E., Robertson, P. K., Biggar, K. W., Campanella, R. G., Hofmann, B. A., Hughes, J. M., ... & Woeller, D. J. (2000). Interpretation of in situ test results from the CANLEX sites. Canadian Geotechnical Journal, 37(3), 505-529.

Yin, J., Lu, Z., Geng, W., Han, W., & Hudu, A. A. (2022). Effect of porewater salinity on compression behaviors and hydraulic conductivity of soft marine clay. Marine Georesources & Geotechnology, 40(7), 813-822.

How to Cite

APA

Chavali, R. V. P., Saeidi, A., Ratna Giri, S. N. & Salsabili, M. (2026). Comparative Analysis of Traditional and Machine Learning Approaches for Estimating Undrained Shear Strength from SCPT Data. Earth Sciences Research Journal, 30(1), 103–113. https://doi.org/10.15446/esrj.v30n1.121762

ACM

[1]
Chavali, R.V.P., Saeidi, A., Ratna Giri, S.N. and Salsabili, M. 2026. Comparative Analysis of Traditional and Machine Learning Approaches for Estimating Undrained Shear Strength from SCPT Data. Earth Sciences Research Journal. 30, 1 (May 2026), 103–113. DOI:https://doi.org/10.15446/esrj.v30n1.121762.

ACS

(1)
Chavali, R. V. P.; Saeidi, A.; Ratna Giri, S. N.; Salsabili, M. Comparative Analysis of Traditional and Machine Learning Approaches for Estimating Undrained Shear Strength from SCPT Data. Earth sci. res. j. 2026, 30, 103-113.

ABNT

CHAVALI, R. V. P.; SAEIDI, A.; RATNA GIRI, S. N.; SALSABILI, M. Comparative Analysis of Traditional and Machine Learning Approaches for Estimating Undrained Shear Strength from SCPT Data. Earth Sciences Research Journal, [S. l.], v. 30, n. 1, p. 103–113, 2026. DOI: 10.15446/esrj.v30n1.121762. Disponível em: https://revistas.unal.edu.co/index.php/esrj/article/view/121762. Acesso em: 20 jul. 2026.

Chicago

Chavali, Rama Vara Prasad, Ali Saeidi, Swamy Naga Ratna Giri, and Mohammad Salsabili. 2026. “Comparative Analysis of Traditional and Machine Learning Approaches for Estimating Undrained Shear Strength from SCPT Data”. Earth Sciences Research Journal 30 (1):103-13. https://doi.org/10.15446/esrj.v30n1.121762.

Harvard

Chavali, R. V. P., Saeidi, A., Ratna Giri, S. N. and Salsabili, M. (2026) “Comparative Analysis of Traditional and Machine Learning Approaches for Estimating Undrained Shear Strength from SCPT Data”, Earth Sciences Research Journal, 30(1), pp. 103–113. doi: 10.15446/esrj.v30n1.121762.

IEEE

[1]
R. V. P. Chavali, A. Saeidi, S. N. Ratna Giri, and M. Salsabili, “Comparative Analysis of Traditional and Machine Learning Approaches for Estimating Undrained Shear Strength from SCPT Data”, Earth sci. res. j., vol. 30, no. 1, pp. 103–113, May 2026.

MLA

Chavali, R. V. P., A. Saeidi, S. N. Ratna Giri, and M. Salsabili. “Comparative Analysis of Traditional and Machine Learning Approaches for Estimating Undrained Shear Strength from SCPT Data”. Earth Sciences Research Journal, vol. 30, no. 1, May 2026, pp. 103-1, doi:10.15446/esrj.v30n1.121762.

Turabian

Chavali, Rama Vara Prasad, Ali Saeidi, Swamy Naga Ratna Giri, and Mohammad Salsabili. “Comparative Analysis of Traditional and Machine Learning Approaches for Estimating Undrained Shear Strength from SCPT Data”. Earth Sciences Research Journal 30, no. 1 (May 27, 2026): 103–113. Accessed July 20, 2026. https://revistas.unal.edu.co/index.php/esrj/article/view/121762.

Vancouver

1.
Chavali RVP, Saeidi A, Ratna Giri SN, Salsabili M. Comparative Analysis of Traditional and Machine Learning Approaches for Estimating Undrained Shear Strength from SCPT Data. Earth sci. res. j. [Internet]. 2026 May 27 [cited 2026 Jul. 20];30(1):103-1. Available from: https://revistas.unal.edu.co/index.php/esrj/article/view/121762

Download Citation

CrossRef Cited-by

CrossRef citations0

Dimensions

PlumX

Article abstract page views

132

Downloads

Download data is not yet available.

License

Copyright (c) 2026 Earth Sciences Research Journal

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Earth Sciences Research Journal holds a Creative Commons Attribution license. 

You are free to:

Share — copy and redistribute the material in any medium or format
Adapt — remix, transform, and build upon the material for any purpose, even commercially.
The licensor cannot revoke these freedoms as long as you follow the license terms.

The Earth Sciences Research Journal is the copyright holder for these license attributes.