Volume 3, Issue 1 — Year 2026 — Article e100060

ISSN (Online): 3115-8129 Biannually

Prediction of Bearing Capacity of Clean Sand using Machine Learning Algorithms based on SPT Data

Article Type: Research
Pages: e100060
DOI: https://doi.org/10.22034/CGEL.3.1.e100060
Crossmark
Open Access
Authors
Affiliations
  1. Department of Civil Engineering, Central Tehran Branch, Islamic Azad University, Tehran 1955847781, Iran
  2. Department of Civil Engineering, Central Tehran Branch, Islamic Azad University, Tehran 1955847781, Iran
  3. Department of Civil Engineering, Industrial University of Ho Chi Minh City, Ho Chi Minh City 084, Vietnam
  4. Department of Civil Engineering, Industrial University of Ho Chi Minh City, Ho Chi Minh City 084, Vietnam
  5. Department of Mechanic Dynamics, Vinh Long University of Technology Education, Vinh Long 85000, Vietnam
Corresponding author
Email: doannhatphi@iuh.edu.vn
ORCID: 0000-0003-3953-5443
Received: 10 March 2026 / Accepted: 28 April 2026 / Published: 25 May 2026
Abstract

Accurate estimation of the bearing capacity of clean sand is a critical task in foundation design, especially in regions where granular soils dominate. Conventional empirical approaches may not fully capture the inherent variability and complex interactions among soil parameters. This study explores the use of machine learning (ML) techniques to predict the ultimate bearing capacity of clean sand based on Standard Penetration Test (SPT) data. A curated dataset of 150 geotechnical records specifically involving clean, well-graded sand (SP and SW according to the Unified Soil Classification System) was compiled. The data were collected from the NCEER database and validated case studies from peer-reviewed journals focusing on sandy soil profiles. Each data entry includes SPT N-values, relative density, dry unit weight, moisture content, and test depth. Four ML models, such as Linear Regression, Decision Tree, Random Forest, and Artificial Neural Network (ANN) were developed and tested using Python’s Scikit-learn and TensorFlow libraries. Model performance was assessed using R², RMSE, and MSE metrics. The Random Forest model yielded the most accurate predictions, with an R² value of 0.93 and a low RMSE, indicating a strong correlation between input features and bearing capacity in clean sand. This study demonstrates that ML-based prediction models can significantly enhance geotechnical design reliability in sandy soils and reduce the reliance on simplified empirical charts and conservative assumptions.

Keywords

Clean sand, SPT, Machine learning, Bearing capacity, Random forest

Data availability statement

The data supporting the findings of this study are available within article. No publicly archived dataset was generated.

Funding

This research received no external funding.

Highlights
  • ML–bearing capacity relation in clean sand using SPT
  • Random Forest shows highest accuracy among models
  • Results support design and reduce empirical reliance
References
  1. Akca N. (2003). Correlation of SPT–CPT data from the United Arab Emirates. Engineering Geology, 67(3-4), 219-231. https://doi.org/10.1016/S0013-7952(02)00181-3.
  2. Al-Khafaji A.W., Andersland O.B. (2006). Simplified Foundation Engineering. Waveland Press.
  3. Anderson J.B., Townsend F.C. (2001). SPT and CPT testing for evaluating lateral loading of deep foundations. Journal of Geotechnical and Geoenvironmental Engineering, 127(11), 920-925. https://doi.org/10.1061/(ASCE)1090-0241(2001)127:11(920).
  4. Arbi S.J., Rehman Z.U., Hassan W., Khalid U., Ijaz N., Maqsood Z., Haider A. (2025). Optimized machine learning-based enhanced modeling of pile bearing capacity in layered soils using random and grid search techniques. Earth Science Informatics, 18(4), 332. https://doi.org/10.1007/s12145-025-01784-2.
  5. Bowles J.E. (1997). Foundation Analysis and Design. McGraw-Hill, New York, USA.
  6. 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. https://doi.org/10.1016/j.enggeo.2008.10.010.
  7. Chen W., Huang H., Li R., Chen L., Jiang Z., Xiong F., Guan W., Zhang S., Tian B. (2021). Revisiting movable fluid space in tight fine-grained reservoirs: a case study from Shahejie shale in the Bohai Bay Basin, NE China. Journal of Petroleum Science and Engineering, 207, 109170. https://doi.org/10.1016/j.petrol.2021.109170.
  8. Das B.M., Sabat A.K. (1997). A simple method for estimating ultimate bearing capacity from SPT. Geotechnical and Geological Engineering, 15(3), 211-218.
  9. De Beer E.E. (1970). The use of static penetration results for the calculation of settlement and bearing capacity of foundations. Géotechnique, 20(4), 387-411.
  10. Dung N.T., Chung S.G., Kim S.R., Beak S.H. (2011). Applicability of the SPT-based methods for estimating toe bearing capacity of driven PHC piles in the thick deltaic deposits. KSCE Journal of Civil Engineering, 15, 1023-1031. https://doi.org/10.1007/s12205-011-0801-0.
  11. Esmaeili M., Tavakoli B. (2019). Finite element method simulation of explosive compaction in saturated loose sandy soils. Soil Dynamics and Earthquake Engineering, 116, 446-459. https://doi.org/10.1016/j.soildyn.2018.09.048.
  12. Farhangi V., Karakouzian M., Geertsema M. (2020). Effect of micropiles on clean sand liquefaction risk based on CPT and SPT. Applied Sciences, 10(9), 3111. https://doi.org/10.3390/app10093111.
  13. Ghorbani B., Sadrossadat E., Bolouri Bazaz J., Rahimzadeh Oskooei P. (2018). Numerical ANFIS-based formulation for prediction of the ultimate axial load bearing capacity of piles through CPT data. Geotechnical and Geological Engineering, 36, 2057-2076. https://doi.org/10.1007/s10706-018-0445-7.
  14. Golafzani S.H., Chenari R.J., Eslami A. (2020). Reliability based assessment of axial pile bearing capacity: static analysis, SPT and CPT-based methods. Georisk: Assessment and management of risk for Engineered Systems and Geohazards, 14(3), 216-230. https://doi.org/10.1080/17499518.2019.1628281.
  15. Hatanaka M., Uchida A. (1996). Empirical correlation between penetration resistance and effective friction angle of sandy soils. Soils and Foundations, 36(4), 1-9.
  16. Hung L.C., Nguyen T.D., Lee J.H., Kim S.R. (2016). Applicability of CPT-based methods in predicting toe bearing capacities of driven piles in sand. Acta Geotechnica, 11, 359-372. https://doi.org/10.1007/s11440-015-0398-4.
  17. Jamiolkowski M. (2012). Role of geophysical testing in geotechnical site characterization. Soils and Rocks, 35(2), 117-137.
  18. Jarushi F., AlKaabim S., Cosentino P. (2015). A new correlation between SPT and CPT for various soils. International Journal of Environmental, Ecological, Geological and Geophysical Engineering, 9(2), 101-107.
  19. Jarushi F.H., Hamuda S.S., Aldawi M. (2016). Correlation between the Standard Penetration Test and the Dynamic Cone Penetration Test for Sandy Soil. BSc thesis, University of Tripoli, Libya. https://doi.org/10.13140/RG.2.2.29128.67849.
  20. Jinguuji M., Toprak S. (2017). A case study of liquefaction risk analysis based on the thickness and depth of the liquefaction layer using CPT and electric resistivity data in the Hinode area, Itako City, Ibaraki Prefecture, Japan. Exploration Geophysics, 48(1), 28-36. https://doi.org/10.1071/EG16137.
  21. Khandaker N.I., Schleifer S. (2015). Geoengineering Constraints on Foundation: Case Study from Queens, New York City, USA. Journal of Earth Sciences and Geotechnical Engineering, 5(14), 35-67.
  22. Khodayari M.R., Mousavizadeh S.M., Ahmadi M.M. (2024). Analysis of pile end bearing capacity in Holocene interlayered silty deposits based on CPT soil behavior type index. Engineering Geology, 337, 107597. https://doi.org/10.1016/j.enggeo.2024.107597.
  23. Kumar P., Sharma R.S. (2009). Estimation of bearing capacity of shallow foundations using SPT and multivariate regression. International Journal of Geotechnical Engineering, 3(2), 295-301.
  24. Lee J.H., Kim H.K., Cho G.C. (2010). SPT-based empirical correlation for bearing capacity on granular soils in Korea. Soils and Foundations, 50(2), 241-247.
  25. Leetsaar L., Korkiala-Tanttu L., Kurnitski J. (2023). CPT, CPTu and DCPT methods for predicting the ultimate bearing capacity of cast in situ displacement piles in silty soils. Geotechnical and Geological Engineering, 41(2), 631-652. https://doi.org/10.1007/s10706-022-02292-6.
  26. Lingwanda M.I., Larsson S., Nyaoro D.L. (2015). Correlations of SPT, CPT and DPL data for sandy soil in Tanzania. Geotechnical and Geological Engineering, 33, 1221-1233. https://doi.org/10.1007/s10706-015-9897-1.
  27. Meyerhof G.G. (1956). Penetration tests and bearing capacity of cohesionless soils. Journal of the Soil Mechanics and Foundations Division, ASCE, 82(1), 1-19.
  28. Mohamed F.M., Vanapalli S.K. (2015). Bearing capacity of shallow foundations in saturated and unsaturated sands from SPT–CPT correlations. International Journal of Geotechnical Engineering, 9(1), 2-12. https://doi.org/10.1179/1939787914Y.0000000082.
  29. Peck R.B., Hanson W.E., Thornburn T.H. (1974). Foundation Engineering. Wiley, New York, USA.
  30. Poor M.M., Azarafza M., Derakhshani R. (2023). A correlation based on pressuremeter, SPT and CPT tests for characterizing of coastal alluvium: A study for phase 14 South Pars, Iran. MethodsX, 10, 101938. https://doi.org/10.1016/j.mex.2022.101938.
  31. Rahman M., Zhang J. (2023). Ensemble machine learning models for SPT-based bearing capacity prediction in clean sands. Soils and Foundations, 63(1), 121-134. https://doi.org/10.1016/j.sandf.2022.12.005.
  32. Ray R., Kumar D., Samui P., Roy L.B., Goh A.T.C., Zhang W. (2021). Application of soft computing techniques for shallow foundation reliability in geotechnical engineering. Geoscience Frontiers, 12(1), 375-383. https://doi.org/10.1016/j.gsf.2020.05.003.
  33. Salgado R., Sakleshpur V.A., Prezzi M., Zaheer M. (2021). CPT-based geotechnical design manual, Volume 2: CPT-based design of foundations—Methods. Joint Transportation Research Program Publication No. FHWA/IN/JTRP-2021/23. West Lafayette, IN: Purdue University. https://doi.org/10.5703/1288284317347.
  34. Seo S., Kim G., Park J.B., Kim J., Park Y.B., Chung M. (2025). Leveraging data-driven machine learning techniques to enhance bearing capacity estimation in prebored and precast piles. Expert Systems with Applications, 285, 128070. https://doi.org/10.1016/j.eswa.2025.128070.
  35. Shioi Y., Fukui J. (1982). Application of N-value to design of foundation in Japan. In: Proceedings of the 2nd European Symposium on Penetration Testing (ESOPT II), Amsterdam, 2, 159-164.
  36. Souza J.M.S., Danziger B.R., Danziger F.A.B. (2012). The influence of the relative density of sands in SPT and CPT correlations. Soils and Rocks, 35(1), 99-113.
  37. Tan T.S., Yuen C.W. (2003). Bearing capacity of shallow foundations on granular fill over soft soil using SPT data. SEAGS Geotechnical Engineering Journal, 34(1), 11-19.
  38. Teng W.C. (1962). Foundation Design. Prentice-Hall, Englewood Cliffs, New Jersey, USA.
  39. Terzaghi K., Peck R.B. (1948). Soil Mechanics in Engineering Practice. John Wiley & Sons, New York, USA.
  40. Wei Y., Wang D., Li J., Jie Y., Ke Z., Li J., Wong T. (2020). Evaluation of ultimate bearing capacity of pre-stressed high-strength concrete pipe pile embedded in saturated sandy soil based on in-situ test. Applied Sciences, 10(18), 6269. https://doi.org/10.3390/app10186269.
  41. Zeini H.A., Seno M.E., Shehab E.Q., Abood E.A., Imran H., Bernardo L.F.A., Ribeiro T.P. (2025). Predicting the Bearing Capacity of Shallow Foundations on Granular Soil Using Ensemble Machine Learning Models. Geotechnics, 5(3), 57. https://doi.org/10.3390/geotechnics5030057.
  42. Zhang D.M., Jiang Q.H., Zhang J.Z., Huang H.W. (2024). Bearing capacity of shallow foundations considering geological uncertainty and soil spatial variability. Acta Geotechnica, 19(6), 3961-3977. https://doi.org/10.1007/s11440-023-02091-0.
  43. Zhang L., Chen J.J. (2012). Effect of spatial correlation of standard penetration test (SPT) data on bearing capacity of driven piles in sand. Canadian Geotechnical Journal, 49(4), 394-402. https://doi.org/10.1139/t2012-005.
How to cite
Amiri, A., Niromand, A., Nguyen, B., Doan, N., & Doan, D. T. (2026). Prediction of Bearing Capacity of Clean Sand using Machine Learning Algorithms based on SPT Data. Civil and Geoengineering Letters, 3(1), e100060. https://doi.org/10.22034/CGEL.3.1.e100060
Note: Please verify the citation against your preferred style guide.
Share
X LinkedIn Facebook Email Mendeley
Article Metrics
409 Readers
282 Downloads
N/A Citations
PDF XML Back to Issue