Cover
Vol. 1 No. 1 (2025)

Published: December 14, 2025

Pages: 84-95

Research Article

Predictive Modeling of Soil Compaction Parameters Using Multiple Linear Regression and Support Vector Machines

Abstract

Field dry density is a soil compaction characteristic that is useful for geotechnical engineering design. Laboratory methods are laborious and time-consuming. The purpose of this paper is to determine and compare the effectiveness of MLR and SVM models in predicting this essential parameter from the fundamental soil property index level. A dataset of 86 soil samples with various geotechnical qualities was used, containing data such as gravel, sand, fines, liquid limit, and plastic limit. The dataset was split into 80% training and 20% testing. Using $R^{2},$ RMSE, and MSE, the performance of the built MLR and SVM prediction models was thoroughly examined. With an R2 value of 0.988 (on the test set), the SVM model outperforms the MLR model in terms of prediction accuracy for FDD $(R2=0.814)$. Compaction behavior and soil property index properties have a complicated relationship, as seen by the performance gap. According to feature importance analysis, the SVM model's predictions heavily relied on the fines content. According to this study, SVM is a useful method that geotechnical engineers can employ to quickly and affordably estimate compaction parameters in the early phases of site investigations and design optimization.

References

  1. Rathnam, U., & Prasad, K. (2020). ASSESSMENT OF COMPRESSION BEHAVIOUR OF COMPACTED SOILS. INTERNATIONAL JOURNAL OF CIVIL ENGINEERING AND TECHNOLOGY (IJCIET). https://doi.org/10.34218/ijciet.11.3.2020.001.
  2. Hussain, S. (2017). Effect of Compaction Energy on Engineering Properties of Expansive Soil. Civil Engineering Journal, 3, 610-616. https://doi.org/10.28991/CEJ-030988.
  3. Ali, H. F. H., Omer, B., Mohammed, A. S., & Faraj, R. H. (2024). Predicting the maximum dry density and optimum moisture content from soil index properties using efficient soft computing techniques. Neural Computing and Applications, 36(19), 11339-11369.
  4. Li, B., You, Z., Ni, K., & Wang, Y. (2024). Prediction of Soil Compaction parameters using machine learning models. Applied Sciences, 14(7), 2716.
  5. Nazari, Z., Tabarsa, A., & Latifi, N. (2021). Effect of compaction delay on the strength and consolidation properties of cement-stabilized subgrade soil. Transportation Geotechnics, 27, 100495.
  6. Tilahun, Y., Qinghua, X., Ashango, A. A., & Han, X. (2024). Determination of Compaction Parameters of Cement‐Lime Soils: Boosting‐Based Ensemble Models. International Journal for Numerical and Analytical Methods in Geomechanics, 48(18), 4365-4382.
  7. ASTM International. (2012). Standard Test Methods for Laboratory Compaction Characteristics of Soil Using Standard Effort (12 400 ft-lbf/ft3 (600 kN-m/m3)) (ASTM D698-12). ASTM International.
  8. ASTM D1557 (2012). Standard test methods for laboratory compaction characteristics of soil using modified effort (56,000 ft-lbf/ft3 (2,700 kN-m/m3)). ASTM International.
  9. Proctor, R. R. (1933). Description of field and laboratory methods. Engineering News-Record, 111(10), 286-289.
  10. Zvonarić, M., Barišić, I., Galić, M., & Minažek, K. (2021). Influence of laboratory compaction method on compaction and strength characteristics of unbound and cement-bound mixtures. Applied Sciences, 11(11), 4750.
  11. Cerni, G., Cardone, F., Virgili, A., & Camilli, S. (2012). Characterisation of permanent deformation behaviour of unbound granular materials under repeated triaxial loading. Construction and Building Materials, 28(1), 79-87.
  12. Simatupang, E. C., Sari, P., & Gunawan, H. (2023). Proctor Application Benefits in Post Pandemic Online Test Implementation. Jurnal Sinestesia, 13(2), 995-1000.
  13. Jamshidi Chenari, R., Tizpa, P., Ghorbani Rad, M. R., Machado, S. L., & Karimpour Fard, M. (2015). The use of index parameters to predict soil geotechnical properties. Arabian Journal of Geosciences, 8(7), 4907-4919.
  14. Abdella, D., Abebe, T., & Quezon, E. T. (2017). Regression analysis of index properties of soil as strength determinant for California bearing ratio (CBR). Gsj, 5(6), 1.
  15. Ramiah, B.K., Viswanath, V., Krishnamurthy, H.V., 1970. Interrelationship of compaction and index properties. In: Proceedings of the Second Southeast Asian Conference on Soil Engineering, Singapore, 577, 577–587.
  16. Gurtug, Y., & Sridharan, A. (2004). Compaction behaviour and prediction of its characteristics of fine grained soils with particular reference to compaction energy. Soils and foundations, 44(5), 27-36.
  17. Almuaythir, S., Zaini, M. S. I., & Lodhi, R. H. (2025). Predicting soil compaction parameters in expansive soils using advanced machine learning models: a comparative study. Scientific Reports, 15(1), 24018.
  18. Hasnat, A., Hasan, M. M., Islam, M. R., & Alim, M. A. (2019). Prediction of compaction parameters of soil using support vector regression. Curr. Trends Civ. Struct. Eng, 4(1), 1-7.
  19. Jalal, F. E., Xu, Y., Iqbal, M., Jamhiri, B., & Javed, M. F. (2021). Predicting the compaction characteristics of expansive soils using two genetic programming-based algorithms. Transportation Geotechnics, 30, 100608.
  20. Karimpour-Fard, M., Machado, S. L., Falamaki, A., Carvalho, M. F., & Tizpa, P. (2019). Prediction of compaction characteristics of soils from index test’s results. Iranian Journal of Science and Technology, Transactions of Civil Engineering, 43(Suppl 1), 231-248.
  21. Sinha, S. K., & Wang, M. C. (2008). Artificial neural network prediction models for soil compaction and permeability. Geotechnical and Geological Engineering, 26(1), 47-64.
  22. Tenpe, A., & Kaur, S. (2015). Artificial neural network modeling for predicting compaction parameters based on index properties of soil. International Journal of Science and Research, 4(7), 1198-1202.
  23. Rowan, H. W., & Graham, W. W. (1948). Proper compaction eliminates curing period in construction fills. Civil Engineering, 18(7), 50-51.
  24. Zhao, T., Shen, F., & Xu, L. (2024). Review and comparison of machine learning methods in developing optimal models for predicting geotechnical properties with consideration of feature selection. Soils and Foundations, 64(6), 101523.