Volume 3, Issue 1 — Year 2026 — Article e100052

ISSN (Online): 3115-8129 Biannually

Application of ANN, SVM, and Logistic Regression Models for Fine-Grained Soil Classification

Article Type: Research
Pages: e100052
DOI: https://doi.org/10.22034/CGEL.3.1.e100052
Crossmark
Open Access
Authors
Affiliations
  1. Department of Civil Engineering, Islamic Azad University - Bonab Branch, Bonab 5551785176, Iran
  2. Department of Civil Engineering, Tabriz Branch, Islamic Azad University, Tabriz 5158913791, Iran
Corresponding author
Email: fatemi_atabriz@gmail.com
Received: 18 February 2026 / Accepted: 12 March 2026 / Published: 25 May 2026
Abstract

This study evaluates the effectiveness of three machine learning models such as Artificial Neural Network (ANN), Support Vector Machine (SVM), and Logistic Regression (LR), for the classification of fine-grained soils based on index properties. A dataset comprising 1,257 samples was compiled through an extensive literature review. Each sample included key index parameters such as liquid limit (LL), plastic limit (PL), plasticity index (PI), and percentage of fines. The methodology involved preprocessing the data, normalizing features, and dividing the dataset into training (70%) and testing (30%) sets. Models were trained and validated using k-fold cross-validation (k=10), and their performance was assessed using accuracy, precision, recall, F1-score, and confusion matrices. The ANN model achieved the highest classification accuracy of 91.6%, followed by SVM at 88.3%, and LR at 84.9%. The mean squared error (MSE) for ANN, SVM, and LR were calculated as 0.078, 0.102, and 0.139, respectively. The ANN model also achieved the highest F1-score (0.92), indicating superior consistency in classification. These results highlight the potential of machine learning models, particularly ANN, for the reliable and automated classification of fine-grained soils using basic index properties.

Keywords

Fine-grained soils, Artificial neural network, Support vector machine, Logistic regression, Soil index properties

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 models classify fine-grained soils from index data
  • ANN achieves highest accuracy and F1 performance
  • Results enhance reliable automated soil classification
References
  1. Alade S.M. (2018). Correlation of unified and AASHTO soil classification systems for soils classification. Journal of Earth Sciences and Geotechnical Engineering, 8(1), 39-50.
  2. Al-Mamoori S.K., Jasem Al-Maliki L.A., Al-Sulttani A.H., El-Tawil K., Hussain H.M., Al-Ansari N. (2020). Horizontal and vertical geotechnical variations of soils according to USCS classification for the city of An-Najaf, Iraq using GIS. Geotechnical and Geological Engineering, 38(2), 1919-1938. https://doi.org/10.1007/s10706-019-01139-x.
  3. Aydın Y., Işıkdağ Ü., Bekdaş G., Nigdeli S.M., Geem Z.W. (2023). Use of machine learning techniques in soil classification. Sustainability, 15(3), 2374. https://doi.org/10.3390/su15032374.
  4. Azarafza M., Nanehkaran Y.A., Akgun H., Mao Y. (2021). Application of an image processing-based algorithm for river-side granular sediment gradation distribution analysis. Advanced Materials Research, 10(3), 229-244. https://doi.org/10.12989/amr.2021.10.3.229.
  5. Budhu M. (2010). Soil mechanics and foundations (3rd Edition). John Wiley & Sons, New Jersey, USA.
  6. Bullock M.D., Scalia I.V.J., Niemann J.D. (2024). Predicting unsaturated soil strength of coarse-grained soils for mobility assessments. Journal of Terramechanics, 115, 100977. https://doi.org/10.1016/j.jterra.2024.100977.
  7. Casagrande A. (1948). Classification and identification of soils. Transactions of the American Society of Civil Engineers, 113(1), 901-930. https://doi.org/10.1061/TACEAT.0006109.
  8. Castro G.M., Park J., Santamarina J. C. (2023). Revised soil classification system: implementation and engineering implications. Journal of Geotechnical and Geoenvironmental Engineering, 149(11), 04023109. https://doi.org/10.1061/JGGEFK.GTENG-10447.
  9. Dolinar B., Škrabl S. (2013). Atterberg limits in relation to other properties of fine-grained soils. Acta Geotechnica Slovenica, 10(2), 4-13.
  10. Edil T.B., Acosta H.A., Benson C.H. (2006). Stabilizing soft fine-grained soils with fly ash. Journal of Materials in Civil Engineering, 18(2), 283-294. https://doi.org/10.1061/(ASCE)0899-1561(2006)18:2(283).
  11. Erguler Z.A. (2016). A quantitative method of describing grain size distribution of soils and some examples for its applications. Bulletin of Engineering Geology and the Environment, 75, 807-819. https://doi.org/10.1007/s10064-015-0790-1.
  12. Freitag D.R. (1987). A proposed strength classification test for fine-grained soils. Journal of Terramechanics, 24(1), 25-39. https://doi.org/10.1016/0022-4898(87)90057-7.
  13. Gadouri H., Harichane K., Ghrici M. (2018). Assessment of sulphates effect on the classification of soil–lime–natural pozzolana mixtures based on the Unified Soil Classification System (USCS). International Journal of Geotechnical Engineering, 12(3), 293-301. https://doi.org/10.1080/19386362.2016.1275429.
  14. Ghaderi A., Shahri A.A., Larsson S. (2022). A visualized hybrid intelligent model to delineate Swedish fine-grained soil layers using clay sensitivity. Catena, 214, 106289. https://doi.org/10.1016/j.catena.2022.106289.
  15. Groenendyk D.G., Ferre T.P., Thorp K.R., Rice A.K. (2015). Hydrologic-process-based soil texture classifications for improved visualization of landscape function. PloS One, 10(6), e0131299. https://doi.org/10.1371/journal.pone.0131299.
  16. Heštera H., Pahernik M., Zelić B.K., Maljković M.M. (2023). The Unified Soil Classification System mapping of the Pannonian Basin in Croatia using multinominal logistic regression and inverse distance weighting interpolation. Rudarsko-Geološko-Naftni Zbornik, 38(3), 147-159. https://doi.org/10.17794/rgn.2023.3.12.
  17. Heydarian M., Doyle T.E., Samavi R. (2022). MLCM: Multi-label confusion matrix. IEEE Access, 10, 19083-19095. https://doi.org/10.1109/ACCESS.2022.3151048.
  18. Kasaragod A.K., Thomas J., Oommen T., Williams R., Paheding S., Angulo A.R., Ewing J., Cole M., Jayakumar P. (2024). Predicting USCS soil texture classes utilizing soil spectra and deep learning. Journal of Soils and Sediments, 24(11), 3594-3609. https://doi.org/10.1007/s11368-024-03921-8.
  19. Kayabali K., Balci M.C. (2013). An Appraisal of the Problems Related to the Classification of Fine-grained Soils. Electronic Journal of Geotechnical Engineering, 18, 2251-2262.
  20. Kim E.K., Kang Y.W., Christy A.D., Weatherington-Rice J. (2017). Predicting fractures in glacially related fine-grained materials and a synthetic soil of bentonite and sand using soil texture. Engineering Geology, 222, 84-91. https://doi.org/10.1016/j.enggeo.2017.03.007.
  21. Kim J., Kim D. (2018). Classification of inorganic natural fine-grained soils in Korea based on modified plasticity chart. Marine Georesources & Geotechnology, 36(5), 579-588. https://doi.org/10.1080/1064119X.2017.1354101.
  22. Kim M., Senturk M.A., Li L. (2024). Compression Index Regression of Fine-Grained Soils with Machine Learning Algorithms. Applied Sciences, 14(19), 8695. https://doi.org/10.3390/app14198695.
  23. Kirts S., Panagopoulos O.P., Xanthopoulos P., Nam B.H. (2018). Soil-compressibility prediction models using machine learning. Journal of Computing in Civil Engineering, 32(1), 04017067. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000713.
  24. Kotsiantis S.B., Zaharakis I.D., Pintelas P.E. (2006). Machine learning: a review of classification and combining techniques. Artificial Intelligence Review, 26, 159-190. https://doi.org/10.1007/s10462-007-9052-3.
  25. Kumar D., Kumari S. (2024). Assessment of liquefaction susceptibility of fine-grained soil based on soil classification. Indian Geotechnical Journal, 54(4), 1366-1380. https://doi.org/10.1007/s40098-023-00812-6.
  26. Liu C.Y., Ku C.Y., Wu T.Y., Ku Y.C. (2024). An Advanced Soil Classification Method Employing the Random Forest Technique in Machine Learning. Applied Sciences, 14(16), 7202. https://doi.org/10.3390/app14167202.
  27. Markoulidakis I., Markoulidakis G. (2024). Probabilistic Confusion Matrix: A Novel Method for Machine Learning Algorithm Generalized Performance Analysis. Technologies, 12(7), 113. https://doi.org/10.3390/technologies12070113.
  28. Mathur U., Kumar N., Pandey N.T., Choudhary A. (2017). Study of index properties of the soil. International Journal of Advance Research and Innovative Ideas in Education, 3, 656-661.
  29. Moreno-Maroto J.M., Alonso-Azcarate J. (2022). Evaluation of the USDA soil texture triangle through Atterberg limits and an alternative classification system. Applied Clay Science, 229, 106689. https://doi.org/10.1016/j.clay.2022.106689.
  30. Moreno-Maroto J.M., Alonso-Azcárate J., O'Kelly B.C. (2021). Review and critical examination of fine-grained soil classification systems based on plasticity. Applied Clay Science, 200, 105955. https://doi.org/10.1016/j.clay.2020.105955.
  31. Ngapgue F., Kenou W.C.G., Tchouata J.H.K., Tatapzia V.W.K., Mbakop Y.M. (2020). Geotechnical identification and classification of soils as flexible pavement subgrade of the section Fongo Tongo-Melong. Journal of Geoscience and Environment Protection, 8(11), 183-200. https://doi.org/10.4236/gep.2020.811012.
  32. O’Kelly B.C. (2021). Review of recent developments and understanding of Atterberg limits determinations. Geotechnics, 1(1), 59-75. https://doi.org/10.3390/geotechnics1010004.
  33. O’Kelly B.C., Alonso-Azcárate J., Moreno-Maroto J.M. (2023). A comprehensive review of soil remolding toughness determination and its use in the classification of fine-grained soils. Applied Sciences, 13(9), 5711. https://doi.org/10.3390/app13095711.
  34. Özdemir N., Gülser C. (2017). Clay activity index as an indicator of soil erodibility. Eurasian Journal of Soil Science, 6(4), 307-311. https://doi.org/10.18393/ejss.304519.
  35. Ozsagir M., Erden C., Bol E., Sert S., Özocak A. (2022). Machine learning approaches for prediction of fine-grained soils liquefaction. Computers and Geotechnics, 152, 105014. https://doi.org/10.1016/j.compgeo.2022.105014.
  36. Park J., Santamarina J.C. (2017). Revised soil classification system for coarse-fine mixtures. Journal of Geotechnical and Geoenvironmental Engineering, 143(8), 04017039. https://doi.org/10.1061/(ASCE)GT.1943-5606.0001705.
  37. Prakash K., Sridharan A. (2012). Classification of non-plastic soils. Indian Geotechnical Journal, 42, 118-123. https://doi.org/10.1007/s40098-012-0007-5.
  38. Reale C., Gavin K., Librić L., Jurić-Kaćunić D. (2018). Automatic classification of fine-grained soils using CPT measurements and Artificial Neural Networks. Advanced Engineering Informatics, 36, 207-215. https://doi.org/10.1016/j.aei.2018.04.003.
  39. Rehman H.U., Pouladi N., Pulido‐Moncada M., Arthur E. (2020). Repeatability and agreement between methods for determining the Atterberg limits of fine‐grained soils. Soil Science Society of America Journal, 84(1), 21-30. https://doi.org/10.1002/saj2.20001.
  40. Richter M., Kurpas M., Maska M.M. (2022). Learning by confusion approach to characterize phase transitions. arXiv:2206.15114v1. https://doi.org/10.48550/arXiv.2206.15114.
  41. Saikia A., Baruah D., Das K., Rabha H.J., Dutta A., Saharia A. (2017). Predicting compaction characteristics of fine-grained soils in terms of Atterberg limits. International Journal of Geosynthetics and Ground Engineering, 3, 18. https://doi.org/10.1007/s40891-017-0096-4.
  42. Sridharan A., Nagaraj H.B. (2000). Compressibility behaviour of remoulded, fine-grained soils and correlation with index properties. Canadian Geotechnical Journal, 37(3), 712-722. https://doi.org/10.1139/t99-128.
  43. Thompson M.R., Robnett Q.L. (1979). Resilient properties of subgrade soils. Transportation Engineering Journal of ASCE, 105(1), 71-89. https://doi.org/10.1061/TPEJAN.0000772.
  44. Vaughan P.R., Maccarini M., Mokhtar S.M. (1988). Indexing the engineering properties of residual soil. Quarterly Journal of Engineering Geology and Hydrogeology, 21(1), 69-84. https://doi.org/10.1144/GSL.QJEG.1988.021.01.05.
  45. Wang R., Wan S., Chen W., Qin X., Zhang G., Wang L. (2024). A novel finer soil strength mapping framework based on machine learning and remote sensing images. Computers & Geosciences, 182, 105479. https://doi.org/10.1016/j.cageo.2023.105479.
  46. Wesley L.D. (2003). Residual strength of clays and correlations using Atterberg limits. Geotechnique, 53(7), 669-672. https://doi.org/10.1680/geot.2003.53.7.669.
  47. Yousif A.A., Mohamed I.A. (2022). Prediction of compaction parameters from soil index properties case study: dam complex of upper Atbara project. American Journal of Pure and Applied Biosciences, 4(1), 01-09.
  48. Zhang H.Y., Li M., Wells R.R., Liu Q.J. (2019). Effect of soil water content on soil detachment capacity for coarse‐and fine‐grained soils. Soil Science Society of America Journal, 83(3), 697-706. https://doi.org/10.2136/sssaj2018.05.0208.
  49. Zolfaghari Z., Mosaddeghi M.R., Ayoubi S., Kelishadi H. (2015). Soil atterberg limits and consistency indices as influenced by land use and slope position in Western Iran. Journal of Mountain Science, 12, 1471-1483. https://doi.org/10.1007/s11629-014-3339-z.
How to cite
Akbari, A., & Fatemi, A. (2026). Application of ANN, SVM, and Logistic Regression Models for Fine-Grained Soil Classification. Civil and Geoengineering Letters, 3(1), e100052. https://doi.org/10.22034/CGEL.3.1.e100052
Note: Please verify the citation against your preferred style guide.
Share
X LinkedIn Facebook Email Mendeley
Article Metrics
329 Readers
239 Downloads
N/A Citations
PDF XML Back to Issue