Integrating Atterberg Limits with Machine Learning for Screening-Scale Prediction of Volumetric Behavior in Pathum Thani Clay Soils

Authors

  • Rattanachot Thongpong Faculty of Industrial Technology, Valaya Alongkorn Rajabhat University under the Royal Patronage, Thailand
  • Pattaraporn Nueasri Faculty of Industrial Technology, Valaya Alongkorn Rajabhat University under the Royal Patronage, Thailand

DOI:

https://doi.org/10.55003/ETH.420408

Keywords:

Atterberg Limits, Polynomial regression, Random Forest, SVR, Volumetric prediction

Abstract

This study investigates the predictive relationship between Atterberg limits and the volumetric ratio behavior (VLL, VPL, and VSL) of tropical clay soils. Laboratory testing, following ASTM D4318, was conducted on 50 clay samples collected from Pathum Thani Province, Thailand. Estimated volumetric ratios were derived from mass–moisture–density relationships representing liquid, plastic, and shrinkage states. Linear, polynomial, and machine learning models, including Random Forest and Support Vector Regression (SVR), were developed to evaluate the statistical association between index parameters and volume change behavior. The models showed weak-to-moderate correlation (R² = 0.31–0.55), indicating that the derived relationships can provide qualitative insights rather than quantitative predictions, supporting a conceptual understanding of soil volume behavior. The Shrinkage Limit (SL) consistently emerged as the most influential parameter, reflecting its strong association with moisture-induced volume reduction and soil–water interaction mechanisms. The results suggest that Atterberg limits can serve as qualitative indicators of volumetric change potential rather than quantitative predictors. Although the models exhibited low explanatory power, they provide transparent, reproducible insights into how index-based soil properties correspond to volumetric transitions. This framework supports early-stage and cost-effective assessment of expansive soils, offering a practical foundation for identifying shrink–swell tendencies before advanced testing. The approach contributes to improving preliminary geotechnical evaluation practices in tropical environments and establishes a reference for future validation incorporating mineralogical and suction-related parameters.

References

G. S. Dasog, D. F. Acton, A. R. Mermut and E. de Jong, “SHRINK-SWELL POTENTIAL AND CRACKING IN CLAY SOILS OF SASKATCHEWAN,” Canadian Journal of Soil Science, vol. 68, no. 2, pp. 251–260, 1988, doi: 10.4141/cjss88-025.

A. D. Karathanasis and B. F. Hajek, “Shrink–Swell Potential of Montmorillonitic Soils in Udic Moisture Regimes,” Soil Science Society of America Journal, vol. 49, no. 1, pp. 159–166, 1985, doi: 10.2136/sssaj1985.03615995004900010033x.

K. Bhavya and H. B. Nagaraj, “Influence of soil structure and clay mineralogy on Atterberg limits,” Scientific Reports, vol. 15, no. 1, 2025, Art. no. 15459, doi: 10.1038/s41598-025-98729-y.

E. Polidori, “Relationship Between the Atterberg Limits and Clay Content,” Soils and Foundations, vol. 47, no. 5, pp. 887–896, 2007, doi: 10.3208/sandf.47.887.

S. Shimobe and G. Spagnoli, “Relationships between strength properties and Atterberg limits of fine-grained soils,” Geomechanics and Geoengineering, vol. 17, no. 12, pp. 1443–1457, 2022, doi: 10.1080/17486025.2021.1940317.

B. S. Firincioglu and H. Bilsel, “Unified Plasticity Potential of Soils,” applied sciences, vol. 13, no. 13, 2023, Art. no. 7889, doi: 10.3390/app13137889.

V. H. R. Barbosa, M. E. S. Marques and A. C. R. Guimarães, “Predicting Soil Swelling Potential Using Soil Classification Properties,” Geotechnical and Geological Engineering, vol. 41, no. 8, pp. 4445–4457, 2023, doi: 10.1007/s10706-023-02525-2.

K. Prakash and A. Sridharan, “Free Swell Ratio and Clay Mineralogy of Fine-Grained Soils,” Geotechnical Testing Journal, vol. 27, no. 2, pp. 220–225, 2004, doi: 10.1520/gtj10860.

D. G. Fredlund and A. Xing, “Equations for the soil-water characteristic curve,” Canadian Geotechnical Journal, vol. 31, no. 4, pp. 521–532, 1994, doi: 10.1139/t94-061.

E. U. Eyo, S. J. Abbey, T. T. Lawrence and F. K. Tetteh, “Improved prediction of clay soil expansion using machine learning algorithms and meta-heuristic dichotomous ensemble classifiers,” Geoscience Frontiers, vol. 13, no. 1, 2022, Art. no. 101296, doi: 10.1016/j.gsf.2021.101296.

S. K. Das, P. Samui, A. K. Sabat and T. G. Sitharam, “Prediction of swelling pressure of soil using artificial intelligence techniques,” Environmental Earth Sciences, vol. 61, no. 2, pp. 393–403, 2009, doi: 10.1007/s12665-009-0352-6.

A. Al-Taie, M. Disfani, R. Evans, A. Arulrajah and S. Horpibulsuk, “Volumetric Behavior and Soil Water Characteristic Curve of Untreated and Lime-Stabilized Reactive Clay,” International Journal of Geomechanics, vol. 19, no. 2, 2019, Art. no. 04018192, doi: 10.1061/(asce)gm.1943-5622.0001336.

H. Komine and N. Ogata, “Prediction for swelling characteristics of compacted bentonite,” Canadian Geotechnical Journal, vol. 33, no. 1, pp. 11–22, 1996, doi: 10.1139/t96-021.

Y. Yukselen and A. Kaya, “Suitability of the methylene blue test for surface area, cation exchange capacity and swell potential determination of clayey soils,” Engineering Geology, vol. 102, no. 1–2, pp. 38–45, 2008, doi: 10.1016/j.enggeo.2008.07.002.

H. Elbadry, “Simplified reliable prediction method for determining the volume change of expansive soils based on simple physical tests,” HBRC Journal, vol. 13, no. 3, pp. 353–360, 2017, doi: 10.1016/j.hbrcj.2015.10.001.

Standard Test Methods for Liquid Limit, Plastic Limit, and Plasticity Index of Soils, ASTM D4318-17, ASTM International, West Conshohocken, PA, USA, Apr. 17, 2018.

J. K. Mitchell and K. Soga, “Soil–Water–Chemical Interactions,” in Fundamentals of Soil Behavior, 3rd ed., Hoboken, NJ, USA: John Wiley & Sons, 2005, ch. 6, sec. 6.3–6.5, pp. 209–259.

I. Yilmaz and O. Kaynar, “Multiple regression, ANN (RBF, MLP) and ANFIS models for prediction of swell potential of clayey soils,” Expert Systems with Applications, vol. 38, no. 5, pp. 5958–5966, 2011, doi: 10.1016/j.eswa.2010.11.027.

A. Sridharan and K. Prakash, “Mechanism Controlling the Shrinkage Limit of Soils,” Geotechnical Testing Journal, vol. 21, no. 3, pp. 240–250, 1998, doi: 10.1520/gtj10897j.

A. Sridharan and K. Prakash, “Shrinkage Limit of Soil Mixtures,” Geotechnical Testing Journal, vol. 23, no. 1, pp. 3–8, 2000, doi: 10.1520/gtj11118j.

P. J. Thomas, J. C. Baker and L. W. Zelazny, “An Expansive Soil Index for Predicting Shrink–Swell Potential,” Soil Science Society of America Journal, vol. 64, no. 1, pp. 268–274, 2000, doi: 10.2136/sssaj2000.641268x.

Downloads

Published

2025-11-11

How to Cite

[1]
R. Thongpong and P. Nueasri, “Integrating Atterberg Limits with Machine Learning for Screening-Scale Prediction of Volumetric Behavior in Pathum Thani Clay Soils”, Eng. & Technol. Horiz., vol. 42, no. 4, p. 420408, Nov. 2025.

Issue

Section

Research Articles