Evaluation of the indirect tensile strength (ITS) of cement-treated clayey soils using XGBoost prediction model
Tóm tắt: 0
| 
PDF: 0 
##plugins.themes.academic_pro.article.main##
Author
Từ khóa:
Cement-stabilized soil
indirect tensile strength
XGBoost
machine learning
SHAP
pavement engineering
Tóm tắt
This study develops a data-driven framework using Extreme Gradient Boosting (XGBoost) to predict the Indirect Tensile Strength (ITS) of cement-treated clayey soils. Using 180 specimens with five input variables - cement content, curing time, curing temperature, plasticity index, and compaction energy - the model was trained (80%) and tested (20%), achieving strong accuracy (training R²=0.932, RMSE=55.41 kPa; testing R²=0.922, RMSE=81.98 kPa). SHapley Additive exPlanations (SHAP) analysis was applied for interpretability, showing cement content (39.3%) and curing time (30.1%) as the dominant predictors, followed by plasticity index (12.9%), while compaction energy (9.1%) and curing temperature (8.6%) had minor influence. K-means clustering combined with SHAP waterfall plots identified five distinct strength-development behavior groups, offering mechanistic insight into ITS variability. Overall, the XGBoost-SHAP framework proves to be a robust, interpretable tool for performance-based design and mixture optimization of cement-treated soils in infrastructure applications.
Tài liệu tham khảo
-
[1] J. K. Mitchell, K. Soga, and C. O'Sullivan, Fundamentals of Soil Behavior. John Wiley & Sons, 2025.
[2] J. Mallela, H. V. Quintus, and K. Smith, Consideration of Lime-Stabilized Layers in Mechanistic-Empirical Pavement Design, The National Lime Association, vol. 200, no. 1, pp. 1-40, 2004.
[3] K. Lemaire, D. Deneele, S. Bonnet, and M. Legret, “Effects of lime and cement treatment on the physicochemical, microstructural and mechanical characteristics of a plastic silt,” Engineering Geology, vol. 166, pp. 255-261, 2013.
[4] W. R. Hudson and T. W. Kennedy, “An indirect tensile test for stabilized materials,” Center for Highway Research, The University of Texas at Austin, Austin, TX, USA, Research Report No. 98-1, 1968.
[5] F. Sariosseiri and B. Muhunthan, “Effect of cement treatment on geotechnical properties of some Washington State soils,” Engineering Geology, vol. 104, no. 1-2, pp. 119-125, 2009.
[6] D. Xuan, L. Houben, A. Molenaar, and Z. Shui, “Mechanical properties of cement-treated aggregate material–a review,” Materials & Design, vol. 33, pp. 496-502, 2012.
[7] M. A. Shahin, M. B. Jaksa, and H. R. Maier, “Artificial neural network applications in geotechnical engineering,” Australian Geomechanics, vol. 36, no. 1, pp. 49-62, 2001.
[8] H. Moayedi, M. Mosallanezhad, A. S. A. Rashid, W. A. W. Jusoh, and M. A. Muazu, “A systematic review and meta-analysis of artificial neural network application in geotechnical engineering: theory and applications,” Neural Computing and Applications, vol. 32, no. 2, pp. 495-518, 2020.
[9] Q.-C. Truong and A.-T. N. Vu, “Machine Learning Applications for Chloride Ingress Prediction in Concrete: Insights from Recent Literature,” The University of Danang - Journal of Science and Technology, vol. 22, no. 11B, pp. 91-97, 2024, doi:10.31130/ud-jst.2024.528E.
[10] T. T. H. Truong and V. D. A. Huynh, “Estimating resilient modulus of subgrade soils using bagging-based ensemble model,” The University of Danang - Journal of Science and Technology, vol 5, no. 114.2, pp. 6-10, 2017.
[11] T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, Aug. 13–17, 2016. New York, NY, USA: ACM, 2016, pp. 785–794. https://doi.org/10.1145/2939672.2939785.
[12] T. Nguyen, D.-K. Ly, T. Q. Huynh, and T. T. Nguyen, “Soft computing for determining base resistance of super-long piles in soft soil: A coupled SPBO-XGBoost approach,” Computers and Geotechnics, vol. 162, p. 105707, 2023, doi: 10.1016/j.compgeo.2023.105707.
[13] S. M. Lundberg and S.-I. Lee, “A unified approach to interpreting model predictions,” in Advances in Neural Information Processing Systems, vol. 30, 2017, pp. 4765–4774.
[14] L. S. Shapley, “A value for n-person games,” in Contributions to the Theory of Games, vol. 2, no. 28, pp. 307–317, 1953.
[15] Y. Liu and A. Just, SHAPforxgboost: SHAP Plots for XGBoost, R package version 0.1.0, github.com, 2020. [Online]. Available: https://github.com/liuyanguu/SHAPforxgboost/ [Accessed March 01, 2026]
[16] B.-Q.-V. Nguyen, T.-H. Nguyen, and V.-C. Le, “An advanced machine learning-based mathematical equation for predicting compression index from readily available soil physical properties,” Geomechanics and Geoengineering, vol. 20, no. 4, pp. 788–804, 2025. https://doi.org/10.1080/17486025.2025.2455109.
[17] K. Yin, N. H. Dong, L. Li, W. Zhang, and J. Xu, “Indirect tensile strength of cement-treated soil under diverse curing conditions: From experimental characterization to prior-fitted transformer-based prediction,” Transportation Geotechnics, vol. 61, Art. no. 102098, 2026.
[18] N. H. Dong and K. Yin, “Indirect tensile strength of cement-stabilized soils: a hybrid experimental and literature dataset,” Mendeley Data, version 3, Mar. 20, 2026. [Online]. Available: https://doi.org/10.17632/gf5n7nb7hj.3 [Accessed March 01, 2026].
Xem thêm
##plugins.themes.academic_pro.article.sidebar##
Đã Xuất bản
Jul 31, 2026
Download
Cách trích dẫn
Pham, V.-N., H.-D. Do, T. P. K. Nguyen, V.-K. Tran, và D.-V. Le. “Evaluation of the Indirect Tensile Strength (ITS) of Cement-Treated Clayey Soils Using XGBoost Prediction Model”. Tạp Chí Khoa học Và Công nghệ Đại học Đà Nẵng, vol 24, số p.h 7B, Tháng Bảy 2026, tr 63-68, doi:10.31130/ud-jst.2026.24(7B).582E.
