Hybrid Naive Bayes (DAOA+SAO) Model for CBR of Rice Husk Ash Amended Geotechnical Soils
DOI:
https://doi.org/10.22399/ijcesen.4808Keywords:
Expansive Soil, Rice Husk Ash, Soil Stabilization, Machine Learning, Naive Bayes, Optimization AlgorithmsAbstract
This paper presents an integrated experimental-computational methodology for the characterization of expansive clay stabilised with rice husk ash (RHA) prolific agro-industrial residue possessing abundance of reactive silica. The clay was mixed with 0-20% dried RHA, based on dry mass, and was tested under Proctor compaction, CBR, and triaxial loading in 102 specimens. New compound feature indices were developed to assess the pozzolanic reactivity (attributed to its high amorphous SiO₂ content) and the particle-packing effects of RHA in the soil matrix. A Gaussian Naive Bayes was also used to classify specimens to ranges of index tests (low, medium, high, and extreme) based on input including RHA dose, dry density and plasticity index. This classification performed very well (≈ 97% accuracy on held-out data), and the feature-importance analysis confirms that the predominant features are the RHA content and the compaction energy. Meanwhile, a hybrid regression model is proposed to predict CBR, where a Gaussian NB base model is integrated with two complementary metaheuristic optimizers, the DAOA and the SAO are, to adjust the model weighting and thresholds. This NB, DAOA, SAO one achieves nearly perfect prediction accuracy (cross-validated R²≈ 0.99), and ultralow RMSE/MAE for CBR, which significantly outperforms a standalone NB and any of the single-optimizer formulas. In combination, this compound-feature, dual optimizer NB model is, to the best of our knowledge, the first of its kind in geotechnical results forecasting applications, and offers speedy, dependable assessments of strength and bearing properties of soil.
References
[1] F. H. Chen, Foundations on Expansive Soils, Elsevier, 1975.
[2] N. Rahaja, A. K. Gupta, and K. Kanwar, "Enhancing Soil Stability: The Impact of Rice
Husk Ash on Expansive Soil Behavior," E3S Web of Conferences, vol. 596, p. 01011, 2024.
[3] Rahaja, N., Gupta, A.K., & Kanwar, K. (2024). The Nexus of Soil Stabilization and Biomedical
Waste Recycling: Lime, RHA, And Microfine Slag Applications. African Journal of Biomedical
Research.
[4] K. J. Osinubi, “Influence of compactive efforts on lime-slag treated tropical black clay,” J. Mater.
Civ. Eng., vol. 18, pp. 175–181, 2006.
[5] E. Kalkan and S. Akbulut, “The positive effects of silica fume on the permeability, swelling pressure and compressive strength of natural clay liners,” Eng. Geol., vol. 73, pp. 145–156, May 2004.
[6] S. Akbulut and S. Arasan, “The variations of cation exchange capacity, pH, and zeta potential in expansive soils treated by additives,” Int. J. Civ. Struct. Eng., vol. 1, no. 2, pp. 139–154, 2010
[7] A. K. Sabat and R. P. Nanda, "Effect of marble dust on strength and durability of rice husk ash stabilised expansive soil," Int. J. Civ. Struct. Eng., vol. 1, no. 4, 2011
[8] F. H. Ali, A. Aminuddin & C. K. Choy, “Use of rice husk ash to enhance lime treatment of soil,” Can. Geotech. J., vol. 29, pp. 843–852, 1992.
[9] N. Ceryan, U. Okkan, and A. Kesima, "Prediction of unconfined compressive strength of carbonate rocks using artificial neural networks," Environ. Earth Sci., vol. 68, pp. 807–819, 2013.
[10] M. I. Hoque, M. Abdallah, M. Hasan, M. S. Islam, and M. H. R. Sobuz, "Machine learning methods to predict and analyse unconfined compressive strength of stabilised soft soil with polypropylene columns," Cogent Eng., vol. 10, no. 1, 2023
[11] S. Wang, A. G. Hussien, S. Kumar, I. AlShourbaji, and F. A. Hashim, "A modified smell agent optimization for global optimization and industrial engineering design problems," J. Comput. Des. Eng., vol. 10, pp. 2147–2176, 2023.
[12] A. Salawudeen, M. T. Abolhasani, M. M. Alhaji, and A. A. Babar, "Development of Smell Agent Optimization," Knowl. Based Syst., vol. 232, p. 107486, 2021,
[13] Das, S.K., Samui, P. & Sabat, A.K. Application of Artificial Intelligence to Maximum Dry Density and Unconfined Compressive Strength of Cement Stabilized Soil. Geotech Geol Eng 29, 329–342 (2011).
[14] I. Das, A. Stein, N. Kerle, and V. K. Dadhwal, “Landslide susceptibility mapping along road corridors in the Indian Himalayas using Bayesian logistic regression models,” Geomorphology, vol. 179, pp. 116–125, 2012
[15] C. Das, S. K. Samui, and A. K. Sabat, “Application of AI to UCS of cement stabilised soil,” Geotech. Geol. Eng., vol. 29, pp. 329–342, 2011
[16] L. K. Sharma and T. N. Singh, “Regression based models for the prediction of unconfined compressive strength of artificially structured soil,” Eng. Comput., vol. 34, no. 1, pp. 175–186, 2018.
[17] T. Li, “Estimating unconfined compressive strength using a hybrid model of machine learning and metaheuristic algorithms,” Signal, Image and Video Processing, vol. 19, Art. no. 164, 2025
[18] K. C. Onyelowe, F. I. Aneke, M. E. Onyia, A. M. Ebid, and T. Usungedo, “AI (ANN, GP, and EPR)-based predictive models of bulk density, linear volumetric shrinkage & desiccation cracking of HSDA treated black cotton soil for sustainable subgrade,” Geomech. Geoeng., vol. 18, no. 6, pp. 497 516, 2023.
[19] K. C. Onyelowe, A. M. Ebid, M. E. Onyia, and L. I. Nwobia, “Predicting nanocomposite binder improved unsaturated soil UCS using genetic programming,” Nanotechnology for Environmental Engineering, vol. 6, art. no. 39, 2021
[20] K. Sahoo, P. Sarkar, and R. P. Davis, “Artificial neural networks for prediction of compressive strength of recycled aggregate concrete,” Int. J. Res. Chem. Metall. Civ. Eng., vol. 3, no. 1, 2016,.
[21] A. M. Ebid, L. I. Nwobia, and K. C. Onyelowe, “Predicting nanobinder improved unsaturated soil consistency limits using genetic programming and artificial neural networks,” Appl. Comput. Intell. Soft Comput., vol. 2021, Art. ID 5992628, pp. 1–13, 2021.
[22] IS: 1498-1970, “Classification and Identification of Soils for General Engineering Purposes,” Bureau of Indian Standards, New Delhi, India.
[23] IS: 2720 Part-3 Sec 1 (1980), “Determination of Specific Gravity,” Bureau of Indian Standards, New Delhi, India.
[24] IS: 2720 Part-4 (1985), “Grain Size Analysis,” Bureau of Indian Standards, New Delhi, India.
[25] IS: 2720 Part-5 (1985), “Determination of Liquid and Plastic Limit,” Bureau of Indian Standards, New Delhi, India.
[26] IS: 2720 Part-7 (1980), “Moisture-Dry Unit Weight Relations,” Bureau of Indian Standards, New Delhi, India.
[27] IS: 2720 Part-9 (1993), “Shear Strength Parameters,” Bureau of Indian Standards, New Delhi, India.
[28] Z. W. S. Abbawi, “Geotechnical properties of expansive soil treated with silica fume,” Eng. Technol. J., vol. 31, no. 17, pp. 2458–2470, 2013
[29] N. Latifi, A. Marto, A. S. A. Rashid, and J. L. J. Yii, “Strength and physico chemical characteristics of fly ash–bottom ash mixture,” Arabian J. Sci. Eng., vol. 40, no. 9, pp. 2447–2455, 2015
[30] T. Yaowarat, S. Horpibulsuk, A. Arulrajah, M. Mirzababaei, and A. S. A. Rashid, “Compressive and flexural strength of polyvinyl alcohol modified pavement concrete using recycled concrete aggregates,” J. Mater. Civ. Eng., vol. 30, no. 4, art. 04018046, 2018.
[31] A. S. A. Rashid, B. A. Black, K. A. B. H. Kueh and N. M. Noor, “Development of sustainable masonry units from flood mud soil: strength and morphology investigations,” Constr. Build. Mater., vol. 131, pp. 682–689, 2017
[32] B. Sedaghat, G. Tejani, and S. Kumar, “Predict the maximum dry density of soil based on individual and hybrid methods of machine learning,” Adv. Eng. Intell. Syst., vol. 2, no. 3, 2023,
[33] L. Farahzadi and M. Kioumarsi, “Application of machine learning initiatives and intelligent perspectives for CO₂ emissions reduction in construction,” J. Clean. Prod., vol. 384, p. 135504, 2023
[34] M. I. Jordan and T. M. Mitchell, “Machine learning: Trends, perspectives, and prospects,” Science, vol. 349, no. 6245, pp. 255 260, 2015
[35] F. Livingston, “Implementation of Breiman’s Random Forest machine learning algorithm,” ECE591Q Machine Learning J. Paper, Fall 2005
[36] Alavi, A. H., Gandomi, A. H., Gandomi, M., & Sadat Hosseini, S. S. (2009). Prediction of maximum dry density and optimum moisture content of stabilised soil using RBF neural networks. The IES Journal Part A: Civil & Structural Engineering, 2(2), 98–106.
[37] A. H. Alavi, A. H. Gandomi, and A. Mollahasani, “A genetic programming based approach for the performance characteristics assessment of stabilized soil,” in Variants of Evolutionary Algorithms for Real World Applications, R. Chiong, T. Weise & Z. Michalewicz, Eds., Springer, 2012, pp. 343–376.
[38] S. S. Park, “Unconfined compressive strength and ductility of fibre reinforced cemented sand,” Constr. Build. Mater., vol. 25, no. 2, pp. 1134–1138, 2011
[39] R. M. Ruffolo and A. Shakoor, “Variability of unconfined compressive strength in relation to number of test samples,” Eng. Geol., vol. 108, pp. 16–23, 2009.
[40] S. Sathyapriya, P. D. Arumairaj, and D. Ranjini, “Prediction of unconfined compressive strength of a stabilised expansive clay soil using ANN and regression analysis (SPSS),” Asian J. Res. Soc. Sci. Humanit., vol. 7, no. 2, pp. 109–123, 2017,
[41] A. H. Alavi, A. H. Gandomi, M. Gandomi, and A. Rashed, “Modeling of maximum dry density and optimum moisture content of stabilized soil using artificial neural networks,” J. Plant Nutr. Soil Sci., vol. 173, no. 3, pp. 368–379, 2010
[42] M. Ghazavi and M. Roustaei, “The influence of freeze–thaw cycles on the unconfined compressive strength of fiber reinforced clay,” Cold Reg. Sci. Technol., vol. 61, no. 2 3, pp. 125 131, 2010
[43] B. S. Narendra, P. V. Sivapullaiah, S. Suresh, and S. N. Omkar, “Prediction of unconfined compressive strength of soft grounds using computational intelligence techniques: A comparative study,” Comput. Geotech., vol. 33, no. 3, pp. 196–208, 2006
[44] R. Nazir, E. Momeni, D. J. Armaghani, and M. F. Mohd Amin, “Correlation between unconfined compressive strength and indirect tensile strength of limestone rock samples,” Electron. J. Geotech. Eng., vol. 18, no. 1, pp. 1737–1746, 2013.
[45] S. K. Das, “Artificial neural networks in geotechnical engineering: modelling and application issues,” in Metaheuristics in Water, Geotechnical and Transport Engineering, X.-S. Yang, A. H. Gandomi, S. Talatahari, and A. H. Alavi, Eds., Elsevier, 2013, pp. 231–270.
[46] K. C. Onyelowe, A. M. Ebid, and L. I. Nwobia, “Evolutionary prediction of soil loss from observed rainstorm parameters in an erosion watershed using genetic programming,” Appl. Environ. Soil Sci., vol. 2021, Art. ID 2630123, pp. 1–15, 2021.
[47] K. C. Onyelowe, T. Gnananandarao, and A. M. Ebid, “Estimation of the erodibility of treated unsaturated lateritic soil using support vector machine polynomial and radial basis function and random forest regression techniques,” Cleaner Mater., vol. 3, art. no. 100039, 2022.
[48] P. K. James and P. K. Pandian, “Effect of micro ceramic dust on the plasticity and swell index of lime stabilized expansive soil,” Int. J. Appl. Eng. Res., vol. 10, no. 42, pp. 30647–30650, 2015.
[49] I. Yilmaz and B. Civelekoglu, “Gypsum: An additive for stabilization of swelling clay soils,” Appl. Clay Sci., vol. 44, pp. 166–172, 2009,
[50] E. Kalkan, “Impact of wetting–drying cycles on swelling behaviour of clayey soils modified by silica fume,” Appl. Clay Sci., vol. 52, pp. 345 353, 2011.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 International Journal of Computational and Experimental Science and Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
