Machine-Learning Prediction and Interpretation of Peak Shear Strength in Fly Ash-Amended, Lignin-Fiber-Reinforced Silty Sand

Nasiri, Masoud; Ahmadi, Masoud

doi:10.22075/jrce.2026.2756

Machine-Learning Prediction and Interpretation of Peak Shear Strength in Fly Ash-Amended, Lignin-Fiber-Reinforced Silty Sand

Document Type : Regular Paper

Authors

Masoud Nasiri ¹

Masoud Ahmadi ²

¹ Faculty of Engineering, Kermanshah University of Technology, Kermanshah, Iran

² Faculty of Earth Sciences Engineering, Arak University of Technology, Arak, Iran

10.22075/jrce.2026.2756

Abstract

Accurate prediction of peak shear strength can facilitate the mechanical assessment of stabilized and reinforced soils while reducing reliance on extensive laboratory testing. This study develops a data-driven framework for predicting and interpreting the peak shear strength of fly ash-amended, lignin-fiber-reinforced silty sand. Eight machine-learning algorithms were comparatively evaluated using 90 observations obtained from unconsolidated–undrained triaxial tests, with lignin fiber content, curing time, initial moisture content, and confining pressure as input variables. Among the evaluated models, Gradient Boosting exhibited the best generalization performance, achieving a test R² of 0.871, an MAE of 92.60 kPa, and an RMSE of 110.10 kPa. Model-based feature importance identified lignin fiber content as the dominant predictor, followed by confining pressure, initial moisture content, and curing time. Partial-dependence and sensitivity analyses further revealed pronounced nonlinear effects of lignin fiber content, whereas confining pressure showed a consistently positive influence on the predicted strength. Residual diagnostics indicated a standard deviation of 113.14 kPa, with no residuals exceeding the adopted ±2σ threshold. Overall, the findings demonstrate the potential of nonlinear ensemble learning for accurate and interpretable prediction of peak shear strength within the investigated experimental domain, while providing insight into the relative influence of key material and testing parameters.

Highlights

Eight machine-learning models were evaluated for peak shear-strength prediction.
Gradient Boosting achieved the best test performance with R² = 0.871.
Lignin fiber content was identified as the most influential model predictor.
Confining pressure showed a strong positive influence on predicted shear strength.
Model interpretation revealed pronounced nonlinear effects of key input variables.

Keywords

Peak shear strength

Machine learning

Lignin fiber

Fly ash-amended soil

Model interpretation

Subjects

Structural Engineering

[1] Shen Z, Pan Q, Chian SC, Gourvenec S, Tian Y. Probabilistic failure envelopes of strip foundations on soils with non-stationary characteristics of undrained shear strength. Géotechnique 2023;73:716–35. https://doi.org/10.1680/jgeot.21.00169.

[2] Guler E, Hamderi M, Demirkan MM. Numerical analysis of reinforced soil-retaining wall structures with cohesive and granular backfills. Geosynth Int 2007;14:330–45. https://doi.org/10.1680/gein.2007.14.6.330.

[3] Nasiri M, Hajiazizi M. An experimental and numerical investigation of reinforced slope using geotextile encased stone column. Int J Geotech Eng 2021;15:543–52. https://doi.org/10.1080/19386362.2019.1651029.

[4] Hatami K, Esmaili D, Chan EC, Miller GA. Moisture Reduction Factors for Shear Strength of Unsaturated Reinforced Embankments. Int J Geomech 2016;16:D4016001. https://doi.org/10.1061/(ASCE)GM.1943-5622.0000624.

[5] Nian T, Li J, Li P, Liu Z, Guo R, Ge J, et al. Method to predict the interlayer shear strength of asphalt pavement based on improved back propagation neural network. Constr Build Mater 2022;351:128969. https://doi.org/10.1016/j.conbuildmat.2022.128969.

[6] Mortazavi A. Anchorage and shear strength properties for composite tendons used in earthwork support systems. Constr Build Mater 2007;21:109–17. https://doi.org/10.1016/j.conbuildmat.2005.06.034.

[7] Fallah M, Mazaheri A, Lajervardi H, Nasiri M. Shear Strength Behavior of Oil-Contaminated Bushehr Carbonate Sand. J Rehabil Civ Eng 2025;13:177–89. https://doi.org/10.22075/jrce.2025.35520.2180.

[8] Ahmaruzzaman M. A review on the utilization of fly ash. Prog Energy Combust Sci 2010;36:327–63. https://doi.org/10.1016/j.pecs.2009.11.003.

[9] Mir BA, Sridharan A. Physical and Compaction Behaviour of Clay Soil–Fly Ash Mixtures. Geotech Geol Eng 2013;31:1059–72. https://doi.org/10.1007/s10706-013-9632-8.

[10] Siddiqua S, Barreto PNM. Chemical stabilization of rammed earth using calcium carbide residue and fly ash. Constr Build Mater 2018;169:364–71. https://doi.org/10.1016/j.conbuildmat.2018.02.209.

[11] Gangloff WJ, Ghodrati M, Sims JT, Vasilas BL. Impact of Fly Ash Amendment and Incorporation Method on Hydraulic Properties of a Sandy Soil. Water Air Soil Pollut 2000;119:231–45. https://doi.org/10.1023/A:1005150807037.

[12] Qiu Z, Zhang L, Likos WJ, Yin J. Mechanical behavior and microstructural insights of bagasse fiber and fly ash-treated dredged clay. Mar Georesources Geotechnol 2026;44:2261–76. https://doi.org/10.1080/1064119X.2026.2620582.

[13] Shaheen SM, Hooda PS, Tsadilas CD. Opportunities and challenges in the use of coal fly ash for soil improvements – A review. J Environ Manage 2014;145:249–67. https://doi.org/10.1016/j.jenvman.2014.07.005.

[14] Yao Z, Ji X, Sarker PK, Tang JH, Ge LQ, Xia MS, et al. A comprehensive review on the applications of coal fly ash. Earth-Science Rev 2015;141:105–21. https://doi.org/10.1016/j.earscirev.2014.11.016.

[15] Wang Y, Acarturk BC, Burris L, Hooton RD, Shearer CR, Suraneni P. Physicochemical characterization of unconventional fly ashes. Fuel 2022;316:123318. https://doi.org/10.1016/j.fuel.2022.123318.

[16] Xu G, Shi X. Characteristics and applications of fly ash as a sustainable construction material: A state-of-the-art review. Resour Conserv Recycl 2018;136:95–109. https://doi.org/10.1016/j.resconrec.2018.04.010.

[17] Vassilev S V, Vassileva CG. A new approach for the classification of coal fly ashes based on their origin, composition, properties, and behaviour. Fuel 2007;86:1490–512. https://doi.org/10.1016/j.fuel.2006.11.020.

[18] Chancey RT, Stutzman PE, Juenger MCG, Fowler DW. Comprehensive phase characterization of crystalline and amorphous phases of a Class F fly ash. Cem Concr Res 2010;40:146–56. https://doi.org/10.1016/j.cemconres.2009.08.029.

[19] Guo X, Shi H, Dick WA. Compressive strength and microstructural characteristics of class C fly ash geopolymer. Cem Concr Compos 2010;32:142–7. https://doi.org/10.1016/j.cemconcomp.2009.11.003.

[20] Phani Kumar BR, Sharma RS. Effect of Fly Ash on Engineering Properties of Expansive Soils. J Geotech Geoenvironmental Eng 2004;130:764–7. https://doi.org/10.1061/(ASCE)1090-0241(2004)130:7(764).

[21] Rios S, Cristelo N, Viana da Fonseca A, Ferreira C. Stiffness Behavior of Soil Stabilized with Alkali-Activated Fly Ash from Small to Large Strains. Int J Geomech 2017;17:4016087. https://doi.org/10.1061/(ASCE)GM.1943-5622.0000783.

[22] Li LH, Ning T, Zhan ZQ, Gui YL, Zhang C. Study on mechanical properties of fly ash and coir fiber improved expansive soil subgrade. Acta Geotech 2026;21:745–65. https://doi.org/10.1007/s11440-025-02784-8.

[23] Wang X, Zhu S, Han Z, Zhang Y, Kai W, Yu X, et al. Volumetric, strength and microstructural characteristics of expansive soil modified by lignin fibers and fly ash. J Rock Mech Geotech Eng 2026;18:6634–50. https://doi.org/10.1016/j.jrmge.2026.05.003.

[24] Yachang O, Kalita A, Taku M. Synergistic Effect of Cement-Fly Ash Stabilization and Fibre Reinforcement on Soil Strength. In: Cameselle C, Gouveia S, Urréjola S, Reddy KR, Agnihotri AK, editors. Sustain. Energy Infrastruct. Keynote Vol. 6th EGRWSE 2025, vol. 802, Cham: Springer; 2026, p. 457–67. https://doi.org/10.1007/978-3-032-15286-2_41.

[25] Nasiri M, Amiri E. Stability Prediction of Excavations Reinforced with Different Geosynthetics–An Integrated Numerical and Machine Learning Approach. Appl Comput Geosci 2026:100351.

[26] Ebadi-Jamkhaneh M, Ahmadi M. Comprehensive Investigations of the Effect of Bolt Tightness on Axial Behavior of a MERO Joint System: Experimental, FEM, and Soft Computing Approaches. J Struct Eng 2021;147. https://doi.org/10.1061/(ASCE)ST.1943-541X.0003168.

[27] Nasiri M, Amiri E, Ashrafi AH. Slope Stability Analysis Using Machine Learning Algorithms Based on Real Cases Datasets. Transp Infrastruct Geotechnol 2026;13:31. https://doi.org/10.1007/s40515-026-00816-8.

[28] Fakharian P. Compressive Strength Prediction of 3D Printed Concrete with Machine Learning Approaches. Comput Eng Phys Model 2025;8:1385. https://doi.org/10.22115/cepm.2026.1385.

[29] Nouri Y, Ghanbari MA, Fakharian P. Flexural behavior of hybrid GFRP-steel reinforced concrete beam: Experimental and explainable artificial intelligence. Eng Struct 2025;345:121565. https://doi.org/10.1016/j.engstruct.2025.121565.

[30] Fakharian P, Nouri Y, Asaad Samani A, Rezazadeh Eidgahee D, Torabi MR, Hoseini Vaez SR. Explainable machine learning model and gene expression programming for predicting reinforced concrete beams moment capacity exposed to fire. Sci Rep 2026;16:2309. https://doi.org/10.1038/s41598-025-32100-z.

[31] Nasiri M, Amiri E, Fadaei E. Ensemble Machine Learning Models for Estimating Stone Column Load-Bearing Capacity Using Combined Experimental and Field Test Data. Transp Infrastruct Geotechnol 2025;12:246. https://doi.org/10.1007/s40515-025-00710-9.

[32] Nasiri M, Amiri E. ANN Insight in Forecasting Slope Stability by Analyzing the Influence of Strength Parameters in 2D and 3D Scenarios. Transp Infrastruct Geotechnol 2025;12:126. https://doi.org/10.1007/s40515-025-00584-x.

[33] Chen W, Qu S, Lin L, Luo Q, Wang T. Ensemble Learning Methods for Shear Strength Prediction of Fly Ash-Amended Soils with Lignin Reinforcement. J Mater Civ Eng 2023;35:4023022. https://doi.org/10.1061/(ASCE)MT.1943-5533.0004676.

[34] Wani NM, Thagunna P. Predictive modeling of shear strength in fly ash-stabilized clayey soils using artificial neural networks and support vector regression. Asian J Civ Eng 2024;25:6131–46. https://doi.org/10.1007/s42107-024-01167-w.

[35] Aggarwal V, Abhi BS, Gupta S, Kaur R, Saini R, Sharma P, et al. Prediction of unconfined compressive strength of fly ash and waste paper sludge stabilized clayey soil using explainable machine learning. Sci Rep 2026;16:16376. https://doi.org/10.1038/s41598-026-47096-3.

[36] Awoyera PO, Fadugba OG, Vasić M V. Optimized machine learning models for predictive performance assessment of fly ash-integrated clay bricks. Sci Rep 2026. https://doi.org/10.1038/s41598-026-63535-7.

[37] Hu J, Li Z, Qin X, Dong S, Zhao T, Li H. Machine learning-based optimization of geopolymer-stabilized soil formulation using blast furnace slag and fly ash. Mater Today Commun 2025;48:113500. https://doi.org/10.1016/j.mtcomm.2025.113500.

[38] Kumar A, Sinha S. Support vector machine-based prediction of unconfined compressive strength of Multi-Walled Carbon nanotube doped soil-fly ash mixes. Multiscale Multidiscip Model Exp Des 2024;7:5365–86. https://doi.org/10.1007/s41939-024-00524-1.