Open Access

ARTICLE

Optimizing UCS Prediction Models through XAI-Based Feature Selection in Soil Stabilization

Ahmed Mohammed Awad Mohammed^1,*, Omayma Husain², Mosab Hamdan³, Abdalmomen Mohammed⁴, Abdullah Ansari^5,6,7, Atef Badr¹, Abubakar Elsafi⁸, Abubakr Siddig⁹

1 Department of Civil Engineering & Quantity Surveying, Military Technological College, Muscat, Oman
2 Department of Information Technology, Faculty of Mathematical Sciences and Informatics, University of Khartoum, Khartoum, Sudan
3 School of Computing, National College of Ireland, Dublin, Ireland
4 Department of Electrical Engineering, Faculty of Engineering, University of Khartoum, Khartoum, Sudan
5 Earthquake Monitoring Center, Sultan Qaboos University, Muscat, Oman
6 Department of Civil Engineering, Inha University, Incheon, Republic of Korea
7 Department of Smart City Engineering, Inha University, Incheon, Republic of Korea
8 Department of Software Engineering, College of Computer Science and Engineering, University of Jeddah, Jeddah, Saudi Arabia
9 School of Computer Science, Technological University Dublin, Dublin, Ireland

* Corresponding Authors: Ahmed Mohammed Awad Mohammed. Email: ,

Computer Modeling in Engineering & Sciences 2026, 146(2), 18 https://doi.org/10.32604/cmes.2026.075720

Received 06 November 2025; Accepted 26 January 2026; Issue published 26 February 2026

Abstract

Unconfined Compressive Strength (UCS) is a key parameter for the assessment of the stability and performance of stabilized soils, yet traditional laboratory testing is both time and resource intensive. In this study, an interpretable machine learning approach to UCS prediction is presented, pairing five models (Random Forest (RF), Gradient Boosting (GB), Extreme Gradient Boosting (XGB), CatBoost, and K-Nearest Neighbors (KNN)) with SHapley Additive exPlanations (SHAP) for enhanced interpretability and to guide feature removal. A complete dataset of 12 geotechnical and chemical parameters, i.e., Atterberg limits, compaction properties, stabilizer chemistry, dosage, curing time, was used to train and test the models. R², RMSE, MSE, and MAE were used to assess performance. Initial results with all 12 features indicated that boosting-based models (GB, XGB, CatBoost) exhibited the highest predictive accuracy (R² = 0.93) with satisfactory generalization on test data, followed by RF and KNN. SHAP analysis consistently picked CaO content, curing time, stabilizer dosage, and compaction parameters as the most important features, aligning with established soil stabilization mechanisms. Models were then re-trained on the top 8 and top 5 SHAP-ranked features. Interestingly, GB, XGB, and CatBoost maintained comparable accuracy with reduced input sets, while RF was moderately sensitive and KNN was somewhat better owing to reduced dimensionality. The findings confirm that feature reduction through SHAP enables cost-effective UCS prediction through the reduction of laboratory test requirements without significant accuracy loss. The suggested hybrid approach offers an explainable, interpretable, and cost-effective tool for geotechnical engineering practice.

---

Keywords

---