Interpretable AI Models Based on Hybrid Ensemble Learning Methods for Predicting Unconfined Compressive Strength of Cement-Stabilized Magnetite Iron Ore Tailing

Background: Iron ore tailings (IOTs) are a mine waste product used as road materials and suffer from a lack of sufficient strength, which should be improved through stabilization. Unconfined compressive strength (UCS) is a crucial parameter for determining the quality and mix design of stabilized soils, which is time-consuming, requires specialized equipment and professional operators, and is not affordable. Methods: In this study, six ensemble learning techniques, five-fold cross-validation, and the Fennec Fox Optimization metaheuristic algorithm were utilized to predict UCS. For this purpose, cement content, curing time, compaction energy, and moisture content were selected as independent variables. Results: The results suggested that XGBoost-FFO was the most accurate model, R2 = 0.9505, MAE = 0.257, MSE = 0.118, and RMSE = 338. Two interpretation methods were employed to evaluate the model’s performance, and the results indicated that the most significant parameter was compaction energy. Conclusions: Moreover, to facilitate practical engineering applications, a graphical user interface (GUI) was also designed to predict the UCS of cement-stabilized IOTs.