Data-Driven Rock Shear Strength Prediction: A Novel Framework

To overcome the limitations of single models in addressing complex, nonlinear problems in predicting rock shear strength parameters and the hyperparameter random selection problem, this study constructed a novel prediction framework for rock shear strength parameters. First, the light gradient boosting machine (LightGBM), extreme gradient boosting (XGBoost), categorical boosting (CatBoost), and random forest (RF) algorithms are employed as the base-learners for the ensemble model, with XGBoost serving as the meta-learner to build a stacking ensemble model. On the basis of the sparrow search algorithm (SSA), tent chaotic mapping is used to initialize the sparrow population, the Cauchy‒Gaussian hybrid mutation mechanism is used to dynamically select the probability control mutation type, the dynamic adaptive weight is used to adjust the balance between global exploration and local development, and Levy flight is used to help the sparrow population individuals jump out of the local optimum to construct the chaos-improved sparrow search algorithm (CISSA) to optimize the hyperparameters of the stacking model. Second, based on the 199 datasets of different rock types, the model was trained via fivefold cross-validation and evaluated based on the coefficient of determination (R²), root mean square error (RMSE) and mean absolute error (MAE). Concurrently, the Shapley additive explanations (SHAP) method was employed to analyse the degree of contribution of each predictive index. The results demonstrate that the CISSA-Stacking model achieves R² values of 0.9936 and 0.9744 for c and φ, respectively, with corresponding RMSE of 0.4303 and 0.7635 and MAE of 0.2161 and 0.5867, indicating significantly superior overall performance compared with benchmark models. SHAP interpretability analysis revealed that the importance rankings for c are Vp, UCS, BTS, and ρ, whereas those for φ are ρ, UCS, Vp, and BTS. Finally, intelligent prediction software based on the CISSA-Stacking model was developed. The software is simple in operation, intuitive in results and excellent in performance, enables rapid and accurate prediction of c and φ through manual input of the Vp, ρ, UCS, and BTS indices or by importing tabular data containing these four indices. The engineering application further confirmed the accuracy and practical utility of both the model and the software, providing a new efficient method for engineers to quickly and accurately estimate rock shear strength parameters.