This study investigates the influence of tunnel span on the dynamic response of rock masses with high integrity under intense dynamic load, analyzing an unlined circular tunnel excavated in intact surrounding rock with a uniaxial compressive strength of $f_r=57$ MPa. Using a combined approach of physical model testing and numerical simulation, the influence mechanism of span on tunnel stability under different intense dynamic loads is systematically analyzed. The research results indicate the following: (1) When the peak intense Dynamic load is below $0.51f_r$, the surrounding rock mass remains in an elastic state. (2) When the peak load ranges between $0.51f_r$ and $0.54f_r$, plastic zones emerge at the tunnel wall. (3) Once the peak load exceeds $0.70f_r$, the influence of the tunnel span on stability becomes significantly more pronounced with increasing load intensity. In small-span tunnels, plastic zones primarily distribute along the wall sides, whereas in large-span tunnels, they extend further upward and downward. (4) At a peak load of $0.70f_r$, the ratio of the maximum extent of the plastic zone in a 20 m span tunnel to that in a 5 m span tunnel is 10.70, and the ratio of the maximum relative displacement between the vault and invert is 4.67. When the peak load increases to $1.40f_r$, the plastic zone extent ratio rises to 13.94, and the vault–invert displacement ratio increases to 6.17. The conclusions of this study provide theoretical foundations for the design of tunnels with varying spans under intense dynamic load.

With the development of various emerging structures, concrete-filled steel tubular (CFST) columns have become critical load-bearing components in key infrastructures such as subways and underground utility tunnels. Accurately predicting their ultimate bearing capacity (N_u) is essential for guaranteeing structural safety. To address the limitations of traditional empirical formulas and code-based calculation approaches, this paper proposes a prediction model for ultimate bearing capacity based on the CatBoost algorithm optimized by Random Search. Furthermore, the marginal contribution of each key feature to the prediction results is measured through interpretability analysis. First, a database containing 438 CFST column ultimate bearing capacity test cases was established, with key parameters such as geometric dimensions and material properties as input variables. Second, the predictive performance of six machine learning algorithms—CatBoost, LightGBM, Random Forest (RF), Gradient Boosting (GB), K-Nearest Neighbors (KNN), and XGBoost—was compared. A five-fold cross-validation integrated with a Random Search strategy was employed for joint hyperparameter optimization. The results show that the optimized CatBoost model significantly outperforms other algorithms and conventional design codes, achieving a coefficient of determination (R²) as high as 0.99 and a root mean square error (RMSE) of 174.29 kN. Furthermore, the SHAP (Shapley Additive exPlanations) method was used to perform global and local interpretability analyses of the prediction model. This not only quantified the individual contribution and interaction effects of each feature parameter on the bearing capacity but also revealed that geometric parameters are the primary influencing factor. This finding confirms a high degree of consistency between the prediction mechanism of the data-driven model and classical mechanical theories, effectively validating the model’s reliability. This study provides an efficient and reliable tool for the optimal design and rapid evaluation of CFST columns and establishes a new data-driven paradigm for the design and reinforcement of key components in underground structures.