Obtaining accurate basic parameters for long hole blasting is challenging, and the resulting vibration damage significantly impacts key surface facilities. Predicting ground vibration velocity accurately and mitigating the harmful effects of blasting are crucial aspects of controlled blasting technology. This study focuses on the prediction of ground vibration velocity induced by underground long hole blasting tests. Utilizing the fitting equation based on the US Bureau of Mines (USBM) formula as a baseline for predicting peak particle velocity, two machine learning models suitable for small sample data, Support Vector Regression (SVR) machine and Random Forest (RF), were employed. The models were optimized using the particle swarm optimization algorithm (PSO) to predict peak particle velocity with multiple parameters specific to long hole blasting. Mean absolute error (MAE), mean Squared error (MSE), and coefficient of determination (R²) were used to assess the model predictions. Compared with the fitting equation based on the USBM model, both the Support Vector Regression (SVR) and Random Forest (RF) models accurately and effectively predict peak particle velocity, enhancing prediction accuracy and efficiency. The SVR model exhibited slightly superior predictive performance compared to the RF model.

The Jinchuan Nickel Mine is the largest large-scale copper–nickel sulfide deposit in China and the third largest in the world. Due to the deep burial of the ore body, high geostress, and broken ore rock, the downward layered cementing and filling mining method with high cost and low production capacity is adopted. The Jinchuan Nickel Mine uses bar milling sand as the filling aggregate and cement as the cementing material and adopts pipeline autoclave conveying filling mining technology with a high cement-to-sand ratio and high concentration of filling slurry, which results in the high cost of filling mining and poor mining economic benefits. In order to reduce the cost of filling mining, the Jinchuan Nickel Mine has carried out a series of research on low-cost filling mining technology by utilizing solid waste, such as using metallurgical slag instead of cement to develop low-cost filling cementitious material, using waste rock and bar mill sand as the mixed aggregate, using waste rock and tailing sand as the mixed aggregate, mixing fly ash with the mixed aggregate, and mixing copper processing tailing with the mixed aggregate. The strength of the 3d, 7d, and 28d cemented filling body of waste rock and bar mill sand reached 1.5 MPa, 2.6 MPa, and 4.8 MPa, respectively; the strength of the 3d, 7d, and 28d cemented filling body of waste rock tailings reached 4.7 MPa, 6.1 MPa, and 9.0 MPa, respectively; the strength of the 3d, 7d, and 28d cemented filling body of mixed fly ash reached 2.0 MPa, 2.0 MPa, 6.1 MPa, and 9.0 MPa, respectively; the strength of 3d, 7d, and 28d doped fly ash cemented filling body reached 2.0 MPa, 2.7 MPa, and 5.9 MPa, respectively; the strength of the 3d, 7d, and 28d doped copper-selecting tailings cemented filling body reached 1.55 MPa, 3.11 MPa, and 5.10 MPa respectively; and the strength of 3d early-strength type green filling cementitious material increased to 1.73 MPa. The application of cemented filling with solid waste resources in the Jinchuan Nickel Mine has been successful and popularized and applied in the Longshou Mine and the second mine area. Early-strength green filling cementitious materials and mixed aggregate paste filling technology are the research and development direction for utilization in Jinchuan Nickel Mine filling and mining.

Rockburst disasters have become increasingly prevalent as distinct forms of subsurface geotechnical engineering advanced to the deep earth. Confronted with such a threatening subsurface geopressure disaster that poses a risk to personnel and equipment safety, the microseismic monitoring technology has been employed to track signals generated from rock fracture and collapse in the field. To guide the prevention and control of the hazard, the investigation conducted an effective microseismic data mining method. Through deep feature engineering and interpretable intelligence, a practical and available short-term prediction approach for the rockburst intensity class was developed. On the basis of rockburst case database collected from various underground geotechnical engineering, the neural network-based feature extraction method was conducted in the process of model training. The optimized model was obtained by combining the K-fold cross-validation approach with the structural parameter search methodology. The evaluation among the considered artificial intelligence models on the testing dataset was conducted and compared. Through analyses, the interpretable coupling intelligent model combining convolutional and recurrent neural networks for rockburst prediction were demonstrated with the most robust performance by evaluation metrics. Among them, the proposed adaptive feature extraction method leads the benchmark method by 6% for both accuracy and precision; meanwhile, the proposed metric generalization loss rate (GLR) for accuracy and precision in the validation–testing process reached 1.5% and 0.2%. Furthermore, the Shapley additive explanations (SHAP) approach was employed to verify the model interpretability by deciphering the model prediction from the perspective of the fined impact of input features. Therefore, the investigation demonstrates that the proposed method can predict rockburst intensity with robust generalization and feature extraction capabilities, which possess substantial engineering significance and academic worth.

Underground mining often causes surface displacement and deformation above and around mined-out areas, and mining-induced subsidence has become a growing concern for ground stability worldwide. Given the proximity between the studied mine and a neighboring operation, potential mutual influences during extraction were examined to ensure the safety of surface structures. This study analyzes the stability of the overlying strata by combining theoretical prediction and numerical simulation, considering the cumulative effects of adjacent mining activities. The main findings are as follows: (1) The probability integration method was used to predict surface deformation and subsidence caused by underground mining, providing deformation data for the 4# shaft, 4# return air shaft, 5# return air shaft, and surrounding ground surface. (2) A three-dimensional geomechanical model was built using FLAC3D finite-difference software based on actual topographical and geological data to assess the impact of mining on overburden stability. Results show that the surrounding rock remained primarily in the elastic stage, with a maximum surface subsidence of 47.7 mm, confirming the structural stability of the 4# and 5# shafts. (3) Analyzing stress redistribution during deep ore extraction in both mining zones reveals that stress disturbances were mainly confined to the excavation areas, with a maximum local stress concentration of 83.34 MPa at stope corners. The combined mining activities resulted in an overall subsidence of approximately 48.7 mm, which decreased gradually outward from the center. This research presents an integrated theoretical and numerical framework that combines probability integration theory with FLAC3D simulation to assess the cumulative deformation and stress interactions of neighboring underground mines. The proposed method offers a practical and transferable tool for evaluating regional mine stability and surface deformation risks in multi-mine districts.