With the gradual depletion of mineral resources in temperate regions, cold regions have become primary areas for mineral extraction. However, the freeze–thaw phenomena induced by temperature fluctuations pose significant threats to the stability of rock masses on open−pit mine slopes, further affecting normal mining operations. To investigate the strength degradation and stability evolution patterns of freeze–thaw slope rock masses, this study takes the Wushan Open−Pit Mine as its engineering context. We analyzed the relationship between rock temperature and burial depth, conducted freeze–thaw cyclic tests under realistic temperature ranges, and developed a mechanical parameter characterization model for freeze–thaw rock masses by integrating the generalized Hoek–Brown strength criterion. Slope safety factors and potential landslide mechanisms were determined through numerical simulations and the strength reduction method. Key findings include the following: (1) Shallow rock temperatures exhibit high synchronization with atmospheric temperature, characterized by large fluctuations and rapid variation rates, whereas deep rock demonstrates opposite trends. (2) As freeze–thaw cycles increase and burial depth decreases, the internal friction angle and cohesion of slope rock masses follow negative exponential decay functions. After 20 freeze–thaw cycles, the internal friction angle and cohesion of rock at a 5.27 m depth decreased by 18.36% and 33.92%, respectively. In contrast, rock at a 0.10 m depth showed more severe reductions of 31.81% and 50.14%. (3) Increasing freeze–thaw cycles progressively lower the safety factors of slope benches, with potential slip surfaces displaying reduced average depths and curvature, alongside elevated dip angles. These findings provide critical insights for preventing freeze–thaw−induced landslide hazards in cold−region open−pit mine slopes.

To address the limitations of traditional early warning methods in open-pit slope displacement monitoring—particularly their neglect of spatiotemporal correlations and their difficulty in analyzing multi-scale non-stationary sequences—this study proposes an early warning framework that integrates spatiotemporal clustering with multi-scale decomposition. Taking the southern slope of the Bayan Obo Main Pit as a case study, high-risk deformation zones were identified using DBSCAN-based spatiotemporal clustering applied to slope radar monitoring data. The displacement time series were decomposed using Variational Mode Decomposition (VMD) into trend and periodic components, for which Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM) models were respectively developed. The results indicate that (1) DBSCAN effectively detects clusters characterized by high average cumulative displacement and broad spatial distribution, while filtering out isolated outliers. (2) The trend component prediction achieved a coefficient of determination (R²) of 0.99755, while the periodic component prediction yielded a root mean square error (RMSE) of just 0.0978 mm. The reconstructed total displacement achieved an R² of 0.9973, verifying the proposed multi-scale decomposition and hybrid modeling framework’s high accuracy and robustness in slope deformation modeling and early warning.

This study takes the Wushan open-pit mine, a typical open-pit mine in cold regions, as the engineering background. Based on the measured extreme temperature values of slope rock masses over one year, a freeze–thaw cycle testing scheme is designed. By conducting experiments under varying numbers of freeze–thaw cycles and burial depths, the degradation patterns of uniaxial compressive strength and tensile strength of the rock are revealed. The rock material constant $\mathrm{m}\mathrm{i}$, representing the rock’s hardness and brittleness, is calculated based on the experimental results. Furthermore, shear tests are carried out on rock masses containing through-going structural planes and infill materials to derive the variation patterns of cohesion and internal friction angle. A comprehensive analysis is conducted on the effects of freeze–thaw cycling and burial depth on rock mechanical properties and infill material parameters, leading to the construction of a spatial variability characterization model for mechanical parameters. Finally, the rock mass fracture coefficient ${\mathrm{K}}_{\mathrm{w}}$ and infill fracture coefficient $K_f$ are proposed to modify the Hoek–Brown failure criterion under freeze–thaw conditions, thereby providing theoretical support for slope stability analysis and engineering design in cold regions.