Slope stability assessment is a critical component of engineering safety. Conventional analytical methods frequently struggle to integrate heterogeneous slope data and model intricate failure mechanisms, thereby constraining their efficacy in practical engineering scenarios. To tackle these issues, this study presents a novel slope stability classification model grounded in the Optuna-TPE-CatBoost framework. By leveraging the Tree-structured Parzen Estimator (TPE) within the Optuna framework, the model adaptively optimizes CatBoost hyperparameters, thus enhancing prediction accuracy and robustness. It incorporates six key features—slope height, slope angle, unit weight, cohesion, internal friction angle, and the pore pressure ratio—to establish a comprehensive and intelligent assessment system. Utilizing a dataset of 272 slope cases, the model was trained with k-fold cross-validation and dynamic class imbalance strategies to ensure its generalizability. The optimized model achieved impressive performance metrics: an area under the receiver operating characteristic curve (AUC) of 0.926, an accuracy of 0.901, a recall of 0.874, and an F1-score of 0.881, outperforming benchmark algorithms such as XGBoost, LightGBM, and the unoptimized CatBoost. Validation via engineering case studies confirms that the model accurately evaluates slope stability across diverse scenarios and effectively captures the complex interactions between key parameters. This model offers a reliable and interpretable solution for slope stability assessment under complex failure mechanisms.

Yellow phosphorus slag has been considered as a potential cement substitute for mine filling material due to its cementing activity; however, its slow setting and low early strength have limited broader use. This study investigates the grading, compactness, and strength of yellow phosphorus slag combined with tailing sand. Using yellow phosphorus slag as an aggregate, cement as a binder, and mixing tailing sand in different ratios, this study evaluates its feasibility as a coarse aggregate in mine backfill. The key findings are as follows. (1) The grading index of tailing sand was 0.5, aligning with Fuller grading, but it required mixing with coarse aggregates to enhance strength and reduce cement consumption. Yellow phosphorus slag, with a grading index of 0.97, does not match Fuller’s curve and thus benefits from mixing with tailing sand. (2) For mixtures of waste rock and tailings, the 5:5 ratio aligned closely with Fuller’s theory, showing optimal packing density and strength. Mixtures of yellow phosphorus slag and tailings at ratios of 3:7, 4:6, and 5:5 had R² values of 0.73, 0.80, and 0.85, respectively, confirming reliable fit. The 5:5 mixture provided the best packing density and strength. (3) A new strength prediction model, accounting for aggregate, cement, and water effects, suggests that a 5:5 ratio with a 71% mass concentration and 1/7 ash–sand ratio meets industrial strength requirements. FLAC3D simulations indicated that cemented backfill reduces stress concentrations caused by excavation and supports stability during mining while also absorbing energy through compaction, creating favorable conditions for safe mining operations.

As open-pit mining extends to greater depths, slope stability is becoming a critical factor in ensuring safe production. This issue is particularly pronounced in geological settings with weak interlayers, where sudden slope failures are more likely to occur, demanding precise and reliable stability assessment methods. In this study, a typical open-pit slope with weak interlayers was investigated. Acoustic testing and ground-penetrating radar were employed to identify rock mass structural features and delineate loose zones, enabling detailed rock mass zoning and the development of numerical simulation models for stability analysis. The results indicate that (1) the slope exhibits poor overall integrity, dominated by blocky to fragmented structures with well-developed joints and significant weak interlayers, posing a severe threat to stability; (2) in the absence of support, the slope’s dissipated energy, displacement, and plastic zone volume all exceeded the failure threshold (Δ < 0), and the safety factor was only 0.962, indicating a near-failure state; after implementing support measures, the safety factor increased to 1.31, demonstrating a significant improvement in stability; (3) prior to excavation, the energy damage index (ds) in the 1195–1240 m platform zone reached 0.82, which dropped to 0.48 after reinforcement, confirming the effectiveness of support in reducing energy damage and enhancing slope stability; (4) field monitoring data of displacement and anchor rod forces further validated the stabilizing effect of the support system, providing strong assurance for safe mine operation. By integrating cusp catastrophe theory with energy-based analysis, this study establishes a comprehensive evaluation framework for slope stability under complex geological conditions, offering substantial practical value for deep open-pit mining projects.

Slope stability analysis is conventionally performed using the strength reduction method with the proportional reduction in shear strength parameters. However, during actual slope failure processes, the attenuation characteristics of rock mass cohesion ($c$) and internal friction angle ($\phi$) are often inconsistent, and their reduction paths exhibit clear nonlinearity. Relying solely on proportional reduction paths to calculate safety factors may therefore lack scientific rigor and fail to reflect true slope behavior. To address this limitation, this study proposes a novel approach that considers the non-proportional reduction of $c$ and $\phi$, without dependence on predefined reduction paths. The method begins with an analysis of slope stability states based on energy dissipation theory. A Bayesian Gaussian Mixture Model (BGMM) is employed for intelligent interpretation of the dissipated energy data, and, combined with energy mutation theory, is used to identify instability states under various reduction parameter combinations. To compute the safety factor, the concept of a “reference slope” is introduced. This reference slope represents the state at which the slope reaches limit equilibrium under strength reduction. The safety factor is then defined as the ratio of the shear strength of the target analyzed slope to that of the reference slope, providing a physically meaningful and interpretable safety index. Compared with traditional proportional reduction methods, the proposed approach offers more accurate estimation of safety factors, demonstrates superior sensitivity in identifying critical slopes, and significantly improves the reliability and precision of slope stability assessments. These advantages contribute to enhanced safety management and risk control in slope engineering practice.

The stability of open-pit slopes with weak interlayers is a critical issue in mining, as the design of bench parameters affects both slope safely and economic outcomes. Traditional optimization methods are often time-consuming and may not find global optimal solutions. This study presents an intelligent optimization approach combining machine learning (ML) and multi-objective optimization techniques. A numerical model simulating slopes with weak interlayers was developed and a dataset linking bench control parameters with slope stability and economic performance was created. Machine learning algorithms, including Support Vector Machines (SVM), were used to build predictive models to assess the impact of various parameter combinations on stability and economic performance. Optimization was carried out using the SVM-NSGAII and SVM-O algorithms. Results showed that SVM-NSGAII out performed SVM-BO, predicting a safety factor of 1.258 with a 3.8% error compared to 5.69%6 for SVM-BO, and achieving a relative economic error of 1.296, significantly lower than the 9.0%6 error of SVM-BO. A software system for bench parameter optimization was developed on the Python platform with an intuitive graphical user interface (GUI), significantly improving slope stability and mining profitability, offering scientific support for mine design in complex environments, and demonstrating both theoretical and practical applications.

Managing surface subsidence caused by underground mining beneath critical infrastructure requires highly efficient and robust optimization models. This study presents a data-driven, multi-objective framework for the collaborative safety optimization of mine stopes and overlying roads, applied to a quartzite mine beneath a secondary highway in Yunnan Province. Based on 88 FLAC3D simulation samples, an XGBoost surrogate model was developed to predict geomechanical responses (Z-displacement and extraction volume), while a Bayesian-optimized Long Short-Term Memory (BO-LSTM) network was employed to forecast ore price signals. To ensure model generalizability and mitigate overfitting in the limited stope dataset, a 5-fold cross-validation (5-fold CV protocol was systematically incorporated into the model training process. Critically, the CV-supported predictive models underwent stress testing under varying training data sizes (40–90%), Gaussian noise intensities (1–13%), and outlier distributions (5–20% proportion; 10–50%amplitude) to define the boundaries of algorithmic reliability. The NSGA-II algorithm was used to map the Pareto-optimal frontier, which was deployed via a Tkinter graphical user interface for dynamic stope geometry adjustments driven by price fluctuations. Secondary FLAC3D validation of the recommended parameters (21.44 m pillar, 1.60 m sidewall) yielded minimal relative errors of 5.07% for displacement and 2.38% for extraction volume. This validated framework demonstrates numerical robustness while balancing geotechnical safety and dynamic market rewards.