As one of the main industrial solid wastes, there are a large number of free alkaloids, chemically bound alkaloids, fluoride, and heavy metal ions in Bayer process red mud (BRM), which are difficult to remove and easily pollute groundwater as a result of open storage. In order to realize the large-scale industrial application of BRM as a backfilling aggregate for underground mining and simultaneously avoid polluting groundwater, the material characteristics of BRM were analyzed through physical, mechanical, and chemical composition tests. The optimum cement–sand ratio and solid mass concentration of the backfilling were obtained based on several mixture proportion tests. According to the results of bleeding, soaking, and toxic leaching experiments, the fuzzy comprehensive evaluation method was used to evaluate the environmental impact of BRM on groundwater. The results show that chemically bound alkaloids that remained in BRM reacted with Ca²⁺ in PO 42.5 cement, slowed down the solidification speed, and reduced the early strength of red mud-based cemented backfill (RMCB). The hydration products in RMCB, such as AFT and C-S-H gel, had significant encapsulation, solidification, and precipitation inhibition effects on contaminants, which could reduce the contents of inorganic contaminants in soaking water by 26.8% to 93.8% and the leaching of toxic heavy metal ions by 57.1% to 73.3%. As shown by the results of the fuzzy comprehensive evaluation, the degree of pollution of the RMCB in bleeding water belonged to a medium grade Ⅲ, while that in the soaking water belonged to a low grade II. The bleeding water was diluted by 50–100 times to reach grade I after flowing into the water sump and could be totally recycled for drilling and backfilling, thus causing negligible effects on the groundwater environment.

In Suichang gold mine, the altered rock type gold deposits were cut by faults and joint fissures, leading to complex resource endowment characteristics, large changes in occurrence, a serious complex of ore vein branches and great difficulty in mining. In order to select a suitable mining method for such a difficult and complicated orebody, a multi-factor and multi-index comprehensive evaluation system involving benefits, costs, safety and other aspects was constructed by using the Pythagorean fuzzy sets and TOPSIS method. Taking Suichang gold mine as an example, the weighted aggregation evaluation matrix was constructed, the closeness index of the four mining schemes were 0.8436, 0.3370, 0.4296 and 0.4334, and the mechanized upward horizontal layering method was determined as the optimal scheme. This method overcame the fuzzy comparison of economic and technical indicators directly, but converted them into corresponding fuzzy numbers to obtain accurate closeness index for optimization. The application of this method not only ensured a safe, efficient and environment-friendly mining effect, but also provided a reference for the optimization of the mining scheme of the severely branched composite orebody.

Tunnel faces in underground mines, as the front line of mining, play an important role in both mine safety and mining intelligence. However, the engineering quality of tunnel faces is still evaluated based on visual observations by technicians, which cannot guarantee safety and real-time performance. Therefore, there is an urgent need for a more effective method to detect the quality of tunnel face engineering. In this study, a high-performance and accurate tunnel face segmentation model was developed by applying the YOLOv5-seg computer vision model to an underground mine. By optimizing a classic Chinese underground mine image dataset through Sobel preprocessing and improving the network structure of the YOLOv5-seg model using the SimAM module, good predictive performance was achieved for tunnel face segmentation, with values of 0.97, 0.89, 0.80, and 0.78, respectively, achieved for the pixel accuracy, Dice coefficient, mask intersection over union (IOU), and box IOU on the test set. And the performance of this model outperforms all YOLOv5 models and U-net in the same task of tunnel face segmentation. Model interpretation and visualization further demonstrated the positive effect of the SimAM module on the model, and, finally, the segmentation results were used to evaluate the tunnel face engineering. Overall, this study’s results provide a feasible, safe, and real-time method for accurately segmenting tunnel faces in underground mines and provide a reliable approach for data-driven applications of intelligent technology in mines in the future.

With mining operations worldwide comprehensively advancing the development of intelligent mines, mine digitalization has become an inevitable trend in the evolution of the mining industry. In this context, efficient and high-precision fracture identification has emerged as a critical prerequisite technology for achieving digital transformation in intelligent mining systems. However, severe environmental noise in deep mines and the limitations of standard pixel-wise loss functions, which ignore the geomechanical continuity of fractures, often lead to fragmented segmentation results. To address this, we introduce the existing SCSegamba architecture as an efficient feature extraction backbone and propose a novel Fracture Orientation Consistency Loss (FOCL) as our core optimization objective. By penalizing directional discrepancies between predicted and actual fracture networks, FOCL explicitly enforces geometric and topological continuity. We evaluated our framework on a custom dataset of 600 high-resolution images from deep underground roadways. The results demonstrate that the SCSegamba-FOCL framework effectively bridges discontinuous fine cracks in low-contrast zones. It achieves a superior Mean Intersection over Union (mIoU) of 85.67% and an F1-Score of 0.869, while maintaining a real-time inference speed of 38 frames per second (FPS) on edge hardware.

Physical climate risk in mining is framed as floods, droughts, heatwaves, and wildfires acting on assets with fixed design conditions. We argue that the deeper change is a moving hydroclimatic operating envelope: climate alters the water and heat conditions around mines, while geology, engineering, and lifecycle stage govern how those changes propagate. Linking a global mine inventory to observed and projected Köppen–Geiger classes shows that 16.2% of 1093 geocoded mines changed climate subtype between 1901–1930 and 1991–2020. By 2071–2099, the share rises to 29.8% under Shared Socioeconomic Pathway 2–4.5 (SSP2–4.5) and 42.5% under Shared Socioeconomic Pathway 5–8.5 (SSP5–8.5). Water trajectories also separate. Under SSP5–8.5, median precipitation falls by 3.1% at arid mines but rises by 6.5% at humid locations, while precipitation seasonality increases in arid regions. Commodity geography stratifies this exposure, whereas mine method alone provides little adjusted separation. Tailings records place weather within multi‐causal failure pathways: 64 of 229 failures with a reported cause included a weather hazard, yet raise categories did not distinguish reported climate‐assessment responses. Literature links these shifts to pore pressure, infiltration, heat, material evolution, water storage, and post‐closure hydrology. The combined evidence supports adaptation based on monitored, scenario‐conditioned operating envelopes rather than static hazard checklists.

The stability of slice drifts is critical to the safety and sustainability of mining operations. In underhand cemented backfill mining, slice drifts may be subjected to a special condition in which both the roof and sidewalls are composed of cemented backfill. Therefore, evaluating their long-term stability is of significant engineering importance. To analyze the time-dependent deformation of this special structure, the roof and sidewalls were idealized as a fixed-end beam and a fixed-end wall, respectively. Burgers creep compliance was then incorporated to derive time-dependent expressions for roof subsidence and sidewall convergence. The effects of slice-drift width, in situ stress conditions, and creep influence range on deformation were then analyzed. Subsequently, a three-dimensional FLAC3D 6.0 model incorporating the actual excavation, backfilling, and creep processes was established. The Mohr–Coulomb and Burgers constitutive models were used to investigate the evolution of stress and deformation in slice drifts with different widths. The results show that increasing the slice-drift width significantly increases the roof tensile stress and sidewall convergence rate. Under the extreme condition in which four adjacent drifts on both sides are excavated simultaneously, roof tensile stress concentration and drift deformation are further intensified. Considering both the roof tensile stress and the allowable convergence rate during the stable creep stage of the sidewalls, a slice-drift width of 5.0 m is recommended. Finally, field convergence monitoring was conducted at eight monitoring points in two slice drifts with widths of 4.8–5.08 m. The monitoring results show that the average convergence rates within this width range were lower than 0.25 mm/d, satisfying the stability requirement. These observations support the reasonableness of the numerical results and the recommended slice-drift width. The findings provide a reference for long-term stability assessment and width design of backfill-formed slice drifts in underhand backfill mining.