To address the challenges of low detection accuracy and weak generalization in identifying mining-induced ground fissures from UAV imagery, caused by their slender and discontinuous morphology, complex background clutter, and multi-scale surface features, this paper proposes an enhanced deep semantic segmentation model, SAG-DeepLabV3+ (with Spatial Vision Transformer, Attention mechanisms, and Adaptive Gated Fusion). Specifically, to enhance global context modeling and fine boundary delineation, we introduce a Spatial Vision Transformer (SVT) branch within the Atrous Spatial Pyramid Pooling (ASPP) module. We further employ a dual attention mechanism, sequentially combining Squeeze-and-Excitation (SE) and a Convolutional Block Attention Module (CBAM), for progressive channel and spatial feature refinement. Moreover, an Adaptive Gated Fusion (AGF) module is designed to dynamically optimize the fusion of multi-level decoder features. Experiments on a dedicated UAV-based mining fissure dataset comprising 1280 annotated images show that SAG-DeepLabV3+ achieves a state-of-the-art mean Intersection over Union (mIoU) of 79.52% (with Xception backbone) and 79.19% (with lightweight MobileNetV2 backbone), surpassing DeepLabV3+, U-Net, and PSPNet by a significant margin. Furthermore, by leveraging transfer learning (pre-training on the public CrackVision12K dataset and fine-tuning on our mining fissure dataset), the model’s mIoU is further elevated to 82.04%, demonstrating superior generalization capability. The proposed SAG-DeepLabV3+ effectively balances high accuracy with operational efficiency, fulfilling the potential demand for lightweight automated fissure monitoring under resource-limited field deployments, and lays a foundation for subsequent real-time on-site deployment verification.

The hilly terrain at the western foot of the Wanda Mountains boasts intricate geological conditions, compounded by long-term mineral extraction and farming activities. The multi-sourced heavy metals stored within stream sediments create substantial obstacles to accurate source apportionment and targeted risk mitigation. In this work, stream sediment samples were collected across the study watershed to test concentrations of eight heavy metals: As, Cd, Cr, Ni, Cu, Pb, Hg and Zn. Pollution and ecological risk assessments were implemented via the pollution load index (PLI), geo-accumulation index (I_geo) and potential ecological risk index (RI). Kriging interpolation was utilized to visualize and interpret the spatial variation patterns of heavy metals. Combined correlation analysis, principal component analysis (PCA) and the Absolute Principal Component Scores–Multiple Linear Regression (APCS-MLR) receptor model were adopted to qualitatively and quantitatively distinguish pollution endmembers of heavy metals. The main results are as follows: Cr, Cd, Pb and As show significant enrichment, whereas Ni, Cu, Zn and Hg appear depleted; all measured heavy metals present strong spatial variability. Weathering of basic bedrocks governs the widespread high-value zones of Cr, Ni, Cu and Zn. Patchy enrichment of Pb, As and Cd is concentrated in river valley farmlands, with no continuous anomalous zones detected for Hg. The watershed as a whole suffers mild contamination and low potential ecological risk, with only sampling points surrounding mines and agricultural lands experiencing moderate-to-severe pollution and medium ecological hazards. Three source endmembers are identified in the region: a natural geogenic endmember (Cr, Ni, Co, etc.), a mixed mining-associated anthropogenic endmember (Zn, Hg, Cu, Cd), and an agricultural non-point endmember (Pb, As, Sb). Quantitative APCS-MLR calculations confirm that mining disturbances serve as the predominant anthropogenic input for Zn, Hg, Cu and Cd; agricultural practices dominate the accumulation of As and Pb; and geogenic contributions stay marginal for all elements. This study corroborates that regional lithology sets the natural geochemical baseline of heavy metals, while anthropogenic interferences function as the primary driver of localized pollution anomalies. The conclusions can deliver theoretical support for heavy metal pollution remediation in similar hilly watersheds throughout Northeast China.

Mining-subsidence-induced surface cracks pose substantial risks to ecological systems, infrastructure stability, and mining safety. Their thin, elongated, discontinuous, and low-contrast characteristics make accurate detection from unmanned aerial vehicle (UAV) imagery challenging, particularly under complex environmental conditions. This study proposes an enhanced YOLO11n framework for detecting surface cracks in mining subsidence areas. Switchable Atrous Convolution (SAConv) was incorporated to strengthen multi-scale feature extraction, while Cascaded Group Attention (CGA) was introduced to suppress background interference and improve feature discrimination, and Shape-IoU loss was adopted to enhance the localization of slender crack targets. The model was evaluated using 5000 annotated UAV images collected in the Zhungeer mining area. It achieved a precision of 85.6%, a recall of 77.9%, an mAP@0.5 of 84.3%, and an F1-score of 81.6%. Compared with the baseline YOLO11n, precision, recall, and mAP@0.5 increased by 1.4, 4.6, and 3.2 percentage points, respectively. Cross-dataset evaluation on the public Crack500 dataset further demonstrated improved robustness under domain variation. These results indicate that the proposed framework improves the detection and localization of slender and discontinuous cracks in complex mining environments, supporting its application in UAV-based geological hazard monitoring.