With the rapid progress of industrialization and urbanization, large amounts of industrial wastewater and mining waste have been discharged into rivers. The problem is especially severe in areas with intensive mineral resource development and hardware manufacturing. Moreover, frequent heavy rainfall and flooding during the flood season significantly increase surface runoff and sediments resuspension, promoting the mobilization and redistribution of heavy metals (HMs) in river systems. Therefore, it is of great practical importance to systematically identify the distribution characteristics and ecological risks of HMs pollution in such regions under changing climatic conditions. Eighty-five surface sediment samples were collected in Southwest China, and the concentrations of As, Hg, Cd, and Pb were determined. The geo-accumulation index (I_geo) and the potential ecological risk index (RI) were used to assess contamination levels and ecological risks, and principal component analysis (PCA) and positive matrix factorization (PMF) were applied to trace pollution sources. The results show that Cd and Hg have similar spatial patterns, with high concentrations mainly downstream of mining areas and industrial parks. I_geo and RI assessments indicate that Hg pollution in sediments is severe in four major rivers of Dazu District, followed by Cd, while As and Pb show relatively low pollution levels. Source apportionment revealed that industrial and traffic-related activities contribute 55.05% of HMs inputs, mining activities account for 41.28%, and natural sources contribute 3.67%. Cd and Pb mainly originate from industrial emissions and traffic, Hg is primarily associated with mining, and As is derived from natural sources.

Precise assessment of the vulnerability characteristics of human–land systems is es-sential for ensuring ecological security and sustainable development in regions affected by large-scale engineering projects. Using the Three Gorges Reservoir Area as a case study, this research develops a comprehensive evaluation index system based on a coupled framework of “Geo-environmental Background—Ecosystem Structure—Anthropogenic Perturbation.” By integrating deep neural networks (DNN), convolutional neural networks (CNN), and the analytic hierarchy process (AHP) with multi-source data, we perform a thorough assessment of eco-geological vulnerability. The results reveal the following key findings: (1) In eco-geological vulnerability assessment, deep learning methods (DNN and CNN) significantly outperform traditional AHP, with CNN showing superior precision and specificity due to its ability to extract local spatial features effectively, while DNN exhibits stronger overall robustness. (2) The spatial distribution of eco-geological vulnerability in the reservoir area is notably heterogeneous, with high and Extreme vulnerability zones concentrated along the main riverbanks, major tributary estuaries, and urban peripheries. These zones are strongly coupled with steep terrain, erodible lithology, high geological hazard risks, and intensive human activity. (3) Although the overall vulnerability remains relatively stable, local sensitivity is increasing. Ecological restoration projects in mountainous regions have effectively mitigated vulnerability in the hinterlands, while rapid urbanization has exacerbated vulnerability in emerging urban areas. The study concludes that the spatial pattern of vulnerability is primarily influenced by the geological–ecological background, with human disturbance—especially land use intensity—acting as the primary driver of vulnerability dynamics and local hotspots of high vulnerability. Based on these findings, we recommend a differentiated management approach tailored to eco-geological units: for high and extreme vulnerability zones along river and urban corridors, efforts should focus on spatial constraints and systemic resto-ration; for low and negligible vulnerability zones in mountainous areas, strategies should aim to enhance ecosystem quality and stability, thus fostering a coordinated regional ecological security framework.

Metal mining affects an estimated 479,200 km of river channels worldwide, and contaminated sediments threaten aquatic ecosystems and human health long after mining ceases. This study examined 53 surface sediment samples from the Xiaozi River and six tributaries in a historical coal-mining area of Chongqing, southwestern China. As, Cd, Pb, Hg and Cr were evaluated using the geoaccumulation index, potential ecological risk assessment and freshwater sediment quality guidelines; differences among rivers were tested with the Kruskal–Wallis test, and sources were explored using APCS–MLR and PMF. Hg and Cd showed the greatest enrichment (mean geoaccumulation indices 1.19 and 0.35). Hg exceeded the background value at all sites and dominated potential ecological risk, accounting for 93.4% of the maximum risk index (914) in the Xibu River. Cr exceeded the probable effect level at 19 sites, whereas As and Hg showed localized exceedances. Concentrations of As, Cd, Pb and Cr differed significantly among rivers (p < 0.01), whereas those of Hg did not. Both receptor models identified Cr–Pb and As–Cd components, whereas Hg was associated mainly with a separate component. These findings identify Hg as the main management priority, together with tributary-specific monitoring of As, Cd and Cr.

Ecological vulnerability assessment serves as a prerequisite for ecological governance, yet evaluating large-scale ecological vulnerability remains challenging. To address this challenge, this study integrates geological elements into ecological vulnerability assessment, taking Ruyuan Area in the Northern Guangdong Mountains, China, as a case study. The area faces ecological hazards such as land desertification and soil erosion, indicating severe governance challenges. This study selected 14 ecological vulnerability factors and constructed assessment models based on Deep Neural Networks (DNNs) and Convolutional Neural Networks (CNNs). A total of 800 ecological vulnerability sampling points were obtained by combining field survey data with remote sensing imagery. The models were trained using binary vulnerability labels. The resulting continuous probability outputs were then classified into five vulnerability levels using the natural breaks method to generate the final ecological vulnerability map. It should be noted that the multi-level vulnerability map represents graded probability-based differentiation rather than supervised multi-class prediction. Model performance was validated using three metrics: Area Under Receiver Operating Characteristic Curve (AUC–ROC), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE). The CNN (AUC = 0.916) model outperformed the DNN model (AUC = 0.895). According to the CNN-based classification results, non-vulnerable, slightly vulnerable, mildly vulnerable, moderately vulnerable, and highly vulnerable areas accounted for 36.19%, 22.85%, 14.24%, 12.31%, and 14.41% of the total area, respectively. High ecological vulnerability zones were concentrated in Daqiao, Luoyang, Dabu, and parts of Rucheng towns, with soil parent material and vegetation coverage identified as the main contributing factors, among which parent material was the most important. This finding underscores the notable impact of geological factors on local ecological vulnerability. Based on these results, nine ecological–geological subareas were delineated, and targeted ecological protection and restoration recommendations were proposed. This study, employing machine learning techniques, constructed an ecological vulnerability assessment model incorporating geological elements, thereby providing scientific support for targeted ecological governance in the study area.

The Yangshikeng mercury deposit in southeastern Chongqing is a carbonate-hosted Hg deposit within the South China low-temperature metallogenic domain, but its metallogenic age and genetic mechanism remain unclear. In this study, we present integrated in situ U-Pb dating of calcite from the main mineralization stage, together with trace element and C-O-Sr isotopic analyses of calcite from different mineralization stages to constrain the ore-forming process. Calcite U-Pb dating yields two age populations: a main mineralization age of 217 ± 12 Ma and a younger age of 114 ± 56 Ma. The Triassic event corresponds to the collision between the Indochina Block and the South China Craton, which induced intense regional compression and generated large-scale fault systems that facilitated deep fluid circulation and basinal brine formation. The Cretaceous age may record later hydrothermal disturbance or overprinting. Calcites from the main mineralization stage (Cal-I) have elevated ⁸⁷Sr/⁸⁶Sr ratios (0.7135–0.7187), which are higher than those of marine carbonates (0.7080–0.7110) and comparable to the Neoproterozoic Banxi Group basement (0.7131–0.7281), indicating contribution from the basement source. Late-stage calcites (Cal-II) show a wider range of ⁸⁷Sr/⁸⁶Sr ratios (0.7091–0.7198), overlapping the host dolostone. They display increased total REE contents and weakened LREE/HREE fractionation, indicating a contribution from the host rock. These integrated geochemical constraints suggest that the ore-forming materials of the main mineralization stage are derived from a radiogenic basement source, whereas the late stage involved mixed contributions from the Qingxudong Formation wall rock and early-stage calcites through recrystallization or fluid–rock interaction. The main mineralization stage is related to a relatively closed basinal brine system, while the late stage records fluid mixing and progressive opening of the system.