Search Results (3,094)

As tunnel engineering continues to advance toward deeper, longer, and more complex projects, the risks encountered during the construction phase have evolved into a combination of various disaster types and the accumulation of multiple contributing factors. Traditional empirical and semi-empirical risk management methods are increasingly revealing shortcomings in terms of timeliness, accuracy, and the ability to process multi-source data. In recent years, driven by advancements in computing power and sensor technology, artificial intelligence algorithms (AI algorithms) such as machine learning and deep learning have been rapidly adopted in tunnel construction risk management. This paper retrieved relevant literature from the Web of Science database covering the period from 2010 to 2025. After rigorous screening, 96 highly relevant papers were selected for bibliometric analysis. This paper systematically reviews research progress from two perspectives: algorithmic models and engineering applications. The review indicates that, in terms of algorithmic models, traditional machine learning, convolutional neural network, recurrent neural network, generative adversarial network, Transformer, and graph neural network constitute a multi-level technical framework encompassing feature representation, risk perception, and intelligent decision-making. In terms of applications, AI algorithms have been widely integrated into typical scenarios such as geological hazard identification and prediction, surrounding rock stability and deformation prediction, rock burst assessment and early warning, lining defect detection and structural safety assessment, construction-induced ground settlement prediction, and tunnel gas and fire hazard prediction, significantly enhancing risk identification and early warning capabilities. However, several challenges remain, including the scarcity of high-quality datasets, the prevalence of noisy, incomplete, and heterogeneous monitoring data, insufficient coupling between model interpretability and engineering mechanisms, limited cross-project transferability, and the lack of integrated management systems for multi-hazard lifecycle control. Based on this, this paper proposes future research directions in areas such as data infrastructure development, integration of mechanism constraints, and multi-hazard collaborative modeling, aiming to provide guidance for the further development of intelligent risk management in tunnel construction. Full article

Excessive fluoride intake from drinking water remains a public health concern in geogenic high-fluoride regions, yet direct evidence linking environmental fluoride levels to internal exposure in remote high-altitude areas is limited. This study integrated environmental monitoring with human biomonitoring to assess fluoride exposure and health risks in the Taruo Lake region of the Tibetan Plateau. Surface water (n = 45 for Taruo Lake; n = 8 for its tributaries) and groundwater samples (n = 4) were collected and analyzed for fluoride concentrations, and blood ionic fluoride (BIF) levels were measured in 122 local residents (47 adults, 75 children). The results showed that fluoride concentrations in most surface water tributaries of Taruo Lake and groundwater sources were below China’s drinking water standard, whereas those in Taruo Lake exceeded this limit (routine monitoring mean 2.54 mg/L; multi-site mean 2.79 mg/L). BIF levels were significantly higher in adults (0.126 ± 0.041 mg/L) than in children (0.075 ± 0.032 mg/L) and showed a positive correlation with age (r = 0.533, p < 0.001). Notably, 23.4% of adults and 1.3% of children exceeded 0.15 mg/L, an empirical threshold typical for healthy populations in non-endemic areas. Based on the hazard quotient (HQ) model recommended by the US EPA, most drinking water sources posed acceptable non-carcinogenic risks (HQ < 1). In contrast, Taruo Lake water presented an elevated risk (HQ > 1) in 2024 primarily due to the regional geological background, and although not used for daily drinking, this finding offers an indicative reference for local water management and risk prevention. This preliminary monitoring and biomonitoring assessment provides baseline data for future studies and underscores the necessity of continuous surveillance and evaluation of total dietary fluoride intake to protect the health of this vulnerable high-altitude population. Full article

Sandstone-type uranium deposits are the main source of uranium in China. The Ordos Basin, one of the most typical Mesozoic intracontinental sedimentary basins in northern China, is a major uranium-bearing basin in China. The Hangjinqi area is a significant uranium-bearing region in the northern Ordos Basin, with favorable geological conditions and promising exploration prospects for mineralization, and the Lower Cretaceous Huanhe Formation is one of the uranium-bearing strata in this area. This study focuses on the Huanhe Formation in the Hangjinqi area to investigate the governing factors of uranium enrichment and mineralization in this stratum. U-Pb dating of detrital zircons from sandstones of the Huanhe Formation reveals dominant peak ages of 2370–2585 Ma, 214–320 Ma, and 1805–2325 Ma, and secondary peak ages of 340–506 Ma, 1598–1797 Ma, and 110–150 Ma. The age results of the selected detrital zircons indicate that the provenance of the Huanhe Formation is mainly derived from three sources: (1) the 2.6–2.5 Ga TTG gneisses and granulites in the Yinshan Block; (2) the Paleoproterozoic (2500–1800 Ma) khondalites and granitic gneisses in the Daqingshan–Wulashan–Jining area, as well as granites in the Yinshan area; and (3) large-scale intermediate–acidic intrusive rocks and volcanic rocks of the Yinshan orogenic belt, whose ages range from 110.9 to 505.9 Ma (predominantly Paleozoic). These source rocks may have provided a potential uranium source. The paleoclimate proxies, including Sr/Cu, Sr/Ba, V/Cr, Ni/Co, and Fe²⁺/Fe³⁺ ratios, combined with the Chemical Index of Alteration (CIA) and the Index of Compositional Variability (ICV), suggest that the Huanhe Formation was formed in a relatively arid and oxidized environment with a low degree of chemical weathering, which facilitated the migration of uranium-bearing ore-forming fluids. The sedimentary environment, provenance, and paleoclimate created favorable geological conditions for uranium enrichment in the Huanhe Formation of the northern Ordos Basin. Full article

This research examines the hydrothermal corrosion behaviour of ceramic matrix composites (CMCs) under highly alkaline conditions (pH > 11.5) in the framework of a deep geological repository for high-level radioactive waste (HLW). The study focuses on the degradation of alumina powder and fibres, key constituents of an oxide/oxide CMC material. Accelerated ageing experiments were conducted in a highly alkaline aqueous environment (pH > 11.5, T = 70 °C for 220 days and T = 150 °C for 30 days). The research used a cross-disciplinary approach integrating thermodynamic calculations and physicochemical analyses to determine the degradation mechanisms of alumina powder and fibres induced by contact with the aqueous ageing solution. Characterisation of the aged alumina powders and fibres revealed the presence of unaltered alumina, hydrated alumina, amorphous phases, and calcium carbonate precipitates from the aqueous solution. Thermodynamic calculations indicate (1) the hydrolysis of alumina to diaspore and (2) the formation of an aluminosilicate phase and calcium carbonate. However, experimental results reveal kinetic limitations, such as the preferential formation of boehmite over diaspore, and morphology-dependent degradation pathways (protective-layer formation on fibres and partial dissolution of powders). Full article

Min County experiences intense debris flow activity due to extreme weather and geological events. This study analyzes debris flow activity in Min County using GIS spatial analysis, time-series statistics, correlation analysis, periodic fitting, and field investigations across four event-based key periods (2002, 2012, 2013, and 2020). Long-term meteorological records (1951–2020) are introduced to support climatic trend analysis. Results indicate that stratigraphic lithology and fault tectonics control about 85–90% of the spatial distribution of debris flows, while extreme short-duration rainstorms trigger large-scale outbreaks and strong earthquakes further intensify activity. The high-occurrence cycle of debris flows (7–8 years) does not fully align with the annual wetness cycle (12 years). On a short time scale (years to decades), extreme earthquakes and rainstorms exert more significant impacts than normal precipitation patterns. This study preliminarily infers potential future peak periods of debris flows in Min County, with uncertainty from climate fluctuations and uncertain seismic events considered. The coupled mechanism of seismic weakening and rainfall triggering, together with lag-time characteristics, is revealed to support disaster prevention and mitigation. Full article

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. Full article

Accurate recognition of fractures on tunnel faces is essential for evaluating surrounding-rock integrity and ensuring excavation safety, yet it remains difficult because fracture traces are slender, irregular, discontinuous, and easily obscured by complex rock textures and illumination variability. This study proposes MF-DeepLabv3+, an enhanced DeepLabv3+-based semantic segmentation framework for tunnel-face fracture identification and geometric characterization. Unlike existing attention-based DeepLab variants that mainly enhance global feature representation, MF-DeepLabv3+ is specifically designed for thin and discontinuous tunnel-face fracture segmentation by integrating a Multi-Scale Cross Attention module for multi-receptive-field feature interaction, a Feature Smoothing Module for noise suppression and fracture-continuity enhancement, and a lightweight MobileNetV2 backbone for improved computational efficiency. A dataset of 2153 annotated images collected from the Qingdao Jiaozhou Bay Second Subsea Tunnel and the Yantai Urban Rapid Road Tunnel was established for training and evaluation. Considering the strong class imbalance between fracture and background pixels, Accuracy is reported only as an auxiliary metric, while mAP, mIoU, per-class IoU, and fracture-specific Precision, Recall, and F1-score are emphasized to provide a more reliable assessment of segmentation performance. Comparative and ablation experiments show that MF-DeepLabv3+ achieved 82.56% mAP and 62.99% mIoU, with an auxiliary Accuracy of 92.47%. Compared with the original DeepLabv3+ baseline, the proposed model achieved a substantial improvement in mAP and a modest improvement in mIoU, indicating enhanced fracture recognition capability and slightly improved region-level overlap and a moderate increase in computational cost in exchange for improved segmentation performance. Fracture grouping and post-processing were further performed using edge detection, Hough transform, connected-component analysis, and fitted-line geometry to estimate fracture length and width. The proposed method therefore enables more reliable tunnel-face fracture recognition and provides quantitative geometric information for engineering assessment and geological interpretation. Full article

The Iberian Peninsula hosts one of the world’s most endemic fish faunas. Its extensive evolutionary, palaeogeographic, and geological history has produced a distinctive freshwater fish fauna. Many of these species have very limited distributions, making them especially vulnerable to habitat disturbance. Past monitoring of this biodiversity has revealed alarming results, indicating that most native Spanish species are at risk. The causes of this serious situation are varied and reflect the ongoing deterioration of freshwater ecosystems. The main pressures faced by populations include pollution, loss of river connectivity caused by hydraulic infrastructure, regulation of watercourses, water extraction, fishing, and the presence of invasive species. Additionally, the effects of climate change worsen the risk of extinction for these populations, particularly through the increased frequency and intensity of droughts and heatwaves. It is evident that current planning models and investments are inadequate to conserve freshwater fish. To prevent the extinction of many populations in Spain, especially Iberian endemics, it is crucial to change the management of aquatic ecosystems and adopt integrated solutions that halt population declines and promote the sustainable use of aquatic resources. The IUCN Red Lists of Threatened Species are vital indicators of biodiversity health and are widely used to guide and structure conservation efforts. These lists, published in the Red Books, result from a thorough evaluation process that employs specific categories and criteria to assess the extinction risk of species, both globally and regionally. This report presents preliminary findings from a monitoring study on the current state of freshwater fish in Spain. The monitoring results reveal that, based on IUCN assessment criteria, two species are classified as extinct (EX), four as critically endangered (CR), eighteen as endangered (EN), and twenty-one as vulnerable (VU). Of fifty-seven species documented, 79% are considered threatened. The project’s final outcome is the development of the Atlas and Red Book of Freshwater Fish of Spain. This resource includes the main native and invasive freshwater and diadromous fish species, offers detailed information on their biological and ecological traits, and provides an up-to-date inventory of records along with an assessment of their conservation status. Full article

Geological observations, excavation performance records, field monitoring data, and support applications obtained during construction were examined in relation to excavation-induced structural behavior. Monitoring systems, including tiltmeters, extensometers, and distomat measurements, were used to evaluate deformation behavior in buildings located near the tunnel alignment. This study additionally discusses the differences between the preliminary FEM-based deformation predictions reported during the design stage and the structural behavior observed during excavation. The results indicate that groundwater-sensitive claystone sections generated significant excavation and stability problems despite controlled excavation and support measures. High groundwater inflow (30–35 L/s) caused base instability, unfavorable excavation conditions, and increased deformation risks. Field observations indicated substantially greater deformation behavior than the preliminary FEM-based predictions reported during the design stage. The findings demonstrate that shallow urban tunneling in weak and groundwater-sensitive formations may generate more complex ground–structure interactions than those represented in preliminary numerical assessments. This study highlights the importance of continuous field monitoring, adaptive support strategies, groundwater control measures, and observational excavation management practices for improving tunnel safety and reducing risks to nearby urban structures. Full article

Hydrothermal alteration mapping is a critical component of porphyry copper exploration because alteration assemblages provide important vectors toward mineralization. This study presents a systematic evaluation of supervised machine learning algorithms for delineating hydrothermal alteration zones using Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) short-wave infrared (SWIR) surface reflectance data (AST_07XT). The investigation focuses on the Nain region within the central Urumieh–Dokhtar Magmatic Arc (UDMA), Iran, a major metallogenic belt hosting numerous porphyry copper systems. Representative spectral endmembers corresponding to Al–OH-bearing and Mg–OH-bearing hydrothermal alteration minerals were extracted using Minimum Noise Fraction (MNF), Pixel Purity Index (PPI), and n-dimensional visualization techniques. These endmembers were subsequently used to train and evaluate a comprehensive suite of supervised machine learning classifiers, including linear, kernel-based, tree-based, ensemble, probabilistic, boosting, and neural-network algorithms for pixel-wise hydrothermal alteration mapping. Model performance was evaluated using multiple statistical metrics, including overall accuracy (OA), average accuracy (AA), precision, recall, F1-score, Cohen’s kappa coefficient, area under the ROC curve (AUC), spatial cross-validation accuracy, uncertainty analysis, and spatial agreement analysis. Among the evaluated classifiers, SVM_Linear, SVM_RBF, LDA, and MLP achieved the highest classification performance, with overall accuracies exceeding 94% and strong spatial consistency between classified maps. The resulting alteration maps display spatially coherent distributions of Al–OH and Mg–OH minerals that are consistent with established hydrothermal alteration zoning models in porphyry–epithermal systems. The mapped hydrothermal alteration zones show strong spatial correspondence with known mineralized areas and alteration patterns within the Urumieh–Dokhtar Magmatic Arc, confirming the geological reliability of the classification results. Uncertainty analysis further indicates high model confidence across most alteration zones, with higher uncertainty values mainly restricted to transitional and spectrally heterogeneous regions. The results demonstrate that integrating ASTER SWIR imagery with supervised machine learning algorithms provides a robust, scalable, and transferable framework for regional-scale hydrothermal alteration mapping and mineral exploration in porphyry copper provinces. Full article

Geological disasters are frequently triggered in steep mountainous mining areas due to the coupling effects of underground excavation and slope stability, yet the applicability of traditional rock movement theories in such terrains remains unclear. This study investigates an extremely steep coal mine in southwestern China, integrating engineering geological surveys, unmanned aerial vehicle (UAV) measurements, InSAR monitoring, and rock movement theoretical calculations to analyze the impact of mining on mountain deformation and slope stability. The results show that the study area exhibits steep slopes (55–85°) and gently inclined, reverse-layered rock masses controlled by structural fracture zones, creating a geological environment prone to mining-induced landslides. The 1151 working face lies at a depth of 286–470 m, with a protective coal pillar of approximately 160 m left between the excavation and the cliff zone. InSAR monitoring indicates cumulative LOS deformation rates of −0.98 to 0.55 cm/a, with subsidence concentrated above the working face, while existing landslides in the cliff zone show no significant deformation. Comparison between theoretical calculations and InSAR inversion reveals that InSAR boundary angles (downslope 61–68°, upslope 67–73°) exceed theoretical predictions (downslope 48–52°, upslope 55°), indicating that complex topography and rock mass structure constrain mining-induced deformation propagation. The findings demonstrate that appropriately designed protective coal pillars and avoidance of unstable slopes can effectively mitigate the impact of mining-induced disturbances on existing hazards. This study provides valuable reference for landslide risk assessment and disaster prevention in extremely steep mining regions. Full article

The Tonglushan ore field is an important component of the polymetallic mineralization belt in the middle and lower reaches of the Yangtze River in China. The skarn-type Cu, Fe, Au, and Mo molybdenum deposits are mainly developed in the contact zone between the rock mass and the strata, as well as in the contact zone between residual and capturing bodies in the rock body. The distribution of ore bodies is controlled by faults and strata, but there is a lack of large-scale geophysical information on the contact relationship between the ore-forming geological body and the host rock and on the deep spatial morphology of the ore-forming structure and intrusion rock. The study uses the JS-WEM2 wide-field electromagnetic instrument and the RS230 spectrometer to conduct the ground frequency domain electromagnetic and radiometric spectrometry measurements on four profiles. The measurement results indicate that the fault distribution in the Tonglushan ore field is predominantly in the NW-trending and NE-trending directions. The NW-trending Tonglushan–Lijiashan fault (F2) is a steeply dipping fault; the NE-trending faults are minor, with steep dips, generally extending no deeper than −1000 m. The Tonglushan stock exhibits the northeastward uplift, characterized by southward overlap and southeastward dip. The deep resistivity is greater than 3000 Ω·m, while the resistivity below −1000 m is less than 2000 Ω·m due to the fault influence. The ore bodies are mainly distributed along the contact zones where variations in the occurrence of the rock intersect with the strata. On resistivity profiles, these zones show the gradient variation in resistivity and the distorted shape of the resistivity contour line. The radioactive element contents of wall rock above the ore bodies are characterized by high U, high Th, and low K. The Wide-Field Electromagnetic Method (WFEM) can effectively detect the distribution and morphology of rocks and faults, and combined with the radioactive characteristics of geological bodies, it can effectively identify concealed faults and the favorable mineralization target areas. Novelty: The study combines the WFEM with radiometric measurements to reduce uncertainty in exploration compared to using only one method. It improves the detection accuracy and target identification ability of deep hidden ore bodies, providing the new technical method for deep mineral exploration in complex structural areas. Full article

Orthorhombic normal fault networks in sedimentary basins and their formation mechanisms are of significant geological importance. Orthorhombic normal fault networks and planar H-shaped normal fault networks (HNF) developed in distinct locations along the Linshang dextral transtensional fault, with the HNF on the eastern hanging wall and the orthorhombic normal fault networks on the western footwall. Using 2D and 3D seismic data, we investigated the geometry, evolution, and formation mechanisms of these fault networks within the regional tectonic context. The HNF consists of systematically arranged E–W-trending normal faults and N–S-trending cross normal faults. The orthorhombic normal fault networks comprise four sets of normal faults. Expansion indices and balanced cross-section analyses indicate that both these networks formed contemporaneously during the E₂s³ stage. Mechanical analysis suggests that differences in the local stress field led to the development of these networks in different segments of the Linshang Fault. The HNF formed sequentially within a single tectonic phase. In contrast, the orthorhombic normal fault networks developed within a 3D strain field driven by the combined effects of dextral transtension along the Linshang Fault and footwall tilting. Hydrocarbon exploration results confirm that these normal fault networks exert significant control on hydrocarbon migration pathways and accumulation patterns. Full article

Tight gas is a critical unconventional energy resource, yet the geological characteristics and accumulation processes of tight gas in China’s Songliao Basin remain poorly documented. This study aims to investigate the tight gas system in the Songliao Basin as a representative continental basin, with key objectives including evaluating source rock and reservoir properties via mineralogical and geochemical analyses, characterizing lithologies and pore types, determining the gas charging mechanism in tight media, and identifying the main controlling factors for accumulation. Geochemical results indicate that the Shahezi Formation contains medium to good mudstones and excellent coals. Reservoirs consist of tight sandstones and conglomerates deposited in fan delta and braided river delta systems, with pore spaces dominated by dissolution pores and microfractures, resulting in ultra-low porosity and permeability. Conventional buoyancy-driven migration is ineffective; instead, gas charging is driven by hydrocarbon generation expansion force, creating overpressure that expels pore water and forces gas into reservoirs through fault-sand conduits. Accumulation is controlled by continuous gas supply from thick, highly mature source rocks, dissolution-enhanced and fracture-dominated reservoir space, and sufficient source–reservoir pressure difference. This study elucidates tight gas characteristics and accumulation mechanisms in continental basins, providing data applicable to both continental and marine settings. Full article

Pegmatite dikes are important prospecting indicators for rare-metal deposits, whereas traditional methods for pegmatite dike identification are constrained by the limited capability of human visual interpretation to capture information from remote sensing imagery, resulting in low identification accuracy and efficiency. In recent years, global research on semantic segmentation of different surface features and remote sensing-based mineral exploration using deep learning methods and high-resolution remote sensing imagery has made significant progress; however, studies on surface-exposed geological bodies such as pegmatite dikes remain highly insufficient. To address the key problem of efficiently identifying pegmatite dikes in remote sensing imagery, this study proposes an improved model based on UNet++, termed GAD-UNet++. In the field of remote sensing geology, this study constructed a pegmatite dike semantic segmentation dataset based on high-resolution RGB imagery by using 0.66 m RGB imagery for visual delineation and ZY1F hyperspectral data for spectral constraint and label refinement; on this basis, semantic segmentation of surface pegmatite dikes in the Yilanlike area of the South Tianshan Mountains, Xinjiang, was conducted using RGB remote sensing image patches as model input. Specifically, because pegmatite dikes are small targets characterized by slender structures, indistinct boundaries, and sparse regional distribution, this study introduced a lightweight feature extraction structure (GhostNetV2) and a long-range dependency attention module (DFC) at the encoder stage, and further incorporated the Coordinate Attention module (CA) to enhance spatial localization and boundary representation of the targets. Finally, focal cross-entropy loss and a deep supervision strategy were adopted to improve the accuracy of semantic information extraction for pegmatite dikes, as well as the training stability and segmentation accuracy under class-imbalance conditions. The results show that the proposed model achieved an mIoU of 93.11% and an F1-score of 94.95% on the test set. Compared with existing semantic segmentation models, the proposed model achieved superior performance in both identification accuracy and computational efficiency for pegmatite dikes. In addition, this study delineated 18 potential pegmatite dike enrichment zones in the Yilanlike area, providing technical support for remote sensing-based rare-metal prospecting and geological interpretation in the study area. Full article