Search Results (1,649)

The Wulonggou gold district is located on the northern margin of the Qinghai–Tibet Plateau and represents the most promising area for mineral exploration within the East Kunlun mineralized belt in Qinghai Province. Previous studies on this gold district have lacked a comprehensive assessment of its metal mineralization potential. This paper conducts a comprehensive investigation of the distribution patterns of geochemical data in the Wulonggou gold district, employing multivariate statistical analysis to explore the distribution characteristics of different geochemical elements. Based on the analysis of geochemical anomaly patterns, the median + 2MAD method and fractal method were further introduced to delineate geochemical anomalies. For comparison, machine learning methods—including the radial basis function link network (RBFLN) model and the Bayesian-optimized random forest (BO-RF) model—were also applied to generate different geochemical anomaly maps. By comparing the results obtained from each method, we found that the BO-RF model performed best in predicting geochemical anomalies. Based on the above information, the BO-RF model was integrated with geological background information to delineate prospective areas. These findings provide important clues for mineral exploration and development in the Wulonggou area and can serve as a reference for other regions with similar geological backgrounds. Full article

With the rapid expansion of metro tunnel construction, safety risks such as collapse, water inrush, and gas explosion have become increasingly critical. Existing warning models often lack fine-grained disaster type identification and dynamic risk assessment capabilities. This paper proposes a two-stage intelligent warning framework based on multi-source data fusion. First, a dual-autoencoder structure (MLP-AE and LSTM-AE) extracts deep features from static geological parameters and dynamic monitoring sequences. Then, a multilayer perceptron (MLP) classifier identifies four typical states: normal, collapse, water/mud inrush, and gas explosion. Subsequently, a regression model predicts a continuous risk score, mapped to three risk levels: Safe, Moderate Risk, and Significant Risk. Experimental results demonstrate that, compared with Decision Tree (DT), Gradient Boosting Decision Tree (GBDT), and Bayesian Network (BN), the proposed framework achieves superior performance in risk level identification, with an accuracy of 91% and an F1-score of 0.87. Notably, it exhibits particularly strong recall for severe (Level III) risks, which is crucial for practical engineering applications. The proposed framework provides a practical and intelligent approach for safety warning in metro tunnel construction. Full article

Malawi lies within the southern segment of the East African Rift System and is exposed to infrequent but potentially damaging earthquakes. While recent advances in fault mapping, seismic monitoring, and hazard modelling have substantially improved scientific understanding of earthquake hazard in the Malawi Rift Zone, the practical reduction in seismic risk remains limited. This Perspective paper argues that earthquake resilience in Malawi is constrained less by scientific uncertainty than by challenges in integrating existing hazard knowledge into governance, planning, and preparedness. Drawing exclusively on published geological, geophysical, engineering, and policy literature, the paper synthesises evidence on seismic hazard, historical earthquake impacts, institutional preparedness, and barriers to the operational use of scientific risk assessments. An integrated, multi-pillar framework is proposed to support improved coordination between science, governance, infrastructure practice, and community preparedness. The framework is conceptual in nature and is intended to inform policy dialogue, prioritisation, and future empirical research rather than to provide a validated operational model. While grounded in the Malawian context, the insights presented are relevant to other low-income, rift-hosted regions facing similar challenges in translating earthquake science into effective disaster risk reduction. Full article

Deep-seated landslide complexes are widespread in soft-rock hill-country landscapes, yet their regional morphometric organisation and controlling factors remain insufficiently quantified. This study uses high-resolution (1 m) airborne LiDAR-derived terrain data integrated with geological and drainage-network datasets to investigate landslide complexes in the eastern Tararua District, New Zealand. A relative, unit-based morphometric framework is applied to compare terrain derivatives (including slope, aspect, and multi-scale relative relief) between mapped landslides and their host geological units. To isolate intrinsic lithological controls from geomorphic influences, the analysis is restricted to landslides occurring entirely within a single geological unit. The results indicate that lithology exerts first-order control on landslide morphometry, while fluvial incision and valley confinement regulate landslide initiation and persistence. Landslides are preferentially associated with low- to mid-order channels, indicating strong hillslope–channel coupling within a young, actively uplifting landscape. A conceptual threshold framework is proposed, showing that landslides develop where lithological susceptibility and relief amplification jointly exceed stability thresholds. By integrating geological information with LiDAR-based morphometric analysis, this study provides a transferable framework for distinguishing instability regimes and improving understanding of sediment dynamics and landscape evolution in soft-rock terrains. Full article

Tight conglomerate reservoirs are characterized by strong heterogeneity, significant in-situ stress differences, and unbalanced fracturing stimulation, which make fracture pressure prediction challenging and severely restrict the effectiveness of reservoir stimulation and ultimate recovery. Although acid pretreatment is an effective means to reduce fracture pressure, its quantitative relationship with fracture pressure remains unclear. There is an urgent need to establish a systematic method that integrates reservoir heterogeneity characterization, data augmentation, and intelligent prediction. Aiming at the tight conglomerate reservoir in the MH Block, this study proposes an intelligent fracture pressure prediction and acid pretreatment optimization method that integrates Self-Organizing Maps (SOMs), Generative Adversarial Networks (GANs), and Transformer models. First, SOM is used to perform unsupervised clustering of logging parameters to identify different geological feature categories and achieve fine-scale characterization of reservoir heterogeneity. Second, to address the issue of limited samples within each cluster, GAN is employed for high-quality data augmentation to expand the training sample set. Finally, a fracture pressure prediction model is constructed based on the Transformer architecture, and the influence of acid treatment parameters on fracture pressure is quantitatively analyzed using the SHAP method and laboratory experiments. The results show that the proposed model achieves a coefficient of determination (R²) of 0.93, a root mean square error (RMSE) of 2.38 MPa, and a mean absolute percentage error (MAPE) of 2.02% on the test set, with prediction accuracy significantly outperforming benchmark models such as BPNN, XGBoost, and LSTM. Ablation experiments verify that both the SOM clustering and GAN augmentation modules effectively enhance model performance. Analysis of acid treatment parameters indicates that hydrofluoric acid (HF) concentration is the dominant factor influencing fracture pressure reduction, and the mud acid system exhibits a stronger synergistic effect compared to the single hydrochloric acid system. Reasonable optimization of acid concentration and dosage can significantly reduce fracture pressure (3.14–5.28 MPa). This method provides a theoretical basis and engineering guidance for accurate fracture pressure prediction and optimal design of acid pretreatment in tight conglomerate reservoirs. Full article

Highly deviated wells commonly exhibit large errors in horizon calibration because the logging path follows an inclined borehole trajectory, whereas post-stack seismic processing effectively treats wave propagation as vertical. This mismatch has received limited attention. Here, we performed horizon calibration and velocity-model building for highly deviated wells drilled in the Mahu Sag, Junggar Basin, and obtained three key findings. First, the assumed vertical travel path in post-stack data is the primary cause of the initial mis-tie for highly deviated wells. Second, calibration in the deviated interval requires a strategy distinct from that of vertical wells and may involve substantial stretching or squeezing of the original logs to achieve a consistent time-depth relationship. Third, the map-view projection of a highly deviated well is essentially linear; relative to vertical wells, it provides denser in situ velocity constraints and, with pseudo-well control, supplies 2D velocity information along the well-trajectory plane, thereby improving velocity-field modeling. Validation against drilling data showed that this workflow improved well ties and refined the velocity model, providing practical guidance for geological well planning and reducing drilling risk. Full article

During the interpretation of Borehole Radar (BHR) B-scan profiles, the accurate determination of the azimuth of geological targets in three-dimensional space is a critical issue for achieving precise anomaly localization and spatial structure inversion. However, existing directional BHR anomaly localization methods exhibit limited intelligence, insufficient adaptability to multi-site data, and weak generalization capability, rendering them inadequate for engineering applications under complex geological conditions. To address these challenges, a robust deep learning model, termed BSS-Pose-BHR, is developed based on YOLOv11n-pose for keypoint detection in directional BHR profiles. The model incorporates three key optimizations: Bi-Level Routing Attention (BRA) replaces Multi-Head Self-Attention (MHSA) in the backbone to improve computational efficiency; Conv_SAMWS enhances keypoint-related feature weighting in the backbone and neck; and Spatial and Channel Reconstruction Convolution (SCConv) is integrated into the detection head to reduce redundancy and strengthen local feature extraction, thereby improving suitability for keypoint detection tasks. In addition, a three-dimensional electromagnetic model of limestone containing a certain density of clay particles is established to construct a simulation dataset. On the simulated test set, compared with current mainstream deep learning approaches and conventional directional borehole radar anomaly localization algorithms, BSS-Pose-BHR achieves superior performance, with an mAP50(B) of 0.9686, an mAP50–95(B) of 0.7712, an mAP50(P) of 0.9951, and an mAP50–95(P) of 0.9952. Ablation experiments demonstrate that each proposed module contributes significantly to performance improvement. Compared with the baseline, BSS-Pose-BHR improves mAP50(B) by 5.39% and mAP50(P) by 0.86%, while increasing model weight by only 1.05 MB, thereby achieving a reasonable trade-off between detection accuracy and complexity. Furthermore, indoor physical model experiments validate the effectiveness of the method on measured data. Robustness experiments under different Peak Signal-to-Noise Ratio (PSNR) conditions and varying missing-trace rates indicate that BSS-Pose-BHR maintains high detection accuracy under moderate noise and data loss, demonstrating strong engineering applicability and practical value. Full article

This research provides an extensive evaluation of liquefaction induced by earthquakes in the Ionian Islands, specifically Lefkada, Cephalonia, Ithaki, and Zakynthos, through the compilation of a liquefaction inventory and GIS-based liquefaction susceptibility index (LiSI) maps. A total of 49 liquefaction sites from 20 causative earthquakes confirm that liquefaction is a recurrent geohazard in the area, primarily affecting coastal and low-lying areas with unconsolidated post-alpine deposits. The relationship between earthquake magnitude and maximum epicentral distance of observed liquefaction is consistent with global empirical datasets, indicating that moderate to strong earthquakes (M_w = 5.9–7.4) can induce liquefaction at considerable distances. The susceptibility model integrates eleven conditioning variables, classified as geological and geomorphological variables, hydrological indices and optical satellite imagery-derived data, within an analytic hierarchy process (AHP) framework. Lithology, age, and geomorphological unit emerged as the dominant conditioning variables. The LiSI maps confirm the zones previously identified in the inventory. Model validation and sensitivity analysis including confusion matrix components, key performance metrics and ROC analysis in coarser grid sizes demonstrate performance ranging from excellent (Zakynthos) to moderate (Lefkada and Cephalonia), while remaining inconclusive for Ithaki due to data limitations. The model exhibits generally conservative behavior, characterized by high precision and specificity but variable sensitivity, while it is largely stable across spatial resolutions in most cases. Full article

Airborne gravity survey serves as a rapid remote sensing technique for mapping subsurface mineral target and geological structure over large areas. The raw gravity data contains significant noise corrupted by airflow and the flight platform’s attitude. The Kalman Filter (KF) is an effective method for airborne gravity data denoising, but its processing accuracy is highly dependent on the empirical parameters. The multi-scale CNN-LSTM-attention adaptive Kalman Filter (MSC-LA-AKF) method is proposed to obtain high precision gravity data, which combines the multi-scale CNN (MSC), bidirectional long short-term memory (Bi-LSTM) and attention mechanism for adaptively estimating the parameters of KF. The multi-scale CNN uses convolution kernel of varying sizes to extract signal features at different scales. The Bi-LSTM combines two LSTM layers in opposite directions to extract the signal features at bidirectional time series, and can effectively identify time-varying noise signals. A multi-head attention mechanism with four attention heads ($H=4$) is incorporated into the output feature layer of the Bi-LSTM to adaptively calculate weights for different features and optimize the parameters of the KF. The simulated data tests demonstrate that the MSC-LA-AKF achieves notably higher denoising accuracy than both the finite impulse response (FIR) and wavelet filters, with detailed quantitative comparisons provided in the experimental section. The proposed method is applied to real airborne gravity data, and effectively removes noise signals and enhances the geological interpretation of gravity maps. Full article

Rainfall-induced landslides represent one of the most recurrent geohazards affecting the transportation network of southwestern Calabria (Italy). This study provides an integrated assessment of landslide occurrence and road damage along the Costa Viola by combining detailed geomorphological mapping, multi-temporal analyses, historical documentation (1950–2025), and GIS-based spatial data processing. A total of 261 landslides were mapped, affecting approximately 19% of the study area. Slides constitute the dominant movement type (66.7%), followed by complex landslides, flows, and falls. Landslide distribution is strongly controlled by geological and morphometric factors: more than 80% of mapped phenomena occur in highly fractured granitic and gneissic rocks, over 70% lie within 500 m of faults, and more than 90% are located within 300 m of streams. Slope gradient (25–55°) and local relief (350–550 m) further contribute to slope instability patterns. The historical dataset documents 237 landslide-induced road damage events over 75 years, with a marked increase in occurrence since the early 2000s. Most damage events affected the SS18 road and frequently corresponded to reactivations of pre-existing landslides, highlighting the long-term persistence of slope instability and the seasonal influence of intense autumn–winter precipitation. Overall, the results demonstrate that landslide hazard in the Costa Viola is governed by the interplay between structural, lithological, geomorphic, and climatic factors, compounded by anthropogenic modifications along road corridors. The combined landslide inventory and historical database provide a robust basis for risk mitigation, identification of critical road sectors, and future susceptibility and predictive modelling to support effective territorial planning. Full article

To address the challenge of surrounding rock instability in deep-buried tunnels crossing fractured fault zones, this study focuses on the Xigu Tunnel of the Lanzhou–Hezuo Railway. A combination of laboratory triaxial tests, an optimized multi-source advanced geological prediction workflow, and a site-specific parameter-weakened Mohr–Coulomb numerical simulation is employed to systematically reveal the physical–mechanical properties, spatial distribution, and deformation response of fractured rock masses under excavation-induced disturbance. The triaxial test results show that the average peak strength of the surrounding rock reaches 149.04 MPa; however, significant variability is observed among samples, and the failure mode exhibits a typical brittle–shear composite feature. The measured cohesion and internal friction angle are 20.57 MPa and 49.91°, respectively, indicating high intrinsic strength of individual rock blocks. Nevertheless, due to the presence of densely developed joints and crushed structures, the overall mass is loose and highly sensitive to dynamic disturbances such as blasting and excavation, revealing a unique mechanical paradox of high-strength rock blocks with low overall rock mass stability in deep-buried fractured zones. Joint TSP (Tunnel Seismic Prediction Ahead) and ground-penetrating radar (GPR) prediction reveals decreased P-wave velocity, increased Poisson’s ratio, and intensive seismic reflection interfaces; a quantitative index system for identifying the boundaries of narrow deep-buried fractured zones is proposed based on these geophysical characteristics. Combined with geological face mapping, these results confirm the existence of a highly fractured zone approximately 130 m in width, characterized by well-developed joints, heterogeneous mechanical properties, and localized risks of blockfall and groundwater ingress. The developed numerical model, with parameters weakened based on triaxial test and geological prediction data, effectively reproduces the deformation law of the fractured zone, and the simulation results agree well with field monitoring data, with peak displacement concentrated at section DK4 + 595, thus accurately identifying the center of the fractured belt as a key engineering validation result of the integrated technical framework. During construction, based on the identified spatial characteristics of the fractured zone and the proposed targeted support insight, enhanced dynamic monitoring and targeted support measures at the fractured zone center are required to ensure structural safety and long-term stability of the tunnel. This study develops an integrated engineering-oriented technical framework for deep-buried tunnels crossing narrow fractured zones, and provides novel mechanical insights and quantitative identification indices for such complex geological engineering scenarios. Full article

The hydrothermal-filling-type tremolite jade (nephrite) deposit in sanchakou, Qinghai Province is hosted in marine dolomite, and its ore-forming fluid sources and metallogenic mechanisms remain poorly constrained. Here, we conducted an integrated study involving field geological mapping, petrographic observations, and geochemical analyses (major and trace elements, REEs, Sr isotopes) to constrain material sources, fluid physicochemical features and mineralization processes of the deposit. Results show that the ore-forming fluids were derived from deep crust, with homogeneous initial ⁸⁷Sr/⁸⁶Sr ratios ranging from 0.70949 to 0.70959, distinctly higher than the host dolomite (~0.707683), indicating intensive water–rock interaction with Sr-radiogenic lithologies during fluid upwelling. The host dolomite provided the main Ca and Mg, while Si and partial Mg were sourced from deep Si-Mg rich hydrothermal fluids, with negligible contribution from coeval gabbro. The ore-forming fluids were rich in Si, Mg, large-ion lithophile elements and volatiles (e.g., F⁻), characterized by medium-high to medium-low temperature evolution and fluctuating oxidation states. Mineralization can be divided into four stages: deep fluid generation and migration, infiltration metasomatism and silicification, tremolite crystallization at peak oxidation, and open-space filling and jade precipitation. High-quality tremolite jade mainly formed via pulsed hydrothermal injection and direct crystallization in tectonic fractures. This study establishes a genetic model for hydrothermal-filling-type nephrite, enriching relevant metallogenic theories and supporting subsequent exploration. Full article

In karst mountainous areas where high-dimensional features coexist with extremely limited sample sizes, accurate landslide susceptibility mapping remains challenging. To address this issue, we propose an ensemble framework termed the Triple-Source Probabilistic Fusion Bidirectional Long Short-Term Memory network (TSPF-BiLSTM). The approach was tested in Sangzhi County, Hunan Province, by integrating three base learners—Random Forest (RF), LightGBM, and AdaBoost. Their raw outputs were first calibrated using five-fold Platt scaling to generate posterior probabilities on a unified scale. A bidirectional LSTM was then employed to perform deep nonlinear fusion of these cross-model probability features. Using a total of 618 landslide and 618 non-landslide samples (split into training and testing sets), the TSPF-BiLSTM model achieved a mean AUC of 0.9525 (±0.0115) under ten-fold cross-validation, outperforming not only the individual base learners but also standalone deep learning models (CNN and Transformer). The frequency ratio in the very high susceptibility zone reached 3.97, significantly exceeding all benchmark models and confirming its superior capability in high-risk area identification. Multi-model importance analysis identified NDVI, elevation, and annual rainfall as the dominant regional landslide predisposing factors. Within the specific ranges of NDVI 0–0.686, elevation 155–462 m, and annual rainfall 1273.6–1301 mm, landslide frequency ratios consistently exceeded 1.96. The proposed framework, with its probability-level fusion and embedded regularization mechanisms, effectively mitigated overfitting despite the small sample size, providing a robust technical solution for geological hazard risk identification and prevention in the data-scarce karst terrain of the Wuling Mountains. Full article

Sustainable groundwater management is essential for water security and human health protection. Fluoride contamination is a serious concern for the sustainable drinking water supply in many parts of Pakistan, including Balochistan, where arid climate conditions and geological formations support the enrichment of fluoride. The toxic nature of fluoride contamination has resulted in negative health impacts on the local population. Conventional geostatistical techniques are usually ineffective to delineate the nonlinear relationships that affect the distribution of fluoride. This study aims to develop a machine learning-driven spatial modelling framework for classifying the spatial distribution of fluoride contamination in groundwater across the study area. The model will help to understand the spatial variability of fluoride contamination and its controlling factors, essential for effective mitigation and early warning systems. Physiochemical elements were used as predictive features in this study, utilizing a unified feature importance framework combining hydrogeochemical analysis, spatial distribution assessment, and ensemble SHAP-based interpretation to identify consistent predictors. Model performance was evaluated using a nested cross-validation framework, followed by validation on an independent geology-informed spatial holdout test set to ensure realistic generalization. Among machine learning models, the Logistic Regression (LR), Support Vector Classifier (SVC), XGBoost (XGB), Decision Tree (DT), Gaussian Naïve Bayes (GNB), and K-Nearest Neighbours (KNN) were evaluated. Support Vector Classifier (SVC) demonstrated a high predictive performance. On the independent spatial holdout dataset, SVC achieved an overall accuracy of 0.75 and an area under the receiver operating characteristic curve (AUC) of 0.821. In addition to classification, a human health risk assessment was conducted using chronic daily intake (CDI) and hazard quotient (HQ) calculations for children and adults, identifying several high-risk water supply schemes. The prediction maps successfully delineated high-risk fluoride points across specific areas, offering a tool for sustainable groundwater management. This study helps to achieve a Sustainable Development Goal (Clean Water and Sanitation, SDG#6) and promotes long-term sustainable planning in water-stressed areas by integrating spatial machine learning mapping and health risk assessment. Full article

The safety and stability of underground coal mining are largely determined by the structural features of coal seams and surrounding rocks. Geological heterogeneities such as faults, fracture zones, and lithological variations strongly influence the distribution of rock pressure and the occurrence of geodynamic hazards. This highlights the need for reliable geophysical methods capable of identifying such zones under mining conditions. Electrical prospecting represents a promising diagnostic approach, as it is highly sensitive to changes in the physical properties of rocks. Unlike conventional geological mapping, it enables the detection of hidden structures and weakened zones often invisible to direct observation. Advances in instrumentation and data processing have further expanded the applicability of electrical methods in complex environments. This study introduces a methodology of electrical prospecting observations for the diagnosis of coal seams. The analysis focuses on conductivity anomalies that reflect tectonic disturbances, fracture systems, and lithological heterogeneities. Field investigations demonstrated the sensitivity of the method to local environmental variations. Comparison with geological records confirmed the validity of the approach: the identified anomalous zones correlated well with documented tectonic features. The methodology showed a stable performance and revealed potential for integration into mine monitoring systems. It allows the identification of areas associated with elevated rock pressure and possible geodynamic activity, thereby contributing to safer underground operations. In the longer term, electrical prospecting may be applied to other coal deposits, including those with a high gas content and complex structure. The development of automated interpretation tools and machine learning algorithms could further increase processing efficiency and improve predictive reliability. Overall, the results confirm that electrical prospecting in mining environments can become an effective instrument for enhancing safety and building more accurate geological–geophysical models of coal seams. Full article