Search Results (44)

The increasing need for accurate prediction of geochemical anomalies requires methods capable of capturing complex spatial patterns that traditional approaches often fail to represent adequately. For N datasets of the form (X_i,Y_i) representing the geographic coordinates of sampling points and C_i denoting the geochemical measurement, training multilayer perceptrons (MLPs) presents a challenge. The low informativeness of the input features and their weak correlation with the target variable result in excessively simplified predictions. Analysis of a baseline model trained only on geographic coordinates showed that, while the loss function converges rapidly, the resulting values become overly “compressed” and fail to reflect the actual concentration range. To address this, a preprocessing method based on anisotropy was developed to enhance the correlation between input and output variables. This approach constructs, for each prediction point, a structured informational model that incorporates the direction and magnitude of spatial variability through sectoral and radial partitioning of the nearest sampling data. The transformed features are then used in a dual-MLP architecture, where the first network produces sectoral estimates, and the second aggregates them into the final prediction. The results show that anisotropic feature transformation significantly improves neural network prediction capabilities in geochemical analysis. Full article

This study investigates the geological, mineralogical, and geochemical features of the Alday ore occurrence (Central Kalba, East Kazakhstan) and aims to identify indicators of rare-metal mineralization, with lithium considered to be one of its principal components. In this study, the structural–stratigraphic position of the occurrence is refined; three series of albite–spodumene pegmatites are identified; the compositions of the ore-bearing schists and the granitoids of the Kunush and Kalba complexes are compared; and the role of metasomatic alteration in the concentration of Li, Ta, Nb, Be, and Sn is established. The plagiogranites and dikes of the Kunush complex are characterized by Li anomalies (up to 306 g/t), Ta (up to 64 g/t), and a fractionated REE spectrum (La/Yb up to 108). In addition, the following predictive criteria are formulated: the presence of tectonically disrupted dikes in the Kunush complex with Na₂O/K₂O > 4, the presence of albite and muscovite alteration zones, and the presence of ladder-type spodumene-bearing pegmatites controlled by northwest-trending faults. The ⁴⁰Ar/³⁹Ar muscovite age of the Alday pegmatites (~292 Ma) aligns with the age range of the Kalba granite complex. Based on the main principles of rare-metal pegmatite generation, it is determined that the Tochka pegmatites were formed during the fluid–magmatic fractionation of magma in large granitic reservoirs of the Kalba complex. The Karagoin–Saryozek zone—located between several large granite massifs of the Kalba complex, where host rocks function as a roof—may be promising for investigating rare-metal pegmatite mineralization. Full article

The Hadamengou gold deposit, located on the northern margin of the North China Craton, represents one of the region‘s most significant gold mineralization clusters. However, exploration in its deeper and peripheral sectors is constrained by ecological protection policies and the structural complexity of the ore-forming systems. Multivariate analysis combined with multi-model integration provides an effective mathematical approach for interpretating geochemical datasets and guiding mineral exploration, yet, its application in the Hadamengou region has not been systematically investigated. To address this research gap, this study developed a pilot framework in the key Buerhantu area, on the periphery of the Hadamengou metallogenic cluster, applying and adapting a multivariate-multimodel methodology for mineral prediction. The goal is to improve exploration targeting, particularly for concealed and deep-seated mineralization, while addressing the methodological challenges of mathematical modeling in complex geological conditions. Using 1:10,000-scale lithogeochemical data, we implemented a three-step workflow. First, isometric log-ratio (ILR) and centered log-ratio (CLR) transformations were compared to optimize data preprocessing, with a reference column (YD) added to overcome ILR constraints. Second, principal component analysis (PCA) identified a metallogenic element association (Sb-As-Sn-Au-Ag-Cu-Pb-Mo-W-Bi) consistent with district-scale mineralization patterns. Third, S-A multifractal modeling of factor scores (F1–F4) effectively separated noise, background, and anomalies, producing refined geochemical maps. Compared with conventional inverse distance weighting (IDW), the S-A model enhanced anomaly delineation and exploration targeting. Five anomalous zones (AP01–AP05) were identified. Drilling at AP01 confirmed the presence of deep gold mineralization, and the remaining anomalies are recommended for surface verification. This study demonstrates the utility of S-A multifractal modeling for geochemical anomaly detection and its effectiveness in defining exploration targets and improving exploration efficiency in underexplored areas of the Hadamengou district. Full article

Predicting mineral deposits accurately requires capturing the complex interactions among geological structures, geochemical anomalies, and alteration patterns. To address this challenge, this study develops a Knowledge–Data Collaboration Graph Attention Network (KDCGAT) to improve copper mineralization prediction by integrating multi-source geological data. The model combines Graph Attention Network (GAT) with multimodal geoscience data, including fracture structures, remote sensing alteration maps, and geochemical anomalies. Spatial correlations are captured through a self-attention mechanism, aligning deep learning predictions with geological and geochemical knowledge. Using the eastern Tien Shan copper belt in Xinjiang as a case study, KDCGAT achieves a copper deposit identification accuracy of 85.9%, outperforming Weight of Evidence (WoE) by 7%, Graph Convolutional Network (GCN) by 11.3%, and Convolutional Neural Network (CNN) by 19.7%. Ablation experiments show a 21.1% improvement over the baseline GAT model. Finally, five Class A and three Class B mineralization prediction zones are delineated. This study demonstrates the effectiveness of graph neural networks for copper prospectivity prediction and highlights knowledge–data collaboration as a practical tool for mineral exploration. Full article

Machine learning (ML) algorithms have promoted the development of predictive modeling of mineral prospectivity, enabling data-driven decision-making processes by integrating multi-source geological information, leading to efficient and accurate prediction of mineral exploration targets. However, it is challenging to conduct ML-based mineral prospectivity mapping (MPM) in under-explored areas where scarce data are available. In this study, the Narigongma district of the Qiangtang block in the Himalayan–Tibetan orogen was chosen as a case study. Five typical alterations related to porphyry mineralization in the study area, namely pyritization, sericitization, silicification, chloritization and propylitization, were extracted by remote sensing interpretation to enrich the data source for MPM. The extracted alteration evidences, combined with geological, geophysical and geochemical multi-source information, were employed to train the ML models. Four machine learning models, including artificial neural network (ANN), random forest (RF), support vector machine and logistic regression, were employed to map the Cu-polymetallic prospectivity in the study area. The predictive performances of the models were evaluated through confusion matrix-based indices and success-rate curves. The results show that the classification accuracy of the four models all exceed 85%, among which the ANN model achieves the highest accuracy of 96.43% and a leading Kappa value of 92.86%. In terms of predictive efficiency, the RF model outperforms the other models, which captures 75% of the mineralization sites within only 3.5% of the predicted area. A total of eight exploration targets were delineated upon a comprehensive assessment of all ML models, and these targets were further ranked based on the verification of high-resolution geochemical anomalies and evaluation of the transportation condition. The interpretability analyses emphasize the key roles of spatial proxies of porphyry intrusions and geochemical exploration in model prediction as well as significant influences everted by pyritization and chloritization, which accords well with the established knowledge about porphyry mineral systems in the study area. The findings of this study provide a robust ML-based framework for the exploration targeting in greenfield areas with good outcrops but low exploration extent, where fusion of a remote sensing technique and multi-source geo-information serve as an effective exploration strategy. Full article

Strategic lithium resources are critical to national security and have attained heightened importance in contemporary geopolitical, economic, and military contexts. Persistent geochemical anomalies of lithium were first identified in coal-bearing claystones of the Middle Jurassic Xishanyao Formation at the Liuhuanggou Coal Mine in the southern Junggar Basin, Xinjiang. In this study, a suite of analytical techniques, including X-ray fluorescence spectrometry, inductively coupled plasma mass spectrometry, X-ray diffraction, scanning electron microscopy-energy dispersive spectroscopy, time-of-flight secondary ion mass spectrometry, and sequential chemical extraction, was employed to investigate the provenance, depositional environment, and modes of lithium occurrence in the claystone. Results indicated that the claystone at the Liuhuanggou Coal Mine was dominated by moderately felsic rocks. The notable enrichment of lithium in the Liuhuanggou coal mine claystone indicates favorable metallogenic potential. Lithium was primarily hosted in the aluminosilicate-bound fraction with inorganic affinity and was structurally incorporated within clay minerals, such as kaolinite, illite, and Fe-rich chlorite (chamosite). Lithium-rich claystone was deposited under intense chemical weathering conditions in a transitional, slightly brackish environment characterized by elevated temperatures and low oxygen levels. These findings advance our understanding of sedimentary lithium mineralization mechanisms and offer direct practical guidance for lithium resource exploration and metallogenic prediction in the Xinjiang region, thereby supporting the development of efficient extraction technologies. Full article

Radon anomalies have long been explored as potential geochemical precursors to seismic activity due to their responsiveness to subsurface stress variations. However, before this study, the scientific progression of this research domain had not been systematically examined through a quantitative lens. This study presents a comprehensive bibliometric analysis of 379 articles published between 1977 and 2025 and indexed in Scopus and Web of Science. Utilizing the Bibliometrix R-package and its Biblioshiny interface, the analysis investigates temporal publication trends, leading countries, institutions, international collaboration networks, and thematic evolution. The results reveal a marked increase in research output since 2010, with China, India, and Italy emerging as the most prolific contributors. Thematic mapping indicates a shift from conventional geochemical monitoring toward the integration of artificial intelligence techniques, such as decision trees and neural networks, for anomaly detection and predictive modeling. Notwithstanding this methodological evolution, core research themes remain centered on radon concentration monitoring and the analysis of environmental parameters. Overall, the findings highlight the coexistence of traditional and emerging approaches, emphasizing the importance of standardized methodologies and interdisciplinary collaboration. This bibliometric synthesis provides strategic insights to inform future research and strengthen the role of radon monitoring in seismic early warning systems. Full article

Mining and analyzing information from multiple sources—such as geophysics and geochemistry—is a key aspect of big data-driven mineral prediction. Clustering, which groups large datasets based on distance metrics, is an essential method in multidimensional data analysis. The Two-Step Clustering (TSC) approach offers advantages by handling both categorical and continuous variables and automatically determining the optimal number of clusters. In this study, we applied the TSC method to mineral prediction in the northeastern margin of the Jiaolai Basin by: (i) converting residual gravity and magnetic anomalies into categorical variables using Ward clustering; and (ii) transforming 13 stream sediment elements into independent continuous variables through factor analysis. The results showed that clustering is sensitive to categorical variables and performs better with fewer categories. When variables share similar distribution characteristics, consistency between geophysical discretization and geochemical boundaries also influences clustering results. In this study, the (3 × 4) and (4 × 4) combinations yielded optimal clustering results. Cluster 3 was identified as a favorable zone for gold deposits due to its moderate gravity, low magnetism, and the enrichment in F1 (Ni–Cu–Zn), F2 (W–Mo–Bi), and F3 (As–Sb), indicating a multi-stage, shallow, hydrothermal mineralization process. This study demonstrates the effectiveness of combining Ward clustering for variable transformation with TSC for the integrated analysis of categorical and numerical data, confirming its value in multi-source data research and its potential for further application. Full article

Progress in the exploration of uranium deposits in the Qinling region is impacted by a number of factors, including extensive forest distribution, large-scale terrain segmentation, and hidden ore bodies. Airborne gamma-ray spectrometry measurement is a direct method for uranium exploration, with data containing rich uranium mineralization information. In addition to surface mineralization information, such measurements also contain some information on deep uranium mineralization. Based on the geological characteristics of a specific area in the Qinling region, conventional data processing methods of airborne gamma-ray spectrometry (such as total elemental content, uranium, potassium and thorium content, and elemental ratios), the overall spectral characteristics obtained were analyzed. By utilizing the geochemical differences among K, U, and Th element contents, a model of four multi-element combination parameters of airborne gamma-ray spectrometry was constructed, including ancient uranium content, uranium activation migration coefficient, uranium abundance degree coefficient, and uranium migration enrichment coefficient, together with their geological significance. The model enhances the weak anomaly information of airborne gamma-ray spectrometry and provides a detailed analysis of key areas within the study area. Lastly, based on the extraction of multi-element anomaly information from airborne gamma-ray spectrometry data and optimal selection, combined with favorable geological information for exploration, a method for rapidly delineating prospective uranium ore areas is proposed, with three uranium ore prospective areas being predicted within the study area. Full article

Unsupervised anomaly detection algorithms have gained significant attention in the field of mineral prospectivity mapping (MPM) due to their ability to reveal hidden mineralization zones by effectively modeling complex, nonlinear relationships between exploration data and mineral deposits. This study utilizes two tree-based anomaly detection algorithms, namely, isolation forest (IF) and extended isolation forest (EIF), to enhance MPM and exploration targeting. According to the conceptual model of porphyry copper deposits, several evidence layers were generated, including fault density, multi-element geochemical signatures, proximity to various alteration types (phyllic, argillic, propylitic, and iron oxide), and proximity to intrusive rocks. These layers were integrated using IF and EIF algorithms, and their results were subsequently compared with a geological map of the study area. The comparison revealed a high degree of overlap between the identified anomalous zones and geological features, such as andesitic rocks, tuffs, rhyolites, pyroclastics, and intrusions. Additionally, quantitative assessments through prediction-area plots validated the efficacy of both models in generating prospective targets. The results highlight the significant influence of hyperparameter tuning on the accuracy of prospectivity models. Furthermore, the study demonstrates that hyperparameter tuning is more intuitive and straightforward in IF, as it provides a clear and distinct tuning pattern, whereas EIF lacks such clarity, complicating the optimization process. Full article

The Precambrian crystalline basement of Madagascar, shaped by its diverse geological history of magmatic activity, sedimentation, and metamorphism, is divided into six distinct geological units. Within this intricate geological framework, five primary types of uranium deposits are present. Despite the presence of these deposits, their resource potential remains largely unquantified. To address this, a comprehensive study was conducted on Madagascar’s uranium geochemical blocks. This study processed the original data of uranium elements across the region, following the “Theoretical Model Pedigree of Geochemical Block Mineralization” proposed by Xie Xuejin. The analysis is based on the geochemical mapping data of Madagascar at a scale of 1:100,000, which was jointly completed by the China–Madagascar team and involved the delineation of geochemical blocks and the division of their internal structures using the 15 km × 15 km window data. The study used an isoline with a uranium content greater than 3.2 × 10⁻⁶ as a boundary and considered five key factors for the classification of prospective areas. These factors included uranium bulk density, anomaly intensity, block structure, prospective area, and the tracing of uranium enrichment trajectories through the pedigree chart of 5-level geochemical blocks. By integrating these factors with potential resource assessment, uranium mining economics, and conditions for uranium mining and utilization, the study successfully classified and evaluated uranium resources in Madagascar. As a result, 10 uranium prospective areas were identified, ranging from Level I to IV, with 3 being Level I areas deemed highly promising for exploration and investment. For the first time, the study predicted a resource potential of 72,600 t of uranium resources, marking a significant step towards understanding Madagascar’s uranium endowment. Full article

The geochemical maps and geochemical anomaly maps produced based on the data in the databases of the Regional Geochemistry–National Reconnaissance (RGNR) and the National Multipurpose Regional Geochemistry Survey (NMPRGS) projects have played a crucial role in China’s geochemical exploration. A geochemical survey of the Mojiang area, Yunnan Province, China, has been completed and reveals potential new regions for Ni exploration related to occurrences of serpentinite melanges. The geochemical maps and geochemical anomaly maps need to be drawn in this area. Traditional geochemical maps, heavily dependent on data quantity, are less suitable for consistent comparisons across distinct regions and elements. Here, a fixed value method is proposed to contour the Ni geochemical map on 19 levels, which is convenient for the comparison among elements. On the geochemical maps, the two known Ni deposits are located in a region with Ni surely screening risk level (on the national standard of pollution risk of heavy metals in China) and a region with Ni economic level (Ni as an associate or main economic metal on the national standard of Ni deposit in China), respectively. In addition, we have determined that the Sn and Li levels in this area are at (low or high) background levels compared to other regions. Then, the method of seven levels of classification, which is also suitable for the comparison across different areas or elements, is used to draw the geochemical anomaly maps in the Mojiang area. On the anomaly maps, the two known Ni deposits are located in the regions with Ni anomaly levels not less than four, while the anomaly areas of Sn and Li are sporadic, with anomaly levels not larger than two in this area. These consistent results with the known facts of Ni, Sn, and Li deposits in the Mojiang area not only consolidate the roles of geochemical maps and geochemical anomaly maps but also illustrate the comparison among elements in mineral exploration. Furthermore, we predicted three Ni potential regions in the Mojiang area on the geochemical survey. Full article

Morocco is rich in Mississippi Valley Type (MVT) copper deposits. Currently, geochemical surveying is being conducted in the Goulmima region in pursuit of breakthroughs in mineral exploration. This paper focuses on the delineation of prospecting targets in the Goulmima area based on the ongoing 1:100,000 geochemical survey work in Morocco. The study employs compositional data transformation to perform isometric log-ratio (ilr) transformations on raw data, followed by the Spectrum-Area (S-A) fractal processing, and then uses the Random Forest (RF) algorithm for mineral prediction. Finally, the prediction results are further delineated using the Concentration-Area (C-A) fractal model to identify high-probability areas, marking two prospecting targets. The results show: (1) the ilr transformation reduces the closure problem of the original data and improves their symmetry, thereby more effectively revealing the spatial structural features of the elements; (2) the principal component analysis (PCA) performed on the ilr-transformed data successfully identifies two main element combinations, representing high-temperature hydrothermal environments (Mo-Sn-Ti-W-U) and low-temperature mineralization environments (CaO-Pb-Zn), consistent with the regional mining history; (3) the application of the S-A multifractal model effectively distinguishes between anomalies and background distributions in the geochemical data of the study area, and combines fault buffer zones as the basis for mineral prediction; (4) the C-A fractal model further subdivides the prediction results, dividing potential mining areas into high, medium, and low probability zones, and ultimately identifies two prospecting targets. Full article

The Lintan gold deposit, located in the “gold triangle” of Qianxinan, Guizhou Province, has become a focal point for implementing the “exploring near existing deposits” strategy, aiming to identify another large-scale gold deposit within the region. This study addresses the challenges of deep-edge mineral exploration in the Lintan gold deposit by adopting a metallogenic system perspective. Using a multidisciplinary approach, it integrates geological, geophysical, and geochemical datasets to construct various three-dimensional (3D) visualization and prospectivity models. The research leverages geostatistical theories and methods, multisource digital information analysis, and advanced 3D modeling and visualization techniques to verify mineralization anomalies. These efforts expand the scope of prospectivity evaluation for the deep-edge regions of the Lintan gold deposit into 3D space. In the 3D spatial framework, this study elucidates the metallogenic geological characteristics, geophysical anomalies, and geochemical signatures within the study area. Building upon this foundation, it conducts a comprehensive analysis and evaluation of geological, geochemical, and geophysical prospecting indicators under multisource geoscience datasets. This approach transitions from known to unknown domains, effectively reducing the ambiguities and uncertainties associated with single-source data interpretations. The findings demonstrate that, under the guidance of geological prospectivity models, the effective integration and synthesis of geological, geophysical, and geochemical data can reveal the interrelationships between metallogenic geological bodies and the contributing factors of the metallogenic system. This enables the identification of anomalous information associated with metallogenic geological bodies and facilitates the spatial localization and prediction of target areas for deep-edge mineral resources. The proposed methodology provides novel insights and techniques for deep-edge mineral exploration. Comprehensive analysis indicates significant prospectivity for mineral resource exploration in the deep-edge regions of the Lintan gold deposit. Full article

Geochemical mapping of river sands in the Manufahi area of Timor-Leste revealed potential areas for future mineral exploration. River sand samples from the study area were collected and geochemically analyzed to identify anomalous concentration distributions of several valuable elements and locate potential target areas and geological formations that may host mineral deposits. The 26 major and minor elements were identified using wavelength-dispersive X-ray fluorescence. The river sands exhibited varying elemental concentrations, with Cr, Cu, Zn, and Ba showing deviations from the normal distribution patterns. Identification of geochemical anomalies is an important task in mineral exploration geochemistry. The mean+2 standard deviations (mean+2STD), median+2 median absolute deviations (median+2MAD), and Tukey’s inner fence (TIF) methods were used to determine the geochemical thresholds. This study shows that TIF and principal component analysis (PCA) methods are highly effective in calculating appropriate threshold values and identifying relevant elemental associations. These approaches have proven useful for delineating target areas for mineral deposits, resulting in reliable outcomes. Four predicted target areas with high potential for deposits and mineralization anomalies of Cr, Cu, Ni, and Ba were delineated in the study area. Full article