Geochemical Anomalies Research Articles

Identification of Geochemical Anomalies Using an End-to-End Transformer

Identification of Geochemical Anomalies Using an End-to-End Transformer

Interpretable Machine Learning for Geochemical Anomaly Delineation in the Yuanbo Nang District, Gansu Province, China

Machine learning (ML) has shown its effectiveness in handling multi-geoinformation. Yet, the black-box nature of ML algorithms has restricted their widespread adoption in the domain of mineral prospectivity mapping (MPM). In this paper, methods for interpreting ML model predictions are introduced to aid ML-based MPM, with the goal of extracting richer insights from the ML modeling of an exploration geochemical dataset. The partial dependence plot (PDP) and accumulated local effect (ALE) plot, along with the SHAP value analysis, were utilized to demonstrate the application of random forest (RF) modeling within both regression and classification frameworks. Initially, the random forest regression (RFR) model established the relationship between the concentrations of Au and those of elements such as As, Sb, and Hg in the study area, and from this model, the most important geochemical elements and their quantitative relationships with Au were revealed by their contributions in the modeling through PDP and ALE analyses. Secondly, the RF classification modeling established the relationships of mineralization occurrences (i.e., known mineral deposits) with geochemical elements (i.e., Au, As, Sb, Hg, Cu, Pb, Zn, and Ag), as did RFR modeling. The most important geochemical elements for indicating regional Au mineralization and the trajectories of PDP and ALE reached a consensus that As and Sb contributed the most, both in the regression and classification modeling, with regard to Au mineralization. Finally, the SHAP values illustrated the behavior of the training samples (i.e., known mineral deposits) in RF modeling, and the resulting prospectivity map was evaluated using receiver operating characteristics.

Mapping exploration targets through multifractal modelling of soil geochemical data in the Xiaohongshilazi Pb-Zn-(Ag) ore district, Jilin Province, NE China

The Xiaohongshilazi Pb-Zn-(Ag) ore district, located in the Jizhong–Yanbian Metallogenic Belt in NE China, presents challenges in identifying geochemical anomalies and prospecting minerals due to thick covers, complex geological evolution, and mining activities. To overcome these obstacles, we adopted an innovative approach that combines multifractal theory with concentration-area (C-A) modelling and local singularity analysis (LSA) to characterize the geochemical signature. Initially, factor analysis of log-transformed data was used to identify ore-forming factors, which were then modelled using C-A and LSA. Subsequently, modelling results were compared to conventional maps generated using inverse distance weighted (IDW) interpolation. Additionally, the C-A model was employed to establish thresholds for singularity indices generated by LSA for target mapping. The results revealed a close relationship between Factor 1 (F1) and mineralization. The C-A model of F1 failed to detect weak anomalies compared to the IDW-interpolated map, while LSA not only identified weak anomalies but also enhanced the detection of reliable anomalies. Three prospecting targets (PT-01, PT-02, and PT-03) were identified. Validation of PT-01 using new drillholes and existing mineralization confirms the effectiveness of targets and the accuracy of the model. Our approach provides a robust alternative for prospecting ore districts encountering similar challenges.

Metallogenic prediction based on fractal theory and machine learning in Duobaoshan Area, Heilongjiang Province

The extraction and integrated analysis of multi-source geological data are key steps in the prediction of mineralization. Current studies are focusing on the extraction and integration of the deep-level mineralization information. In the era of big data, mathematical models and computer algorithms for data mining of multi-source prospecting information have emerged as a leading research area in mineral prediction. In this study, we quantitatively analyzed the structure and remote sensing alteration information using the concentration–area (C–A) fractal model and the box-counting method for the Duobaoshan mineralization area, Heilongjiang Province, China. Results indicate that areas of high fractal dimension of remote sensing alteration correspond to abundant alteration anomalies. Fractal characterization of geological structures is consistent with the spatial distribution. Therefore, fractal characterization provides predictive factors of structure and remote sensing alteration in the development of a predictive model of mineralization. Soil geochemical data were analyzed using the component data analysis (CDA) method and the spectrum–area (S–A) fractal model. The analyses identified anomalous and background signals represented by the PC1 and PC2 principal component combinations. These combinations show a strong correlation between geochemical anomaly data and known deposits in the study area, suggesting that the S–A model effectively identifies geochemical anomalies that can be used as a predictive factor of a mineralization prediction model. The mineralization prediction model was developed using random forest (RF) and support vector machine (SVM) algorithms. The model incorporates predictive factors from multiple sources, including the ore-forming geological background, fractal-characterized geological structure, fractal-characterized remote sensing alteration, and geochemical characteristics. The models incorporated the C–A fractal model to evaluate the probability of mineral prediction. By integrating the characteristics of multi-source mineral prospecting information with the predictive results of machine-learning models, we delineated eight prospective mineralization areas. This approach validates the effectiveness of a combined method involving fractal theory and machine-learning in mineral exploration, offering new insights and theoretical guidance for further mineral prospecting in the study area

Principal components analysis and K-means clustering of till geochemical data: Mapping and targeting of prospective areas for lithium exploration in Västernorrland Region, Sweden

To achieve the demand for elements used for the green transition energy, such as lithium, it is necessary to recognize the spatial distribution of the concentrations of these elements in different earth materials such as bedrock and soil and to identify areas with anomalous concentrations of such elements (i.e., mineralization) for further exploration and hopefully exploitation. This study carried out multivariate statistical analyses on compositional (i.e., element concentration) data from till samples to recognize areas that likely contain lithium pegmatite mineralization in the Västernorrland region, central Sweden. We applied principal components analysis (PCA) and K-means clustering techniques to reveal regional-scale patterns in the till geochemical data. We demonstrate that these two methods have potential for recognition of geochemical anomalies related to the underlying bedrock geology as well as to mineralization. The results of PCA- and K-means clustering were validated using known occurrences of lithium mineralization. Two different datasets were compared; one containing all available geochemical data and the second containing only available trace elements in the dataset and it was found that anomalous clusters of samples defined by K-means clustering have anomalous multi-element signatures defined by robust PCA. This demonstrated that principal components are the continuous solutions to the discrete cluster members for the K-means clustering. The results show that both PCA and K-means clustering of till geochemical datasets at the early stages of exploration and target generation may reveal useful information that can be used to identify potential areas for more detailed mapping or exploration activities.

Источники, токсичность и биоаккумуляция редкоземельных элементов в окружающей среде: обзор

The anthropogenic part of the rare earth elements (REE) cycle is becoming increasingly noticeable due to its increasing mining, using, accumulating in wastes. The aim of the work is to summarize current scientific data of the REE effect on living organisms in different habitats, including the mechanisms and specificity of their action, as well as bioaccumulation. Both REE’s natural geochemical anomalies and anthropogenic polluted zones are known. The REE soil accumulation in industrial areas is up to 2.3 µg/kg; in urban snow the REE content varies from 0.411 µg/kg to 1.463 µg/kg. The REE negative molecular mechanism provokes oxidative stress; the latter can be expressed as stimulation of vital functions at low doses of toxicants, and as inhibition of organisms with increasing concentrations. The REE toxic concentrations depends on the chemical element nature, as well as on set of environmental factors and the exposure target, but they are often 2–3 orders of magnitude higher than those of heavy metals. In the early 21th century, this served as a basis to consider REEs environmentally safety. But many sublethal and delayed effects of REEs including endocrine disorders and negative effects on the breeding potential of populations have now been shown. The complexity of REEs study is due to additive, antagonistic, or synergistic effects of their mixtures and combinations with other elements. Thus, a comprehensive study of rare earth elements remains an urgent task with preventive environmental importance. The vulnerable species identification, REEs delayed effects and the REEs co-action with other substances are the most promising scientific issues.

A New Discovery of Cu Mineralization in the North Qaidam, Tibet via Log-Ratio, Robust Factor Analysis, and Spectrum–Area Modeling

The Qinghai–Tibet Plateau, abundant in mineral resources, is a treasure trove for geological explorers. However, exploration has been hindered by the presence of dense vegetation, weathering layers, and desert cover, particularly in the North Qaidam region. As a result, there is an urgent need to develop efficient geochemical composition methods. In a study of stream sediment geochemical data from the Lüliangshan area of the North Qaidam, the log-ratio transformation was used for data processing, Robust Factor Analysis (RFA) was used for model construction, and the spectrum–area (S-A) model was used for anomaly separation. The outcomes identified two distinct groups of element combinations associated with mineralization. The first group consisted of Au + Ag + Pb + Sb + Hg linked to tectonic-altered rock-type Au (antimony) deposits, while the second group consisted of Cu + Zn + Co and was closely associated with Cu-Ni sulfide deposits. The S-A fractal filtering technique amplified weak anomalies and minimized the area of anomalies against strong backgrounds. The study successfully detected substantial Cu mineralization in the source areas of geochemical anomalies in the Lüliangshan region. Consequently, the log-ratio–RFA–S-A fractal model has been proven to be an effective combination of methods for identifying and extracting geochemical anomalies from stream sediment samples and for mineral exploration in covered areas.

Identification of geochemical anomalies in multibackground areas using the combined k-means clustering and residual contrast value method: A case study in a district in Hunan, China

Due to the complex characteristics of geological structures, identifying geochemical anomalies in valuable deposits using regional geochemical datasets of stream sediments is challenging. In this study, an effective combined method was proposed to solve the problem of anomaly identification in multibackground areas. First, samples were classified into different clusters through the k-means clustering method using major elements/minerals (such as SiO2 and Na2O) that can reflect the lithology and were chosen as classification indicators. Considering the double restriction of the contour coefficient and lithological background, each sample within the same cluster was considered to have the same background. Then, the residual value between each sample and the mean data of adjacent samples within the same cluster was calculated, and the original data of each sample were replaced with the ratio (a new parameter defined as the residual contrast value) of the residual value and the anomaly threshold obtained for the corresponding cluster. Finally, geochemical maps and anomaly maps were generated using the residual contrast values. A practical example involving a regional geochemical dataset of stream sediments in Hunan, China, was examined in detail to clarify the procedure. Moreover, a comparative analysis through success rate curves of the percentage of deposits correctly determined was performed between the traditional method, singularity method and new combined method. The results showed that the anomalies identified by the proposed method were closely associated with known deposits, and the residual contrast value, which considers the effects of the lithological background, random error, and structural anomalies, could eliminate the influence of lithology and enhance weak anomalies. Moreover, the geological significance of this method is clear, and the calculation procedure is simple. Thus, this method could be applied for identifying regional geochemical anomalies in multibackground areas and could be used as a guide for new exploration targets.

Geologically-constrained GANomaly network for mineral prospectivity mapping through frequency domain training data

Generative adversarial networks (GAN) and various deep autoencoders have been frequently executed to recognize multi-element geochemical anomalies linked to different ore resources in recent decade. Efficient recognition of multi-element geochemical anomaly patterns is a significant issue in mineral exploration targeting. Traditional procedures have not sufficient capability to perform efficient pattern recognition. While, deep learning algorithms as influential subset of machine learning algorithms can present magnificent conclusions in classification and pattern recognition. Because those have robust ability in extracting high-level features of complex inputs. Although, many deep learning algorithms were used to recognize geochemical anomalies but the GANs have demonstrated specific dignity in recognizing multi-element geochemical anomaly patterns. But, these frameworks should be constrained to learn geological knowledge and yield reasonable potential maps. In this regard, a novel geologically-constrained GANomaly was trained with frequency domain training data to recognize multi-element geochemical anomalies. Application of the geologically-constrained GANomaly network with considering mineral system parameters of the Au–Cu mineralization in the Feyzabad district, NE Iran was eventuated to suitable results. The success-rate curves demonstrated that produced map of frequency domain geochemical data has traced 86.68% Au–Cu occurrences via 30% corresponded area while produced map of spatial domain geochemical data has traced 80.13% Au–Cu occurrences via 30% corresponded area.

Lithium exploration targeting through robust variable selection and deep anomaly detection: An integrated application of sparse principal component analysis and stacked autoencoders

Lithium is a strategic metal for high-technology industries that plays a vital role in realizing electromobility and effective energy storage for smartphones and electric/hybrid vehicles, in addition to being important in accumulating energy from renewable sources. Motivated by this, the development of state-of-the-art workflows is imperative to make Li exploration more efficient and guarantee a sustainable supply to the demanding markets in the future. In this paper, a computational protocol was described to address two critical challenges raised in the Li exploration: (i) selection of mineralization-related pathfinder variables and (ii) recognition of multi-element geochemical anomalies related to ore-forming processes. Robust sparse principal component analysis (SPCA) was employed to reduce active (non-zero) loading coefficients and straightforward selection of Li pathfinder variables. The selected variables were then fed into the training network of stacked autoencoders (SAE) to learn deep representations of multivariate input signals and quantify reconstruction errors linked to Li-vectoring geochemical anomalies. As a representative example, the proposed workflow, i.e., SPCA + SAE, was implemented in the R programming language and applied to a real-case experiment with stream sediment geochemical data pertaining to the Moalleman district, NE Iran. Moreover, compositional robust principal component analysis (RPCA) and Mahalanobis distance (MD) technique were adopted to constitute two comparative models, RPCA + SAE and SPCA + MD, as benchmarks to judge the competence of the SPCA + SAE model in variable selection and anomaly detection, respectively. A performance appraisal by success-rate curves and relevant area under the curves (AUCs) indicated that the SPCA + SAE model brings, by calculating the highest AUC, spatial patterns that are more promising for vectoring towards Li-mineralized grounds. Moreover, AUCSPCA+MD was measured to be greater than AUCRPCA+SAE, suggesting robust variable selection is a more important paradigm than deep anomaly detection for Li exploration targeting. Student's t–statistic method was eventually applied to the anomaly map from the SPCA + SAE model to define relevant thresholds for narrowing down prospective areas for the next round of Li exploration within the study area.

Uncertainty Quantification in Geochemical Mapping: A Review and Recommendations

AbstractGeochemical mapping is a crucial tool that can provide valuable insights for a wide range of applications, including mineral resources prospecting, environmental impact assessment, geological process understanding, and climate change research. Despite its significance, geochemical mapping requires spatial modeling based on sparse, heterogeneous, and potentially inaccurate data sets. Moreover, the underlying geological processes are often imperfectly understood. Therefore, uncertainty quantification (UQ) is vital in geochemical mapping to ensure accurate and reliable results, ultimately facilitating well‐informed decision‐making. In this contribution, we distinguish two primary types of uncertainties: systemic and stochastic. We identify the key sources of uncertainties in geochemical mapping and review the techniques that have been employed or hold potential for uncertainty quantification, communication, visualization, and sensitivity analysis. This contribution also illustrates the general procedure of UQ in geochemical mapping by a case study of mapping geochemical anomalies associated with gold mineralization in northwestern Sichuan Province, China. We also explore potential strategies for mitigating the critical uncertainties, such as gathering more geochemical data, developing more effective models, enhancing our understanding of the geochemical dispersion process, or leveraging other thematic information or knowledge. Future research should prioritize addressing underexplored uncertainties and implementing more practical applications to validate the UQ procedure in geochemical mapping.

Geochemical Anomalies of the Heavy Metals in the Industrial and Urban Agglomeration Soils

Geochemical Anomalies of the Heavy Metals in the Industrial and Urban Agglomeration Soils

Denoising of Geochemical Data using Deep Learning–Implications for Regional Surveys

Regional geochemical surveys generate large amounts of data that can be used for a number of purposes such as to guide mineral exploration. Modern surveys are typically designed to permit quantification of data uncertainty through data quality metrics by using quality assurance and quality control (QA/QC) methods. However, these metrics, such as data accuracy and precision, are obtained through the data generation phase. Consequently, it is unclear how residual uncertainty in geochemical data can be minimized (denoised). This is a limitation to propagating uncertainty through downstream activities, particularly through complex models, which can result from the usage of artificial intelligence-based methods. This study aims to develop a deep learning-based method to examine and quantify uncertainty contained in geochemical survey data. Specifically, we demonstrate that: (1) autoencoders can reduce or modulate geochemical data uncertainty; (2) a reduction in uncertainty is observable in the spatial domain as a decrease of the nugget; and (3) a clear data reconstruction regime of the autoencoder can be identified that is strongly associated with data denoising, as opposed to the removal of useful events in data, such as meaningful geochemical anomalies. Our method to post-hoc denoising of geochemical data using deep learning is simple, clear and consistent, with the amount of denoising guided by highly interpretable metrics and existing frameworks of scientific data quality. Consequently, variably denoised data, as well as the original data, could be fed into a single downstream workflow (e.g., mapping, general data analysis or mineral prospectivity mapping), and the differences in the outcome can be subsequently quantified to propagate data uncertainty.

Assessing the deposition of heavy metals in edaphotopes and synantrophy vegetation under the conditions of technological pollution of the city

The object of this study is a regional center with a developed industry and a significant traffic load. The study provides an assessment of the impact of the urbanization process on the conditions of development of urban edaphotopes and their role in the functioning of urban ecosystems. It was determined that the geochemistry of the soils of urban ecosystems is significantly different from natural landscapes, which is due to the symbiosis of natural and anthropogenic factors. The content of mobile forms of heavy metals in the soil of 14 localities of different functional zones within the city was investigated. A comparative assessment of the spatial heterogeneity of the content of heavy metals in the vegetative organs (root, shoot) of the diagnostic species Polygonum aviculare L. was performed. Based on the sources of emission of heavy metals and the formed geochemical anomalies, a direct dependence was established on their accumulation by the vegetative organs of Polygonum aviculare L. According to the calculated biological absorption coefficient (BAC), high bioavailability for the accumulation of man-made toxicants Cu, Zn, Pb, Cd by the phytomass of Polygonum aviculare L. was proven. It was determined that the content of heavy metals in different parts of the test object is due to their physiological ability to accumulate these toxicants in the root and above ground mass. Active translocation of toxicants from the soil to the roots is characteristic of localities with intense influence of man-made factors, for which the value of the bioavailability coefficient varies within 0.6>BAC<0.85. Correlation coefficients between the content of heavy metals in the atmosphere, soil, and vegetative organs of the plant were determined. The research allows us to evaluate the prospects for using Polygonum aviculare L. as a cumulative indicator of metal pollution in urban technogenic ecosystems and their high phytoremediation value under conditions of environmental pollution with heavy metals

Regional Geochemical Characteristics of Lithium in the Mufushan Area, South China

With the explosive growth in demand for lithium (Li) resources, the Mufushan area has been a hotspot for Li deposit exploration in China in recent years. Geochemical maps and geochemical anomaly maps are basic maps in the geochemical exploration of mineral resources. A fixed-value method to contour a Li geochemical map is presented here, in which Li concentrations are divided into 19 levels on 18 fixed values, ranging from 5 μg/g (corresponding to the detection limit) to 1858 μg/g (corresponding to the cut-off grade of Li deposit in hard-rock type) and illustrated in six color tones corresponding to Li areas of low background, high background, low anomaly, high anomaly, mineralization in clay-type, and mineralization in hard-rock type. The geochemical map of Li in the Mufushan area using the new fixed-value method indicates that the study area belongs to the high background area, and the known Li deposits are located in the high anomaly areas. In addition, the geochemical anomaly map of the Mufushan area is drawn using the method of seven levels of classification, and indicates that the known Li deposits are all in the anomaly areas, with anomaly levels not lower than the second level. Furthermore, four other areas are recognized for Li resource potential based on the geochemical map and geochemical anomaly map in the Mufushan area.

High-performance imbalanced learning ensembles of decision trees for detecting mineralization anomalies from geochemical exploration data

How to effectively detect geochemical anomalies associated with mineralization is a challenging task due to the extreme class-imbalance of geochemical exploration data. To address this challenge, various machine learning techniques have been employed to detect geochemical anomalies associated with mineralization. However, almost all of these machine learning techniques have their limitations when it comes to modeling class-imbalanced geochemical exploration data. To establish efficient robust high-performance models for detecting geochemical anomalies associated mineralization, a case study was carried out in the Helong area, Jilin Province, China. Decision tree (C4.5) classifiers were used as the base or weak classifiers, four imbalanced learning ensemble models, including self-paced ensemble model, under-bagging ensemble model, synthetic minority oversampling technique (SMOTE)-boost ensemble model and random under sampling (RUS)-boost ensemble model were established and compared in the detection of polymetallic mineralization anomalies from the 1:50,000 stream sediment survey data. The output of the base classifier is a vector consisting of the probability that the sample belongs to a mineralization anomaly and the probability that the sample belongs to the background. The performance of each ensemble model was evaluated using the receiver operating characteristic (ROC) curve and the area under the ROC curve (AUC). The ROC curves of the four models are close to the upper left corner of the ROC space. The AUC values of the four models are not lower than 0.9589. The polymetallic mineralization anomalies detected by the four models account for less than 7 % of the entire study area, but contain not less than 93 % of the polymetallic deposits found in the study area. In addition, the polymetallic mineralization anomalies detected by the four models spatially coincide with the regional controlling factors of polymetallic mineralization in the study area. To summarize, the four models have very high performance in detecting polymetallic mineralization anomalies, and the polymetallic mineralization anomaly detection results are consistent with the regional geological and metallogenic characteristics in the study area. Therefore, the imbalanced learning ensemble techniques are powerful tools for the establishment of high-performance ensemble classification models for detecting mineralization anomalies from geochemical exploration data.

A comprehensive evaluation of OPTICS, GMM and K-means clustering methodologies for geochemical anomaly detection connected with sample catchment basins

The process of data-driven clustering to uncover geochemical anomalies linked to sample catchment basins (SCBs) includes a comprehensive framework to discern areas exhibiting unique geochemical attributes within a specified study area. The Ordering Points to Identify the Clustering Structure (OPTICS) method can serve as a robust methodology for detecting geochemical anomalies in SCBs. This is attributed to its capacity to effectively manage varying cluster densities, adaptively identify cluster numbers, exhibit resilience to noise, and display minimum sensitivity to parameters. A comparison was conducted in this research between the outcomes of the OPTICS clustering algorithm and two traditional clustering techniques, namely the Gaussian Mixture Model (GMM) and K-means clustering. In the following, the Expectation-Maximization (EM) technique is employed to train the GMM for clustering. Moreover, the Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) as two validate statistical metrics implemented to ascertain the optimal number of components (clusters) belong to the GMM. It should be noted that the effectiveness of the clustering algorithms was further assessed using the Calinski-Harabasz (CH) index and the success-rate curves. OPTICS, a density-based clustering approach, was confirmed to be more effective than K-means and GMM for identifying MVT PbZn anomalies in Varcheh district, western Iran. Furthermore, the specified anomalies show a geo-spatial correspondence with the geological facts, and it has been observed that strong anomalies are more discoverable in close proximity to MVT PbZn occurrences. This work suggests a novel anomaly detection approach based on OPTICS, which exhibits superior performance and data-modeling efficiency. The main emphasis is on effectively distinguishing geochemical anomalies from sample data originating from populations with uncertain distributions.

Recognition of REEs anomalies using an image Fusion fractal-wavelet model in Tarom metallogenic zone, NW Iran

This study aims to detect REE geochemical anomalies in relationship to Iron-apatite ores utilizing an image Fusion based on Deep Learning (FDL). The geochemical data was modeled for elements related to Iron-apatite mineralization using multi b Spline B. The results were fusioned in applying the Deep learning method based on pre-trained networks. Wavelet-Number (WN) fractal model classified the best results based on the combination of a two-dimensional Discrete Wavelet Transformation (DWT) signal analysis and a Concentration-Area (C-A) fractal modeling. Sym8 carried the DWT as a selected wavelet pattern for REE based on Stream sediment samples collected from the Tarom region (NW Iran). In addition, the DWT was decomposed by wavelet coefficients at five levels. Furthermore, the DWT data were classified using a fractal-wavelet model to delineate REE anomalies from background levels in this region. Overlayed with the catchment basins model and weighted using the upstream and downstream parts. As a result, the prominent REE source anomalies are located in the southern parts of the study area. The results obtained by the proposed fractal-wavelet modeling are in connection with field check anomaly samples and the rock samples collected from the Iron-Apatite ore deposits.

Extraction of weak geochemical anomalies based on multiple-point statistics and local singularity analysis

Extraction of weak geochemical anomalies based on multiple-point statistics and local singularity analysis

Incorporating Geological Knowledge into Deep Learning to Enhance Geochemical Anomaly Identification Related to Mineralization and Interpretability

Incorporating Geological Knowledge into Deep Learning to Enhance Geochemical Anomaly Identification Related to Mineralization and Interpretability