Multivariate Geochemical Anomalies Research Articles

Local phase-constrained convolutional autoencoder network for identifying multivariate geochemical anomalies

Autoencoder is a powerful tool for identifying multivariate geochemical anomalies. However, existing autoencoder-based geochemical anomaly detection methods primarily rely on a global reconstruction error (e.g., mean square error) to define the lower limit of geochemical anomalies, neglecting the common, local structure information of geochemical data. This limitation inevitably results in the decreased accuracy of geochemical anomaly identification. This study proposed a local Phase-Constrained Convolutional AutoEncoder network (PC-CAE) for the identification of multivariate geochemical anomalies. Initially, we employed a local Fourier transform to extract phase information from both the original and the reconstructed data. Subsequently, a convolutional autoencoder network was utilized to learn the latent representation of geochemical background, using the local phase difference between the original and reconstructed data to preserve the local data structure related to geology setting. Additionally, an adaptive weighting strategy was employed to mitigate the overfitting issue. The training samples with high reconstruction errors were finally identified as anomalies. We tested the validity of PC-CAE using the stream sediment geochemical dataset collected in the Jiaodong gold province, Eastern China. The results demonstrated that PC-CAE outperforms existing convolutional autoencoder network and spectrum–area multifractal model in identifying multivariate geochemical anomalies associated with Au mineralization.

An interpretable attention branch convolutional neural network for identifying geochemical anomalies related to mineralization

Geochemical anomalies play a crucial role in geochemical prospecting as they directly indicate the existence of mineralization. Deep learning algorithms (DLAs) have received increasing attention in the domain of multivariate geochemical anomaly recognition due to their extraordinary ability to extract complex and nonlinear geochemical patterns. However, the black-box nature inherent in DLAs typically prevents one from understanding the potential operational mechanisms behind the recognition procedure, resulting in lack of confidence in the identification results. In this study, visualization techniques and attention mechanisms were integrated into a convolutional neural network (CNN) as an attention branch in order to construct an interpretable attention branch convolutional neural network (ABCNN) model for geochemical anomaly identification. Specifically, the class activation mapping was applied to visualize the spatial features extracted by the model and to identify important regions during model inference. The attention mechanism was further incorporated into a CNN to generate attention maps for enhancing spatial features associated with mineralization and interpreting the recognition results based on attention weights. A case study for identifying multivariate geochemical anomalies linked to Au polymetallic mineralization in the western Henan Province of China was presented to illustrate and validate the feasibility of the ABCNN model. The geochemical anomalies delineated by the ABCNN model coincide well with known gold deposits and ore-controlling geological features. The comparative studies between the ABCNN and a traditional CNN further manifested that the incorporation of an attention mechanism can both effectively improve the model interpretability and performance.

Recognizing geochemical patterns related to mineralization using a self-organizing map

The recognition of geochemical patterns, including the spatial association of geochemical patterns, geochemical element associations, and geochemical anomalies related to mineralization, requires different methods to meet the corresponding requirements. In this study, a self-organizing map (SOM), an unsupervised learning technique, was employed to realize the whole processes of geochemical pattern recognition in southeastern Hubei Province, China. First, the clustering ability of SOM was adopted to reveal the spatial association of geochemical patterns; then, geochemical elemental associations were adopted according to the association between variables and clusters derived from the correlation analysis between the unified distance matrix (U-matrix) and SOM maps, and finally the quantification error (QE) of the SOM was adopted as an anomalous index to detect multivariate geochemical anomalies related to mineralization. The obtained results show that two of the clusters are spatially closely related to ore-forming geological bodies, that is Precambrian strata and Yanshanian intrusive rocks. The associations of Au–As–Ba–Cd–Sb–V and Au–Ag–Pb–Zn–Bi–Cu–Mo–Na2O–P–Sr–W are responsible for the characterization of the two clusters, and their combination was further used for multivariate geochemical anomaly detection. The extracted multivariate geochemical anomalies are closely spatially correlated with known gold polymetallic deposits. Both the receiver operating characteristic (ROC) and success-rate curves suggest a satisfactory anomaly detection results, which can provide guidance for further mineral exploration. The results of this study also suggest that SOM is an effective and interpretable tool for a better recognition of geochemical patterns related to mineralization.

Recognizing Multivariate Geochemical Anomalies Related to Mineralization by Using Deep Unsupervised Graph Learning

Recognizing Multivariate Geochemical Anomalies Related to Mineralization by Using Deep Unsupervised Graph Learning

Identifying multivariate geochemical anomalies via tensor dictionary learning over spatial-elemental dimensionalities

Geochemical data is a typical geospatial-data with high-dimensional elemental properties. Existing methods for recognizing multivariate geochemical anomalies are limited in fully profiting from the inherent spatial-elemental structures of the geochemical data. This paper presents a novel method for the identification of multivariate geochemical anomalies, which leverages tensor dictionary learning over spatial-elemental dimensionalities to learn the joint representation of the spatial-elemental structures of geochemical data. The learned representations in spatial and elemental dictionaries are capable of capturing both the non-local features over space and the high-correlated distributed features across elements. The sparse representations over the spatial and elemental dimensions are exploited to reconstruct the geochemical background values, which permits us to identify multivariate geochemical anomalies considering the spatial-elemental structure of geochemical data. The proposed method is applied to recognize geochemical anomalies related to Au mineralization in the northwest Jiaodong Peninsula, Eastern China. By comparing with the anomalies recognized by deep autoencoder and local singularity analysis, we conclude that the tensor dictionary learning method is more effective to identify the mineralization-associated anomalies attribute to its ability to fuse spatial-elemental information of the geochemical data.

A geologically-constrained deep learning algorithm for recognizing geochemical anomalies

The effective identification of geochemical anomalies is essential in mineral exploration. Recently, data-driven deep learning algorithms have gained popularity for recognizing the geochemical patterns linked to mineralization. While purely data-driven deep learning algorithms can exploit geochemical patterns well, but the predicted and extracted results may be inconsistent with the geologic knowledge. In this study, a geologically-constrained deep learning algorithm was proposed to extract multivariate geochemical anomalies associated with W polymetallic mineralization in the south Jiangxi Province, China. The construction of the proposed algorithm involved two steps: (1) quantifying the spatial distribution of the known mineral deposits via fractal analysis, and (2) using prior knowledge obtained by the fractal analysis as a geological constraint to restrain an adversarial autoencoder network for delineating geochemical anomalies associated with mineralization. We conducted a comparative study of geologically-constrained and purely data-driven deep learning algorithms. We found that the former obtained more reasonable and interpretable geochemical anomalies linked to W mineralization. The results obtained by a geologically-constrained deep learning algorithm were more consistent with the regional metallogenic law. Therefore, this geological constraint can improve the generalization ability of the deep learning algorithm and enhance the interpretation of the obtained results in geosciences.

Dictionary learning for multivariate geochemical anomaly detection for mineral exploration targeting

Dictionary learning is usually used to train an overcomplete dictionary composed of basis vectors (i.e., atoms) to best sparsely represent the training dataset. The sparse representation of a data point is a sparse linear combination of the atoms derived from the well-trained overcomplete dictionary. The sparse representations of all the training data points constitute a supporting set of the population distribution of the training dataset. In this paper, geochemical exploration data was used as the training data of the five dictionary learning algorithms to train overcomplete dictionaries. The sparse representations of all the geochemical data points were used to describe the (complex) geochemical background, and the Euclidean distance between a data point and its sparse representation was used to express the anomality of the data point in multivariate geochemical anomaly detection. For demonstration purposes, the Chengde district in Hebei Province (China) was used as the case study area, and five dictionary learning models were established for multivariate geochemical anomaly detection for gold mineral exploration targeting. The performances of the five dictionary learning models were compared with that of the k-nearest neighbor (KNN) model, combined KNN model, and Gaussian mixture model (GMM) in gold mineral exploration targeting. The results show that (a) the five dictionary learning models are superior to the KNN model, the combined KNN model, and the GMM model either in terms of receiver operating characteristic curve (ROC) or in terms of area under the curve (AUC), and (b) the gold prospective areas optimally delineated in the study area accounts for a small proportion of the area, but contains most of the known gold deposits, and have spatial correlation with the favorable ore-forming factors such as the outer contact zone of multistage magmatic intrusion and the NE-trending fault zone. Therefore, the dictionary learning algorithms are feasible techniques of multivariate geochemical anomaly detection for mineral exploration targeting. It is worth to further test the usefulness of the dictionary learning algorithms in different areas with complex geochemical backgrounds.

Detection of geochemical anomalies related to mineralization using the GANomaly network

In this study, a GANomaly network was used to detect geochemical anomalies related to mineralization in the southern part of Jiangxi Province and its adjacent areas in China. The training data used in this study belong to a typical rare-sample category of imbalanced data samples; thus, during the training phase, only non-mineralized dataset randomly selected from the study area was used for training in order to avoid the overfitting problem caused by an imbalance between positive and negative training samples. The established GANomaly network structure can effectively extract anomalous geochemical information from the exploration geochemical data. The geochemical anomalies identified by GANomaly and known tungsten polymetallic deposits show a close spatial correlation. Further, the anomalous high-value areas are located in or around the Yanshanian intrusive rock. The performance of GANomaly for the identification of multivariate geochemical anomalies was compared to that of the deep autoencoder. The comparative results indicated that the GANomaly network can learn the internal connections and characteristics between multivariate geochemical data and can effectively avoid the influence of noise in geochemical data. Therefore, the abnormal areas identified by GANomaly are determined to be significant for mineral exploration.

Recognition of multivariate geochemical anomalies associated with mineralization using an improved generative adversarial network

Deep learning (DL) algorithms have a strong ability to recognize high-level features in geochemical exploration data and have been widely employed for the recognition of multivariate geochemical anomalies linked to mineralization. In this study, the adversarially learned anomaly detection (ALAD) algorithm, an improved generative adversarial network (GAN), was employed to detect multivariate geochemical anomalies related to mineralization. Compared with other unsupervised deep learning algorithms, ALAD significantly improves anomaly detection performance by combining the advantages of deep variational autoencoder and generative adversarial network. Various experiments were performed to construct a well-designed network structure to process high-dimensional geochemical data to identify geochemical anomalies linked to tungsten (W) polymetallic mineralization in the south of Jiangxi Province of China. The extracted geochemical anomalies have a high spatial distribution correction with the locations of the discovered W polymetallic mineralization. Both the area under the receiver operating characteristic curve and the prediction-area plot indicate a good performance of the ALAD model. Furthermore, the extracted geochemical anomalies are spatially correlated with granites which control the spatial distribution of W polymetallic mineralization. These observations indicate that, as an unsupervised deep learning algorithm, ALAD is useful for detecting geochemical anomalies associated with mineralization.

Detection of the multivariate geochemical anomalies associated with mineralization using a deep convolutional neural network and a pixel-pair feature method

Machine learning (ML) algorithms are widely applied in various fields owing to their strong ability to abstract high-level features from a large number of training samples. However, few supervised ML algorithms have been applied in geochemical prospecting and mineral exploration because mineralization is a rare geological event that leads to an insufficient number of training samples. Generating a large number of training samples is crucial for the application of supervised ML in geochemical prospecting and mineral exploration. In this study, a novel anomaly detection framework combined with a pixel-pair feature (PPF) method and a deep convolutional neural network (CNN) was employed to identify the multivariate geochemical anomalies associated with mineralization. First, the PPF method was employed to generate sufficient training samples by recombining the pixel pairs of the labeled samples. Then, a multilayer supervised CNN framework, which consists of 13 convolutional layers, an average pooling layer, and a fully connected layer, was trained with these pixel pairs for geochemical anomaly recognition. The testing procedure was based on the fact that neighboring pixels belong to the same class with a high probability. The dual-window detector was applied to detect multivariate geochemical anomalies related to Fe polymetallic mineralization in the southwest Fujian Province of China. The identified geochemical anomalies exhibited a close spatial correlation with the known mineral deposits, which validates the potential of the proposed method. Therefore, the method developed in this study can enhance the application of supervised ML in geochemical prospecting and mineral exploration.

Detection of Multivariate Geochemical Anomalies Using the Bat-Optimized Isolation Forest and Bat-Optimized Elliptic Envelope Models

Isolation forest and elliptic envelope are used to detect geochemical anomalies, and the bat algorithm was adopted to optimize the parameters of the two models. The two bat-optimized models and their default-parameter counterparts were used to detect multivariate geochemical anomalies from the stream sediment survey data of 1:50 000 scale collected from the Helong district, Jilin Province, China. Based on the data modeling results, the receiver operating characteristic (ROC) curve analysis was performed to evaluate the performance of the two bat-optimized models and their default-parameter counterparts. The results show that the bat algorithm can improve the performance of the two models by optimizing their parameters in geochemical anomaly detection. The optimal threshold determined by the Youden index was used to identify geochemical anomalies from the geochemical data points. Compared with the anomalies detected by the elliptic envelope models, the anomalies detected by the isolation forest models have higher spatial relationship with the mineral occurrences discovered in the study area. According to the results of this study and previous work, it can be inferred that the background population of the study area is complex, which is not suitable for the establishment of elliptic envelope model.

Robust Feature Extraction for Geochemical Anomaly Recognition Using a Stacked Convolutional Denoising Autoencoder

Deep neural networks perform very well in learning high-level representations in support of multivariate geochemical anomaly recognition. Geochemical exploration data typically contain a proportion of large variations and missing values, which motivated us to construct a network architecture optimized to deal with these data. Our approach adopted a stacked convolutional denoising autoencoder (SCDAE) to extract robust features and decreased the level of sensitivity to partially corrupted data, that is, input data that are partially missing. SCDAE parameters, which include the network depth, number of convolution layers, number of convolution kernels, and convolution kernel size, were optimized using trial-and-error experiments. The optimal SCDAE architecture was then used to recognize multivariate geochemical anomalies related to mineralization in a case study in southwestern Fujian Province, based on the differences in the reconstruction errors between sample populations. The spatial distribution of high reconstruction errors in the anomaly map was closely related to most known Fe deposits, indicating the effectiveness of the SCDAE at recognizing geochemical anomalies related to Fe mineralization. A comparative study between the SCDAE and a stacked convolutional autoencoder (SCAE) with different corruption levels showed that the SCDAE exhibited reduced sensitivity to stochastic disturbances with different corruption proportions, and had an enhanced ability to recognize geochemical anomalies varying in a reasonable range. The robustness of the SCDAE makes it applicable to a wide variety of geochemical exploration scenarios, particularly in areas with incomplete or missing data.

Detection of multivariate geochemical anomalies associated with gold deposits by using distance anomaly factors

The outliers of the statistical population are usually far from most samples in the observation space. Therefore, the total distance from a sample to all remaining samples in the population can be used to quantitatively represent the anomaly level of the sample. The greater the total distance between the sample and all the remaining samples, the more likely the sample is to be an outlier. Accordingly, the total distance of each sample in the population can be used to define a distance anomaly factor for each sample for outlier detection. The spatial distance between each pair of samples in the population can be measured by different distance measures, such as the Mahalanobis distance, Manhattan distance, Euclidean distance, and kernel Euclidean distance. According to different distances, different distance anomaly factors can be defined for each sample in outlier detection. These distance anomaly factors are potentially useful in geoscientific data procession. For demonstration purposes, the distance anomaly factors were used to detect multivariate geochemical anomalies associated with gold deposits from the stream sediment survey data in the Jinchanggouliang district, Inner Mongolia, China. Receiver operating characteristic curve and area under the curve were used to evaluate the performance of distance anomaly factors for geochemical anomaly detection. The results show that the distance anomaly factors perform better than continuous restricted Boltzmann machine and one-class support vector machine in the detection of multivariate geochemical anomalies associated with gold deposits. The Youden index was used to determine the optimal threshold to separate geochemical anomalies from geochemical background. The geochemical anomalies detected by the distance anomaly factors occupy 6.2–14.4% of the study area while contain 70–91% of the known gold deposits. The geochemical anomalies detected by the continuous restricted Boltzmann machine occupy respectively 3.1% of the study area while contain 52% of the known gold deposits. The geochemical anomalies detected by the one-class support vector machine occupy respectively 8.5% of the study area while contain 70% of the known gold deposits. Therefore, the distance anomaly factors are potentially useful techniques for geochemical anomaly detection.

Using geostatistics and maximum entropy model to identify geochemical anomalies: A case study in Mila Mountain region, southern Tibet

Separating geochemical anomalies from background values is crucial for the processing of geochemical data. In the present study, a workflow for identifying geochemical anomalies was constructed by using the direct sampling algorithm of multi-point geostatistics, the maximum entropy model, and local singularity analysis. The smoothing effect and the uncertainty of the unsampled point value in the traditional interpolation method were taken into consideration in this workflow. Based on the statistic of singular exponential distribution of each element with equal probability, the geochemical anomaly probability distribution of each element was obtained (Ag、Cd、Cu、Pb、Zn). Based on the five anomaly probability distributions, the maximum entropy model was used to establish a comprehensive perspective of geochemical anomaly uncertainty evaluation. The validity of the method was verified by analyzing geochemical data of stream sediment samples from the Mila Mountain region in Tibet. The results showed that the prospectivity map of copper deposits generated by the maximum entropy model can effectively link the probability of multivariate geochemical anomalies with the known positions of copper deposits and greatly increase the precision of the potential exploration areas for copper deposits.

Convolutional neural network and transfer learning based mineral prospectivity modeling for geochemical exploration of Au mineralization within the Guandian–Zhangbaling area, Anhui Province, China

The Zhangbaling–Guandian area is located in the eastern part of Anhui Province, China, and contains several small Au-Cu deposits and occurrences that highlight the prospectivity of this area for future mineral exploration. Recent research has determined that machine learning can identify potentially mineralization-related geochemical anomalies that represent targets for mineral exploration. However, the majority of this previous research has focused on identifying geochemical anomalies based on individual sample points but has not incorporated associated data such as the spatial characteristics of the shape, overlap, and zonation within multivariate geochemical anomalies and haloes. Here, we present a convolutional neural network algorithm based approach to identify areas prospective for Au exploration based on the multielement geochemical maps. This approach considers various spatial characteristics and employs a transfer learning method to reduce the influence of the limited number of known deposits and occurrences in this area, accelerating convergence rates and improving the accuracy of the model. The training results indicate that the accuracy of each training model is >99 and cross-entropy loss values are < 0.1. The results for the entirety of the study area indicate that about 88% of the known mineralization and mineralized occurrences are located in the prospective areas identified during this study. These results indicate that combining geochemical data with an approach employing convolutional neural network algorithms and transfer learning methods can effectively outline the Au mineralization prospectivity of relatively unexplored regions. This indicates that this type of approach could be a useful addition for future mineral exploration using geochemical data. In addition, the use of convolutional neural network approaches yields more accurate identification of geochemical anomalies and can include more geochemical variables, meaning that more geochemical data can be used in convolutional neural network-based approaches to target identification and mineral prospectivity modeling than is used in conventional geochemical anomaly identification.

Recognizing multivariate geochemical anomalies for mineral exploration by combining deep learning and one-class support vector machine

The recognition of multivariate geochemical anomalies is important for mineral exploration. Big data analytics, which involves the whole data and variables, is an alternative manner to delineate multivariate geochemical anomalies in support of machine learning algorithms due to their strong ability to capture the complex intrinsic and diverse links between geochemical characteristics and mineralization. However, this method faces the issue of data redundancy and calculation complexity, and high-dimensional problems raise great challenges for anomaly detection. This is the curse of dimensionality problem, which hinders the development of a variety of techniques for anomaly detection. In this study, a hybrid model that combines unsupervised deep belief networks (DBNs) and one-class support vector machine (OCSVM) is adopted to address the high-dimensional geochemical anomalies detection problem. In this model, the relevant features first extracted through the DBN are used as the input of the OCSVM. The decision function values of the hybrid method are employed to map the geochemical patterns related to iron mineralization. The comparative results on the performance of the hybrid model and the other three anomaly detection models (deep autoencoder model, OCSVM, and hybrid model with principal component analysis and OCSVM) in terms of the area under curve(AUC) values, suggest that the hybrid method of the DBN and OCSVM can efficiently recognize the geochemical anomalies related to iron mineralization. The DBN can extract the geochemical information, reduce the redundant features, and further enhance the scalability of the OCSVM for processing high-dimensional geochemical data. The extracted geochemical anomalies, which show a close spatial relationship with the Yanshanian intrusions, can provide significant guidance for the next round of mineral exploration.

Co-simulated Size Number: An Elegant Novel Algorithm for Identification of Multivariate Geochemical Anomalies

Identification of geochemical anomalies is of particular importance for tracing the footprints of anomalies. This can be implemented by advanced techniques of exploratory data analysis, such as fractal/multi-fractal approaches based on priori or posteriori distribution of geochemical elements. The latter workflow involves analysis of 2D/3D produced maps, which can be mostly obtained by geostatistical algorithms. There are two challenging issues for such an analysis. The first one corresponds to handling the cross-correlation structures among the data, and the second one relates to the compositional nature of data. To tackle these problems, this paper investigates the application of Gaussian co-simulation for modeling the cross-correlated compositional data in order to recognize the multivariate geochemical anomalies in integration with fractal analysis. In this context, an innovative algorithm, namely co-simulated size number (CoSS-N), is introduced for this purpose. The compositional nature of data is addressed by additive log-ratio transformation of original data while the Gaussian co-simulation handles the reproduction of cross-correlation among the components. The co-simulated outputs are then taken into account for capturing different geochemical populations, showing different levels of backgrounds and anomalies. The algorithm is illustrated via a real case study located in Philippine wherever seven geochemical components are required to be considered. The accuracy of results is examined by statistical validation techniques, indicating the capability of the CoSS-N algorithm for multivariate identification of geochemical anomalies.

Identification of multivariate geochemical anomalies using spatial autocorrelation analysis and robust statistics

Multivariate geochemical anomaly identification is one of the most important tasks in exploration geochemical data analysis. This paper proposes a new approach to identify multivariate geochemical anomalies which accounts for the degree of spatial autocorrelation among observations. This method is a combination of Robust Mahalanobis Distance (RMD), spatial autocorrelation analysis and robust statistics. The Minimum Covariance Determinant (MCD) estimator-based RMDs were first used to reduce the dimension of geochemical data sets. Spatial correlogram and local Moran’s I statistics were then applied to determine the spatial variability (spatial scales) and to measure the degree of spatial autocorrelation at global and different local scales, respectively. Negative and positive anomalies were finally separated from a set of local Moran’s I values using robust statistics, the MEDIAN ± 1.5*IQR (IQR: interquartile range) rule. We illustrated the proposed method by using a data set of 1842 stream sediment samples associated with Cu-Au-Mo and Sn mineralizations in the Jiurui ore district (Jiangxi province, southeastern China). The results showed that (i) the maximum spatial variability of RMDs were 12 km, in which strong positive spatial autocorrelation was detected at the first three spatial scales ranging from 0 to 6 km; (ii) both of negative and positive multivariate geochemical anomalies were strongly correlated with 13 known Cu-Au-Mo and Cu-Mo deposits, especially at spatial scales where high degrees of positive spatial autocorrelation were measured; (iii) weak anomalies associated with a magmatic-hydrothermal related Sn and polymetallic mineralization were successfully identified in the Zengiialong and Jianfengpo Sn deposits, which were not detected in previous studies. We demonstrate the combination of spatial autocorrelation analysis and robust statistics allows for improved identification of significant multivariate geochemical anomalies of the deposit-type sought from stream sediment geochemical data.

Integration of auto-encoder network with density-based spatial clustering for geochemical anomaly detection for mineral exploration

Auto-encoder network can be used for dimensionality reduction of data and for re-construction of sample population with unknown, complex multivariate probability distribution, where small-probability samples have little contribution to the auto-encoder network, leading to high re-construction error. In this paper, the trained auto-encoder networks were used to detect geochemical anomalies. Compared with deep auto-encoder network, the density-based spatial clustering application with noise (DBSCAN) regards noise samples (e.g., geochemically anomalous samples) that differ from core samples (e.g., geochemically background samples) as anomalies. Therefore, the learned representations from the code layer in the auto-encoder network are clustered by DBSCAN to detect noise samples representing geochemical anomalies. As benchmark for evaluating the performance of auto-encoder network and DBSCAN, and in consideration of the compositional nature of geochemical data, the compositional multivariate outlier detection was also applied. We applied these methods to two forms of the geochemical data, namely (1) without any transformation and (2) with isometric log ratio transformation. The similarities of the resulting anomaly maps in terms of data forms indicate that the auto-encoder network is effective for detecting multivariate geochemical anomalies. Differences between the anomaly maps indicate, however, that the compositional nature of geochemical data affects the performance of multivariate geochemical anomaly detection. Nevertheless, the assessment, by receiver operating characteristics analysis, of the geochemical anomalies derived using the different methodologies described implies that the detected geochemical anomalies are related to Au mineralization. Finally, the Youden index, which measures the relationship between binary anomalies and known deposits, was used for optimal threshold selection to create an optimal mineral potential map from the derived continuous geochemical anomaly data. The spatial distribution of geochemical anomalies at/around faults and magmatic rocks provides insights to where further detailed exploration is warranted in the study area.

Mapping geochemical anomalies related to Fe–polymetallic mineralization using the maximum margin metric learning method

Geochemical anomaly identification is an important task in mineral exploration targeting. This task can be regarded as a binary classification problem whereby the aim is to discriminate between anomalous and not anomalous (i.e., background). We can analyze geochemical data from the aspects of frequency distributions, correlations and variances, geometrical properties of geochemical anomalies, and scale independence of geochemical patterns. In this study, we recognize geochemical anomalies based on the intrinsic relationship between geochemical elements which can be addressed by measuring their separation distance. As a machine learning method, metric learning aims at exploiting the statistical information between the geochemical features in limited training samples, and developing a more suitable distance to evaluate the similarity of samples without priori distribution assumptions. Accordingly, a metric learning method based on the maximum margin frame was applied to identify multivariate geochemical anomalies related to Fe-polymetallic mineralization in the southwestern Fujian Province of China. The geochemical exploration data were firstly translated into a dimensional reduced subspace with the help of maximum margin metric learning (MMML). The adaptive coherence estimator (ACE) detector, from the field of target detection, was then employed to identify geochemical anomalies. The anomaly results obtained by this integrated procedure using a combination of MMML and ACE were compared to those obtained by ACE without metric learning using a receiver operating characteristic (ROC) curve. The area under the curve value implied superior performance using the combination of MMML and ACE, suggesting that this hybrid method can be effectively applied to recognize geochemical anomalies linked to mineralization.