Geochemical Exploration Data Research Articles

A deep autoencoder network connected to geographical random forest for spatially aware geochemical anomaly detection

Machine learning (ML) and deep learning (DL) techniques have recently shown encouraging performance in recognizing metal-vectoring geochemical anomalies within complex Earth systems. However, the generalization of these techniques to detect subtle anomalies may be precluded due to overlooking non-stationary spatial structures and intra-pattern local dependencies contained in geochemical exploration data. Motivated by this, we conceptualize in this paper an innovative algorithm connecting a DL architecture to a spatial ML processor to account for local neighborhood information and spatial non-stationarities in support of spatially aware anomaly detection. A deep autoencoder network (DAN) is trained to abstract deep feature codings (DFCs) of multi-element input data. The encoded DFCs represent the typical performance of a nonlinear Earth system, i.e., multi-element signatures of geochemical background populations developed by different geo-processes. A local version of the random forest algorithm, geographical random forest (GRF), is then connected to the input and code layers of the DAN processor to establish nonlinear and spatially aware regressions between original geochemical signals (dependent variables) and DFCs (independent variables). After contributions of the latter on the former are determined, residuals of GRF regressions are quantified and interpreted as spatially aware anomaly scores related to mineralization. The proposed algorithm (i.e., DAN‒GRF) is implemented in the R language environment and examined in a case study with stream sediment geochemical data pertaining to the Takht-e-Soleyman district, Iran. The high-scored anomalies mapped by DAN‒GRF, compared to those by the stand-alone DAN technique, indicated a stronger spatial correlation with locations of known metal occurrences, which was statistically confirmed by success-rate curves, Student's t‒statistic method, and prediction-area plots. The findings suggested that the proposed algorithm has an enhanced capability to recognize subtle multi-element geochemical anomalies and extract reliable insights into metal exploration targeting.

Exploration Vectors and Indicators Extracted by Factor Analysis and Association Rule Algorithms at the Lintan Carlin-Type Gold Deposit, Youjiang Basin, China

The Youjiang Basin in China is the world’s second-largest concentrated area of Carlin-type Au deposits after Nevada, USA, boasting cumulative Au reserves nearing 1000 t. This study examined the recently unearthed Lintan Carlin-type Au deposit within the Youjiang Basin. Factor analysis and association rule algorithms were used to identify exploration vectors and indicators essential for navigating this promising geological territory. In the Lintan mining area, the geological strata encompass the Triassic Bianyang, Niluo, and Xuman formations comprised clastic rocks, followed by the deeper Permian Wujiaping Formation with massive carbonate rocks. The orebodies are restricted to the F14 inverse fault, cutting through the Xuman Formation, with an additional F7 fault between the Wujiaping and Xuman formations. A total of 125 rock samples from the F14 fault and a representative cross-section were analyzed for 15 elements (Au, Ag, As, Bi, Cd, Co, Cu, Hg, Mo, Ni, Pb, Sb, Tl, W, and Zn). The elements were divided into four groups based on cluster and factor analysis. Group 1 (Co, Cu, Zn, Ni, Tl, W, and Bi) was mainly enriched in the Xuman, Niluo, and Bianyang formations controlled by sedimentary diagenesis. Group 2 (Au, As, Hg, and Sb) was concentrated in the F14 and F7 faults, representing Au mineralization. Group 3 (Pb, Ag, and Mo) was mostly enriched near the F14 and F7 faults, displaying a peripheral halo of Au mineralization, and was probability controlled by ore-forming hydrothermal activities. Group 4 (Cd and Mo) exhibited extreme enrichment along the periphery of the F7 fault. This pattern indicates the presence of a substantial hydrothermal alteration zone surrounding the fault, likely influenced by ore-forming hydrothermal processes. Additionally, Pb, Ag, Cd, Mo, and W are considered essential indicators for ore formation besides Au, As, Sb, Hg, and Tl. Twelve effective association rules were derived using the association rule algorithm, which can aid in discriminating Au mineralization. The spatial distributions of the 15 elements indicated that the F14 fault is the main ore-bearing fracture zone, while the F7 fault serves as the ore-conducting structure, channeling ore-forming fluids into the F14 fault. Faults between the Wujiaping and Xuman formations, along with their associated reverse faults, present potential prospecting targets both within and outside the Lintan Au deposit in the Youjiang Basin. Exploration geochemical data can be fully utilized by combining factor analysis and association rule algorithms, offering key guidance for prospecting Carlin-type gold and similar deposits.

Prospecting Prediction for the Yulong Metallogenic Belt in Tibet Based on Remote Sensing Alteration Information and Structural Interpretation

The Yulong porphyry copper belt in eastern Tibet is located in the middle of Tethys–Himalayan metallogenic mega-province, which is one of the three major porphyry copper metallogenic mega-provinces. The Yulong copper belt belongs to the super porphyry copper belt and represents one of the most important copper mineralization prospecting areas in China. A significant quantity of research data shows that this study area belongs to the environment of intracontinental collision and compression, with a complex geological structure, magmatic rock development and excellent metallogenic geological background. However, because this area is located in an alpine and high-altitude area, it is difficult to carry out any traditional field geological surveys, and the existing studies of both prospecting and prediction are relatively weak. This study focused on information extraction for alteration minerals in the Yulong metallogenic belt and its surroundings based on multispectral data and hyperspectral data, establishing a spectral library of alteration minerals in this area. Based on Sentinel-1A radar data and Landsat-8 OLI color synthesis data, the linear structure of the study area was interpreted. On this basis, the information extraction results relating to alteration minerals obtained from multi-source remote sensing data, linear structure interpretation results and the geochemical exploration data of the study area were superimposed to comprehensively analyze the metallogenic geological conditions and mineralization characteristics in the area, establish remote sensing prospecting indicators there and optimize the potential areas for prospecting, providing technical support for the next step of prospecting and exploration in the area.

Extracting geological and alteration information and predicting antimony ore based on multisource remote sensing data in Huangyangling, Xinjiang

Introduction: China has the world’s largest amount of antimony resources and plays a vital role in the global antimony industry. The Huangyangling area in Xinjiang belongs to the Lazhulong-Huangyangling antimony mineralization belt; this area is rich in antimony ore resources, with potential for discovery of additional ore. This high-elevation mountainous area is located in the northwestern region of the northern Tibetan Plateau, with a harsh natural environment and poor transportation access; thus, the use of traditional geological exploration methods is limited, and remote sensing technology provides unique advantages.Methods: Using Landsat 8 OLI and Gaofen-6 (GF-6) data, we extracted stratigraphic, lithologic and fault information from the study area through information enhancement processing of the images. Based on Landsat 8 OLI, Sentinel-2 and ASTER images and the use of remote sensing image preprocessing and interference information masking, the spectral characteristics of limonite, as well as hydroxyl, carbonate, and silicified alteration minerals were utilized; the characteristics included reflection or absorption in specific spectral bands. The spectral characteristics were then combined with principal component analysis (PCA) and the band ratio method to extract the alteration information for the study area.Results: The stratigraphy and boundaries between stratigraphic and lithologic units extracted in this study were defined, and numerous small faults were identified based on a comparison with 1:250,000 geologic maps. And the overall distribution trends of the indicators of alteration extracted in this study were located along fault zones; additionally, the hydroxyl and carbonate alteration anomalies matched well with known deposits (occurrences). Thus, the alteration information is a good indication of antimony ore bodies. Based on the geological interpretation, alteration information extraction and geochemical exploration data, four prospecting areas were identified.Discussion: The method of extracting geological and hydrothermal alteration information by remote sensing has practical significance because it provides the possibility for geological work and mineral exploration in difficult high-elevation environments.

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 SMOTified extreme learning machine for identifying mineralization anomalies from geochemical exploration data: a case study from the Yeniugou area, Xinjiang, China

A SMOTified extreme learning machine for identifying mineralization anomalies from geochemical exploration data: a case study from the Yeniugou area, Xinjiang, China

A high-performance voting-based ensemble model of graph convolutional extreme learning machines for identifying geochemical anomalies related to mineralization

How to effectively identify mineralization anomalies from geochemical survey data is one of the key problems that must be properly solved in geochemical exploration. Although supervised machine learning and deep learning techniques have been adopted to solve this problem, the performance of the established mineralization anomaly identification models is not satisfactory because the mutual relationship between neighborhood data points is not taken into account in the modeling of geochemical exploration data. The graph convolutional extreme learning machines (GCELMs) provide a new technique for modeling the graph data transformed from geochemical exploration data. To improve the performance of mineralization anomaly identification algorithms, the GCELM techniques were adopted to establish the supervised classification models for identifying mineralization anomalies from geochemical exploration data. To improve the robustness of the GCELM models in mineralization anomaly identification, an ensemble classification model called voting-based GCELM (V-GCELM) model was established by voting the outputs of multiple GCELM models. The Baishan area of Jilin Province (China) was taken as the study area for carrying out an experiment of mineralization anomaly identification from geochemical exploration data. The synthetic minority over-sampling technique (SMOTE) was used to alleviate the class-imbalance of the training data. The GCELM model, V-GCELM model and extreme learning machine (ELM) model were established for identifying mineralization anomalies, and their performances were compared in terms of the receiver operating characteristic (ROC) curves, area under the curves (AUCs) and lift indices. The results show that the V-GCELM model has the best performance, and its AUC and lift index are 0.9989 and 28.6, respectively. The GCELM model has the second-best performance, and its AUC and lift index are 0.9977 and 20.1, respectively. The ELM model has the worst but still high performance, its AUC and lift index are 0.9402 and 9.2, respectively. The mineralization anomalies identified by the three models have close spatial correlation with the polymetallic deposits found in the study area, and spatially controlled by the main controlling factors in the study area. Therefore, GCELM and V-GCELM are promising techniques for building the high-performance classification models for identifying mineralization anomalies from geochemical exploration data.

Graph inference algorithms as high-performance tools for detecting geochemical anomalies related to mineralization from geochemical exploration data

Geochemical exploration data usually consists of a small number of labeled data (cells containing known deposits) and a large number of unlabeled data (cells containing none of known deposits). How to make full use of a small number of labeled data and a large number of unlabeled data to build a high-performance anomaly detection model for identifying mineralization anomalies from geochemical exploration data is a challenge faced by geochemical exploration practitioners. The graph inference algorithms including label propagation and label spreading can efficiently build high-performance semi-supervised classification models by learning from sparse labeled and abundant unlabeled data in machine learning. For this reason, the two graph inference algorithms were used to build the semi-supervised classification models to detect Fe-mineralization anomalies from stream sediment survey data of 1: 50,000 scale in the Chengde area (Hebei Province, China). The label propagation model and label spreading model were compared with the Gaussian mixture model and logistic regression model in detecting Fe-mineralization anomalies. The data processing time of the label propagation algorithm and label spreading algorithm is 64.26 s and 28.21 s, respectively; and the data processing time of the Gaussian mixture model and logistic regression algorithm is 37.79 s and 18.98 s, respectively. The area under the receiver operating characteristic curves (AUCs) of the label propagation model and label spreading model are 0.979 and 0.999, respectively; and the AUCs of the Gaussian mixture model and logistic regression model are 0.800 and 0.817, respectively. Therefore, the data modeling efficiency of the label propagation model and label spreading model is comparable to that of the Gaussian mixture model and logistic regression model in detecting Fe-mineralization anomalies. However, the performance of the label propagation model and label spreading model are significantly better than that of the Gaussian mixture model and logistic regression model. It can be concluded that the two graph inference algorithms are potentially useful high-performance tools for detecting mineralization anomalies from geochemical exploration data.

CNN2D-SENet-Based Prospecting Prediction Method: A Case Study from the Cu Deposits in the Zhunuo Mineral Concentrate Area in Tibet

Intelligent prospecting and prediction are important research foci in the field of mineral resource exploration. To solve the problem of the performance degradation of deep convolutional neural networks, enhancing the attention to target information and suppressing unnecessary feature information, this paper proposes a new prospecting prediction method based on a two-dimensional convolutional neural network (CNN2D). This method mainly uses known Cu deposits as the positive sample labels, adopts the sliding window method for data enhancement, and uses the window area as a unit to extract spatial variation features. It is important to supplement squeeze-and-excitation networks (SENets) to add an attention mechanism to the channel dimension, assign a weight value to each feature layer, and finally make prospecting predictions by matching the features of the known deposit window area and the features of the unknown window area. This method allows the neural network to focus on certain characteristic channels and realizes prospecting prediction in the case where there are few known deposits so that the deep learning method can be more effectively used for the prospecting prediction of mineralization. Based on geological data, geochemical exploration data of water system sediments, and aeromagnetic data, and via this method, this study carried out prospecting prediction of Cu deposits in the Zhunuo area of Tibet and predicted 12 favorable Cu prospecting prediction areas. Combined with previous research results and field exploration, the predicted result is consistent with the established mineralization and prospecting pattern and has good prospects for Cu deposit prospecting.

Self-paced ensemble for constructing an efficient robust high-performance classification model for detecting mineralization anomalies from geochemical exploration data

Given a base classifier such as the support vector classifier, the self-training algorithm can be used to build a high-performance classification model to detect mineralization anomalies from geochemical exploration data. However, the established classification model has poor robustness. To solve this problem, the self-paced ensemble algorithm was adopted to establish an efficient robust high-performance model for detecting mineralization geochemical anomalies. The self-paced ensemble algorithm can efficiently build a robust classification model based on a base classifier such as the support vector classifier, decision tree classifier, k-nearest neighbor classifier, gradient boosting classifier and multilayer perceptron. To illustrate the superiority of the self-paced ensemble algorithm, a case study for molybdenum mineralization anomaly detection was carried out in the Molidawa area, Inner Mongolia, China. The self-paced ensemble algorithm and self-training algorithm were used to build classification models based on decision tree classifier to detect molybdenum mineralization anomalies from stream sediment survey data. Each algorithm was repeated five times, each time using the same set of parameters to initialize the algorithm. Thus, five classification models were established for each algorithm. The precision-recall curve (PRC) and area under the precision-recall curve (AUPRC) were used to evaluate the performance of the classification models in geochemical exploration. The results show that compared with the PRCs of the five classification models established by the self-training algorithm, the PRCs of those established by the self-paced ensemble algorithm coincide with each other and are closer to the upper right corner of the precision-recall space. The AUPRCs of the five classification models established by the self-paced ensemble algorithm are all 0.3538, and the AUPRCs of those established by the self-training algorithm are between 0.006624 and 0.02941, much lower than the value 0.3538. In addition, the time of the self-paced ensemble algorithm for geochemical data modeling ranges from 44.84 to 47.05 s, and the time of the self-training algorithm for geochemical data modeling ranges from 51.97 to 59.46 s. Therefore, the data-modeling efficiency, robustness and classification performance of the model established by the self-paced ensemble algorithm are better than those of the model established by the self-training algorithm in detecting molybdenum mineralization anomalies. It can be concluded that the self-paced ensemble algorithm is one of effective tools to establish an efficient robust high-performance classification model for mineralization anomaly detection.

Detection of geochemical anomalies related to mineralization using the Random Forest model optimized by the Competitive Mechanism and Beetle Antennae Search

This study aimed to detect the geochemical anomalies related to Fe-mineralization in the Hunjiang area in Jilin Province, China. For this purpose, a Random Forest model was optimized from two aspects of parameters' search and seeking the optimal solution by integrating the “Beetle Antennae Search” and “Competitive Mechanism”. The optimized Random Forest model was compared with the original Random Forest model in the detection of geochemical anomalies related to Fe-mineralization. The results showed that the optimized Random Forest model avoids some limitations of the original Random Forest model, with significant advantages in the detection of mineralization-related anomaly information from exploration geochemical data. It allowed automatic optimization of parameters by integrating two heuristic searching processes. Simultaneously, it focussed more on the quest for the best global optimal solution. Through the case study, it is found that the optimized Random Forest algorithm significantly improved the overall performance for the detection of geochemical anomalies related to Fe-mineralization. The geochemical anomalies detected by the optimized Random Forest model showed close spatial correlation with known iron polymetallic deposits. Therefore, using the optimized Random Forest model to detect geochemical anomalies related to mineralization is of great importance. It also provides a better supporting foundation for geochemical exploration and mineral resource exploration in the Hunjiang area.

Geochemical survey data cube: A useful tool for lithological classification and geochemical anomaly identification

Geochemical survey data play a critical role in geological studies, mineral exploration, and environmental applications by providing information on geological events and processes such as mineralization and pollution. A typical geochemical survey dataset contains the analysis of multiple elements. For example, the National Geochemical Mapping Project of China comprises 39 major and trace element concentrations. Multiple geochemical maps can be generated by interpolating geochemical samples into raster maps to constitute a geochemical survey data cube in which elements are sorted by their atomic numbers. A geochemical spectrum can be created using these geochemical maps in which each pixel that records geochemical characteristics. In this study, a convolutional neural network (CNN) that considers the geochemical spectrum and spatial pattern of geological objects was employed to mine a geochemical survey data cube, aiming of geological mapping and geochemical anomalies identification associated with mineralization in the eastern part of Hubei Province of China. The results showed that (1) a geochemical survey data cube which built based on various geochemical exploration data provided vital information on mineralization process and the formation of geological features; and (2) a CNN had a strong ability to recognize high-level features in the geochemical survey data cube, and it showed excellent performance in mineral exploration and related geological studies.

Introduction to the thematic collection: applications of innovations in geochemical data analysis

Geochemistry: Exploration, Environment, Analysis (GEEA) as the scientific journal of the AAG focuses on the use of geochemistry in mineral exploration/resource development. Since the first issue of GEEA was published in 2001, there have been hundreds of papers regarding methodologies for geochemical data analysis. In 2017, a thematic issue: analysis of exploration geochemical data for mapping of anomalies (Carranza and Zuo, 2017) was published on the development of methods and techniques for exploration geochemical data analysis. As a successor, this current thematic set of papers introduces some new progress and advancements in geochemical data analysis, e.g., nonlinear, fractal/multifractal, multi-statistical, machine learning methods and their applications in mineral exploration. Twelve papers from Professor Qiuming Cheng's colleagues in China and Canada are organized in this thematic set in honor of his Gold Medal Award. Thematic collection: This article is part of the Applications of Innovations in Geochemical Data Analysis collection available at: https://www.lyellcollection.org/topic/collections/applications-of-innovations-in-geochemical-data-analysis

Constructing a high-performance self-training model based on support vector classifiers to detect gold mineralization-related geochemical anomalies for gold exploration targeting

In an area where mineral deposits have been discovered, both anomaly detection algorithms and supervised classification algorithms can be adopted to detect mineralization-related geochemical anomalies for mineral exploration targeting. However, anomaly detection algorithms themselves cannot use known mineral deposits as the supervisors to improve the performance of geochemical anomaly detection models. Supervised classification algorithms can not properly deal with the extreme class-imbalance of geochemical exploration data in the establishment of classification models. Therefore, neither anomaly detection models nor supervised classification models perform well in the detection of mineralization-related geochemical anomalies. In order to obtain a high-performance mineral exploration targeting model, the self-training algorithm was adopted to construct a self-training model based on support vector classifiers to detect gold mineralization-related geochemical anomalies in the Chengde area in Hebei Province (China). The self-training model was compared with the support vector classification model, logistic regression model and five dictionary learning models in terms of area under the curve (AUC) and lift index. The AUC value of the self-training model (0.89) is much higher than those of the two supervised classification models (0.81–0.82) and five anomaly detection models (0.79–0.81). The lift index of the self-training model (11.87) is also much higher than those of the two supervised classification models (2.77–4.04) and five anomaly detection models (2.64–3.48). Therefore, the self-training model performs much better than the two supervised classification models and five anomaly detection models in the detection of gold mineralization-related geochemical anomalies. The gold mineralization-related geochemical anomalies detected by the self-training model highly conform to the metallogenic and geological features in the study area. Therefore, it is a prospective method to establish a self-training model to detect mineralization-related geochemical anomalies in an area where mineral deposits have been discovered.

Identification of geochemical anomalies related to mineralization: A case study from porphyry copper deposits in the Qulong-Jiama mining district of Tibet, China

Geochemical exploration data plays a vital role in mineral prospectivity mapping (MPM) for discovering unknown mineral deposits. In this study, compositional balance analysis (CoBA), unsupervised and supervised learning are collaboratively used to improve the practice of identification of geochemical anomalies related to mineralization in the Qulong-Jiama mining district of Tibet. For CoBA, five balances of geochemical elements were constructed by the sequential binary partition (SBP) technique, facilitating the interpretation of geochemical/geological processes and contrasting with geochemical anomalies generated by unsupervised and supervised learning. The iterative self-organizing data analysis techniques algorithm (ISODATA) and isolation forest (iForest) are used for preprocessing the geochemical data and therefore optimizing the appropriate training sets (e.g., positive and negative training samples) for supervised learning. Different training datasets including locations of known mineralization, randomly selected positive samples from resulting clusters by ISODATA and outliers by iForest are fed to the support vector machine (SVM) and random forests (RF) algorithm. The results of high AUC values indicate that supervised learning can effectively delineate prospective areas both with SVM and RF, however, the excessive large area of high-prospectivity and a bias toward known mineralization makes the outcomes of MPM unpractical. Nevertheless, a hybrid of the CoBA, unsupervised learning and supervised learning could alleviate such situations and provide insights into MPM using the geochemical data.

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.

Geochemical anomaly mapping using sparse principal component analysis in Jining, Inner Mongolia, China

Mapping geochemical anomalies is one of the most important tasks in mineral exploration. Sparse principal component analysis (SPCA) can be applied to investigate the correlations among geochemical elements and geological variables, which forces the loading values of the partial elements to zero. In this paper, the robust SPCA algorithm was used to process geochemical exploration data on a scale of 1:50,000 for identifying geochemical anomalies related to mineralization. The results show SPC1 and SPC3 indicate the spatial distribution of the Hannuoba basalt and Jining Group formation, respectively. The outcropped Hannuoba formations are located in high-value area of scores map of SPC1. The element association of W-Mo on SPC2 is related to molybdenum (Mo) mineralization. The spatial distribution of SPC2 scores suggests the distribution of Mo mineralization. The discovered Mo polymetallic deposits are located in the anomalous area of SPC2 scores. The SPCs identify localized geochemical anomalies and disambiguate the effects of outliers, which improve interpretability. These results indicate SPCA is a powerful tool for mapping geochemical anomalies.

The concept of anomaly as interpretative basis for the geochemical exploration data

The concept of anomaly as interpretative basis for the geochemical exploration data

Information value-based geochemical anomaly modeling: A statistical index to generate enhanced geochemical signatures for mineral exploration targeting

Converting geochemical exploration data into information relevant to descriptive statistics of indicator elements facilitates gaining the knowledge of spatial and genetic relationships between mineralization and elemental dispersion patterns. This allows obtaining insights into alternatives to exploration strategies aiming at vectoring toward undiscovered mineral deposit sites. In this regard, shaping geochemical data for better understanding of their underlying patterns and extraction of information about ore deposition-related anomalies are challenging issues. To better extraction of the information from the geochemical data, we adapted the “information value” concept to quantify the significance of geochemical anomaly classes as spatial proxies of mineral deposits. To illustrate and evaluate the procedure proposed, a dataset of porphyry-Cu exploration was used to delineate exploration targets in the Baft district, Kerman province, Iran. Through this, geochemical models of information values were created for ore deposition-related elements. Then, the geochemical models were combined to produce an information value-based multi-element geochemical signature aiming at utilizing the prediction ability of every indicator element in a single model. Through the combination, spatial patterns of geochemical signals around mineral deposits are revealed that makes it easier to explore undiscovered deposit sites. We also applied fuzzy operators, as common and alternative practices, to integrate values of the same indicator elements for comparison purpose. The results demonstrated that the model of information value-based multi-element geochemical signature is an efficient geochemical proxy, over those geochemical models generated by the application of fuzzy operators, for exploration targeting.

Visualization and interpretation of geochemical exploration data using GIS and machine learning methods

Geochemical exploration has provided significant clues for mineral exploration and has helped discover many mineral deposits. Although various methods, including classic statistics, multivariate statistics, geostatistics, fractal/multifractal models, and machine learning algorithms, have been successfully employed to process geochemical exploration data, efficient interpretation and visualization of geochemical exploration data in support of the discovery of mineral deposits remain challenging. In this study, a workflow for intelligent interpretation and visualization of geochemical exploration data, defined as processing geochemical survey data with support of a geographical information system (GIS) and machine learning algorithms, was proposed. The effectiveness of the intelligent interpretation and visualization of geochemical exploration data supported by GIS and machine learning algorithms was demonstrated using a case study of processing a regional-scale geochemical survey dataset collected from Sichuan Province, China. Future research should add more advanced mathematical and statistical models, such as deep learning algorithms, into GIS to support the intelligent interpretation and visualization of geochemical exploration data.