Prediction-area Plot Research Articles

The influence of supervised and unsupervised methods in the analysis of low density stream sediments in the regional prospecting of pegmatites in the state of Espírito Santo, Araçuaí Orogen - Eastern Pegmatite Province of Brazil

The state of Espírito Santo is located in Brazil southeastern and it is geologically inserted in the Eastern Brazilian Pegmatite Province in the Araçuaí Orogen. This province is one of the most important pegmatite provinces in the world, known mainly for the occurrence of gem-quality minerals and high grade lithium deposits. Although Espírito Santo has a geological framework with many granite intrusions similar to those hosting mineralized pegmatites in Minas Gerais, it hasn't been acknowledged as a potential pegmatitic area. There are reports of mineralization of beryl (aquamarine), topaz, amethyst, and chrysoberyl in the state's mineral history. I this research we use regional stream sediment geochemical data of the Espirito Santo State, to create prospective geochemical maps to map gemological pegmatites. To do so, primary descriptive statistical analyses as well as Pearson and Spearman correlations and Principal Component Analysis (PCA) were used to select elements associated with pegmatites. The geochemical prospectivity mapping was carried out by supervised and unsupervised approaches. The supervised method was based on integration of the elements by C-A fractal models, used to define the geochemical thresholds, and fuzzy logic methodology to integrate weighted geochemical maps. The unsupervised approach, however, was based on interpolation of the representative principal component scores. All models were validated using the Prediction Area plot (P-A plot). The results of our research showed that unsupervised methodology overperformed the other weighted supervised models, with a prediction rate of 78.14 % and prospectivity of 0.87. The final results also show a pegmatite prospectivity map for the Espirito Santo state, that indicates a great exploration potential for gemological minerals.)

Adopting a cell-based method to identify mineralized geological structures in support of mineral prospectivity mapping at the Kuh–Lakht epithermal gold deposit, Central Iran

Mineral prospectivity mapping (MPM) is a new tool in mineral exploration with the objective of gathering and integrating multi-source evidence to provide decision-making criteria for exploration targeting. Ideally, the MPM approach accounts for the uncertainties associated with different predictive modeling techniques. The cell-based association (CBA) is a computational workflow that addresses the prediction-related bias of the MPM protocols. In this contribution, the CBA technique was employed to prioritize grid cells according to the importance of mineralized geological features and to identify geological settings favorable for ore deposition. The Kuh-Lakht epithermal gold deposit in Central Iran was adopted as a case study to examine the relevance of the proposed workflow and define target areas for brownfield exploration. To assess the significance of the proposed technique in dealing with evidence layers rather than training locations (i.e., mineralized/non-mineralized sites), two geochemical evidence layers, single-element and multi-element signatures, were used to train the CBA technique. An appraisal analysis through prediction-area plots and success-rate curves indicated that multi-element geochemical signatures are more relevant for delineating mineralized geological structures and vectoring for concealed gold mineralization. Notably, the input of single-element geochemical data into the CBA workflow enabled the prediction of additional exploration targets, whereas multi-element geochemical data failed to achieve the same results. The results indicated that the CBA technique can efficiently cope with the uncertainty of insufficient data input and permit the delineation of exploration targets. Additionally, our results suggest that the incorporation of a ranking system of critical geological factors that facilitate the gold mineralization into conventional MPM protocols can improve the robustness of mineral exploration targeting.

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.

Targeting porphyry Cu deposits in the Chahargonbad region of Iran: A joint application of deep belief networks and random forest techniques

Mineral prospectivity modeling (MPM) is a valid and progressively accepted predictive tool for mapping reproducible potential mineral exploration targets. In this study, a hybrid approach combining unsupervised deep belief networks with supervised random forest (DBN-RF) is performed to delineate potential exploration targets for porphyry Cu deposits in the Chahargonbad region of Iran. Firstly, a mineral system model for porphyry Cu deposits is established, and relevant targeting criteria are delineated based on comprehensive exploration datasets. Subsequently, within this hybrid framework, the DBN extracts deep implicit feature information, which is then utilized as input for the RF. The comparative results on the performance of the hybrid model and the RF model trained by the primary targeting criteria, in terms of the improved prediction-area plot, demonstrate that the DBN-RF prospectivity model outperformed the RF-generated model with an overall efficiency of 0.53. This hybrid model accurately identified 81.97 % of known Cu deposits within an investigation area of 18.03 %, with primary trends aligned with the primary faults and volcanic units of the region. This study demonstrates effective performance of DBN-RF in identifying exploration targets for porphyry Cu deposits at regional scale and also highlights the potential of deep learning-based methods for successful MPM.

Fractal-Based Multi-Criteria Feature Selection to Enhance Predictive Capability of AI-Driven Mineral Prospectivity Mapping

AI-driven mineral prospectivity mapping (MPM) is a valid and increasingly accepted tool for delineating the targets of mineral exploration, but it suffers from noisy and unrepresentative input features. In this study, a set of fractal and multifractal methods, including box-counting calculation, concentration–area fractal modeling, and multifractal analyses, were employed to excavate the underlying nonlinear mineralization-related information from geological features. Based on these methods, multiple feature selection criteria, namely prediction–area plot, K-means clustering, information gain, chi-square, and the Pearson correlation coefficient, were jointly applied to rank the relative importance of ore-related features and their fractal representations, so as to choose the optimal input feature dataset readily used for training predictive AI models. The results indicate that fault density, the multifractal spectrum width (∆α) of the Yanshanian intrusions, information dimension (D1) of magnetic anomalies, correlation dimension (D2) of iron-oxide alteration, and the D2 of argillic alteration serve as the most effective predictor features representative of the corresponding ore-controlling elements. The comparative results of the model assessment suggest that all the AI models trained by the fractal datasets outperform their counterparts trained by raw datasets, demonstrating a significant improvement in the predictive capability of fractal-trained AI models in terms of both classification accuracy and predictive efficiency. A Shapley additive explanation was employed to trace the contributions of these features and to explain the modeling results, which imply that fractal representations provide more discriminative and definitive feature values that enhance the cognitive capability of AI models trained by these data, thereby improving their predictive performance, especially for those indirect predictor features that show subtle correlations with mineralization in the raw dataset. In addition, fractal-trained models can benefit practical mineral exploration by outputting low-risk exploration targets that achieve higher capturing efficiency and by providing new mineralization clues extracted from remote sensing data. This study demonstrates that the fractal representations of geological features filtered by multi-criteria feature selection can provide a feasible and promising means of improving the predictive capability of AI-driven MPM.

Geochemical mapping by stream sediments of the NW portion of Quadrilátero Ferrífero, Brazil: Application of the exploratory data analysis (EDA) and a proposal for generation of new gold targets in Pitangui gold district

Quadrilátero Ferrífero (QF) is a worldwide known metallogenetic province and has in its NW portion the Pitangui greenstone belt, one of the new frontiers for gold exploration in that region, presenting important gold deposits, such as Turmalina and São Sebastião. Among several actions of the geological and mineral resources projects carried out by Geological Survey of Brazil (SGB/CPRM) in the QF region, a high-density geochemical survey (1 sample/4 km2) by stream sediments was accomplished in its NW portion to better understand the behavior and distribution of chemical elements along the main geological units, especially those related to gold mineralization (Au, As, Sb, Bi, etc.). The exploratory data analysis (EDA), regarding uni-, bi-, and multivariate analyses, point to an important chemical control of the stream sediments by the geological units and help to describe some lithological features and to understand the behavior and distribution of hydrothermal processes and gold mineralization. This procedure defined the main geochemical associations, including the association As, Sb, Cu and Bi linked to Ni, Cr and Co, interpreted as gold mineralization hosted in the metavolcanosedimentary lithotypes. The staged factor analysis (SFA) considering compositional data (CoDa), logistic function, and fractal model approaches provided the generation of the geochemical mineralization probability index (GMPI), which produce a GMPI map for gold mineralization. The calculations did not take into account the gold concentrations but only the pathfinder elements and the model validation by the prediction-area plot, confirm the high performance of this approach. The gold mineralization map, in addiction to satisfactorily predicting the location of most known gold occurrences, was able to indicate new potential targets for prospecting new gold deposits.

Infomax-based deep autoencoder network for recognition of multi-element geochemical anomalies linked to mineralization

In recent years, deep autoencoder networks (DANs) have shown enormous potential to achieve state-of-the-art performance for recognizing multi-element geochemical anomalies related to mineralization. By training a DAN, multi-element signatures of geochemical background are learned by higher-level representations of input signals, providing key references to quantify reconstruction errors linked to complex patterns of metal-vectoring geochemical anomalies in non-linear Earth systems. However, the learning of geochemical background representations may be suppressed by redundant mutual information from inter-element correlations and by mixed information of elemental concentration data caused by multiplicative cascade geo-processes. To deal with these issues, we conceptualized an idea of a new deep learning architecture called Info‒DAN, chaining the information maximization (Infomax) processor to the training network of stacked autoencoders. Infomax is an adaptive learning algorithm from information theory paradigms which aims at maximizing the information flow (joint entropy) passed through a feed-forward neural network processor. It was adopted to encode original multi-element data into independent source signals associated with different geochemical sub-populations and to prevent the dilution of background representations caused by inter-element information redundancy. The recovered source signals were then fed into a DAN processor to assist in modeling the improved representations of geochemical background populations and in enhancing complex anomaly patterns. The Info‒DAN technique was applied to stream sediment geochemical data pertaining to the Moalleman district, NE Iran, for performance appraisal in recognition of metal-vectoring geochemical anomalies. Evaluation tools comprising success-rate curves and prediction-area plots indicated that anomaly patterns derived from Info‒DAN, compared to those from a stand-alone DAN, reveal a stronger spatial correlation between ore-controlling fractures/faults and locations of known metal occurrences. The findings suggest that, thanks to the proposed algorithm, complex patterns of geochemical anomalies can be quantified with improved generalization accuracy as well as practical insights for vectoring towards metal exploration targets.

A comparative analysis of multi-index overlay and fuzzy ordered weighted averaging methods for porphyry Cu prospectivity mapping using remote sensing data: the case study of Chahargonbad area, SE of Iran

One of the specific features of porphyry copper (Cu) mineralization is the distinct occurrence of hydrothermal alteration zones, which can be mapped by processing various satellite images. Among free multispectral images, Landsat 8 OLI and ASTER data are known to be efficient in mapping different geological features, such as alteration zones and tectonic lineaments. This study aims to show the potential of these data types in mapping porphyry Cu mineralization by proposing a framework for employing and integrating different image processing methods. These methods include principal component analysis (PCA), spectral angle mapper (SAM), and matched filtering (MF) employed on these satellite images to map target al.teration zones. Moreover, PCA and directional filtering are applied to the ASTER dataset to enhance and map structural features. The results are evaluated and then combined to provide a potential map of Cu mineralization in the Chahargonbad area, located within the Urumieh-Dokhtar magmatic belt (UDMB) in Kerman province, Iran. The prediction-area plot and normalized density, which are data-driven methods, are used to assign the relative weight of each layer and evaluate them. Finally, using the calculated weights, data-driven multi-index overlay (DMIO) and fuzzy ordered weighted averaging (FOWA) methods are applied to combine the evidential layers. The potential mineralization maps created by the DMIO and FOWA provide a prediction rate of 80% and 82%, respectively. Furthermore, the accuracy of the integrated maps is investigated using the area under the curve (AUC) of the receiver operating characteristic (ROC) curves. The AUC scores obtained from the ROC curves of DMIO and FOWA methods are 0.85 and 0.88, respectively, representing powerful positive spatial relationships with mineralization areas. Based on the results, the proposed framework can be applied to provide a potential map of porphyry Cu mineralization, particularly in arid regions, with reasonable accuracy.

Applying Data-Driven-Based Logistic Function and Prediction-Area Plot to Map Mineral Prospectivity in the Qinling Orogenic Belt, Central China

This study combines data-driven-based logistic functions with prediction–area (P–A) plot for delineating target areas of orogenic Au deposits in the eastern margin of the Qinling metallogenic belt, central China. First, appropriate geological and geochemical factors were identified, optimized, and transformed into a series of fuzzy numbers with a range of 0–1 through a data-driven-based logistic function in order to determine the evidence layer for prospecting orogenic Au. In addition, the P–A plot was derived on the above evidence layers and their corresponding fuzzy overlay layers to pick out a proper prediction scheme, in the process of which acidic magmatic activity proved to be the most important factor of ore-controlling. Moreover, to further prove the advantages of this method, a traditional linear knowledge-driven approach was carried out for comparative purposes. Finally, based on concentration–area (C–A) fractal theory, the fractal thresholds were determined and a mineral prospecting map was generated. The obtained prediction map consisted of high, medium, low, and weak metallogenic potential areas, accounting for 2.5%, 16.1%, 38.4%, and 43% of the study area, containing 2, 3, 1, and 0 of the 6 known mine occurrences contained, respectively. The P–A plot indicated that the result predicted 83% of Au deposits with 17% of the area, confirming the joint application of the data-driven-based logistic function and P–A plot to be a simple, effective, and low-cost method for mineral prospectivity mapping, that can be a guidance for further work in the study area.

Geochemical potential mapping of iron-oxide targets by Prediction-Area plot and Concentration-Number fractal model in Esfordi, Iran

This study serves the purpose of generating a geochemical Fe-bearing potential map. Stream sediment geochemical survey was employed by collecting 843 samples for analyzing 19 elements and oxides. Taking preprocessing of data (e.g. outlier correction and data normalization) into consideration, a Concentration–Number (C-N) fractal model was used to separate different geochemical populations of Fe2O3, TiO2, V and the main multi-element factor in close spatially association with the Fe targeting. A prediction-area (P-A) plot was drawn for each variable to determine the weight of each geochemical indicator. Results indicate that the main geochemical factor with an ore prediction rate of 73%, has occupied 27% of the Esfordi area as favorable zones for further mining propsectivity. The Esfordi as a favorable Fe-bearing zone is of special interest in the NE of the Bafq mining district that hosts important “Kiruna-type” Magnetite-Apatite deposits. In addition, a synthesized indicators map was prepared through implementing a data-driven multi-class index overlay in a similar fashion to the previous version of the method, upon which geochemical potential zones were mostly in the NE part of the Esfordi, intimately linked with intense fault density map. The significance of this study lies in localizing of the most geochemical favorable zones through simultaneous consideration of the C-N and P-A plots accompanied with the incorporation of known active mines and prospects to determine indicator weight. Of note is that the Mineral Potential Mapping (MPM) has higher efficiency over each geochemical indicator with an ore prediction rate of 78% and area occupation of 22%.

A spatial reconnaissance survey for gold exploration in a schist belt

Geological data integration and spatial analysis for structural elucidation are more assertive approaches for reconnaissance scale mineral exploration. In this study, several methods involving Fry analysis, distance correlation analysis, prediction area plots as well as knowledge driven predictive models including TOPSIS, ARAS and MOORA were systematically employed for unravelling the spatial geological attributes related to gold mineralisation. Additionally, statistical validation of knowledge driven predictive models were implemented using the Receiver Operating Characteristic/Area Under Curve analysis (ROC/AUC). The evidence from Fry and distance correlation analysis suggests that gold occurrence within parts of the Malumfashi schist belt of Nigeria is defined by a strong spatial association with the ENE-WSW as well as the NNE-SSW trending structures. The prediction area plot also revealed a robust spatial correlation between mineral occurrence and spatial data related to geological structures. The application of knowledge driven predictive models suggest a high favourability for gold occurrence within the southern, central, and north-eastern parts of the study location, while statistical validation using the ROC/AUC curves suggest a high prediction accuracy greater than 70% for all models. The geospatial analysis for mineral exploration within the Malumfashi area has unveiled an invaluable geological criterion for gold targeting with a considerable level of certainty.

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.

Regional-Scale Mineral Prospectivity Mapping: Support Vector Machines and an Improved Data-Driven Multi-criteria Decision-Making Technique

Mapping mineral prospectivity (MPM) is mostly beset with prediction uncertainties, which are generally categorized into (a) stochastic and (b) systemic types. The stochastic type is usually linked to the low quality as well as insufficiency/inefficiency of data used. In contrast, inaccurate selection of exploration criteria, exaggerated and arbitrary weighting of spatial evidence layers resulting from subjective judgment of analyst and applying an integration methodology, which is not able to consider the complexities of geological processes, are main sources of systemic type. This paper aims for reducing the second type of MPM uncertainty in delineating favorable exploration targets for Cu-Au mineralization in the Moalleman District, NE Iran. Thus, several efficient evidence layers were translated from geospatial criteria (e.g., geochemical, geological, structural and hydrothermal alterations) and were considered for integration purpose in the study area. Then, an improved data-driven simple additive weight (data-driven SAW) procedure was introduced for generating prospectivity model. In this procedure, prediction-area plots and frequency ratio method were applied for assigning objective weights to efficient evidence layers and their corresponding classes, respectively. Furthermore, a supervised algorithm for machine learning classification namely support vector machine (SVM) with radial basis function kernel was executed for comparison purposes. The results indicated that the two prospectivity models are succeeded in delineating favorable targets of mineralization; however, the SVM model is more reliable than data-driven SAW in predicting high-potential areas of mineralization.

Mapping gold mineral prospectivity based on weights of evidence method in southeast Asmara, Eritrea

Eritrea at the southern Nubian shield in northeast Africa has many gold deposits, and has been an important target for exploration. In view of the arid to semi-arid nature of the terrain, there is continuous quest for new methods of mineral exploration. In this study, we highlight the importance of GIS-based weights of evidence (WofE) method in mapping the gold mineral prospectivity of the Ewanet area, southeast Asmara. For the purpose, data was gathered from geological, metallogenic, geochemical and remote sensing analyses of the study area. Seven evidence maps produced from these spatial data sets were used to calculate posterior probabilities and delineate prospectivity areas for gold deposits. The prediction-area plot provides the evaluation of posterior probabilities and indicates that 83% of the existing mineral occurrences are predicted in 19% of the study area. Two types of gold occurrences, i.e., structure-alteration type and quartz-vein type, were identified during field work. It was found that faults are the main ore-controlling factors, and Au geochemical anomaly is prominently correlated with mineralization. We suggest that the identified prospectivity areas of gold exploration in the Ewanet area are well worth carrying out further mineral exploration.

Modelling gold potential in the Granites-Tanami Orogen, NT, Australia: A comparative study using continuous and data-driven techniques

The Granites-Tanami Orogen (GTO), a poorly exposed component of the North Australian Craton, is host to significant Paleoproterozoic orogenic gold mineralization amounting to a total endowment of greater 20 Moz Au. This study adopted a multi-technique approach to mineral potential modelling (MPM) of orogenic gold deposits in the GTO, using four different techniques: Continuous fuzzy gamma, geometric average and data-driven index overlay and data-driven random forest methods. The predictive models generated in this study delivered the first public-domain gold prospectivity maps for the Northern Territory (NT)-portion of the GTO. The predictor maps at the core of these models represent mappable proxies of mineralizing processes believed to have been critical in the formation of the orogenic gold deposits, and were generated in the framework of a mineral systems approach. Normalized density, prediction-area and area under the receiver operating characteristic curve methods were used to test the robustness of these predictors and determine the most effective. The performance of the gold potential models generated in this study was assessed using the improved prediction-area plot procedure, with the data-driven random forest approach having delivered the best performing model. The multi-technique approach taken in this study, in which multiple mineral potential models are generated for the same study area and using the same predictor maps, is a relatively new and, as of yet, underutilized approach to MPM that, in contrast to the standard procedure (i.e., generation of a single data- or knowledge-driven model) ensures optimal utilization of the available conceptual and empirical information, helps to better understand and minimize stochastic and systemic uncertainties, facilitates cross-validation of the resulting prospectivity models, and allows the resulting models to be compared and contrasted. From a practical, exploration point of view, the models served as decision-support tools that helped to improve confidence in targeting underexplored, gold-prospective areas in the GTO more effectively and identify new search areas previously not recognized as areas of high gold potential.

3D analysis of catchment basins by incorporating modified dilution correction equations in geochemical anomaly delineation

Analysis of stream sediment geochemical data has undergone a series of developments during last decades. As a matter of fact, many factors can potentially influence the chemical composition of these sediments and the existing techniques are not able to fully explain compositional variations occurring along with their transport. By applying some recently developed equations, this paper takes into account the topographical relief and the morphological surface areas of outcropping lithological units to both estimate local geochemical background values and delineate promising zones in terms of mineral exploration. Specifically, through the combination of a three-dimensional sample catchment analysis with dilution correction equation, the process of delineating catchment basins featured by economically relevant Cu occurrences has been improved. The effectiveness of the technique has been evaluated through the application of the prediction-area plot obtaining better results than applying the two-dimensional approach.

Weighted Photolineaments Factor (WPF): An Enhanced Method to Generate a Predictive Structural Evidential Map with Low Uncertainty, a Case Study in Chahargonbad Area, Iran

Decreasing the uncertainty and increasing the prediction rate of evidential maps are two important objectives in mineral prospectivity mapping (MPM). In this paper, we proposed weighted photolineaments factor (WPF) to generate a continuous weighted structural evidential map with high prediction rate and low uncertainty in Chahrgonbad area. The WPF which has four components was defined as weighted sum of the values related to four following characteristics of lineaments: (a) number, (b) length, (c) number of intersection and (d) number of directional sets. We used the extracted lineaments from geological map and processing of aeromagnetic data in our analysis to enhance the prediction rate of WPF map. The process was implemented using an effective multistage algorithm including: texture analysis, phase symmetry analysis, non-maximal suppression, thresholding, skeletonization and line fitting process. Afterward, values related to various characteristics of lineaments were extracted and transformed by a logistic function to improve their predictive ability. Then, using the concentration-area fractal model and prediction-area plot, the prediction rate of WPF components was derived and their importance weights were calculated using normalized density. Finally, the WPF map was generated and evaluated using location of 18 known mineral occurrences in the study area. The results demonstrated a good concordance with our previous geological knowledge and experience about Cu mineralization in Chahrgonbad area. The number of lineaments directional sets and the number of lineaments were recognized as structural criteria with the highest prediction rate for Cu prospectivity. The generated WPF map has a higher prediction rate (80%) in comparison with each individual component and delineated 20% of the study area as prospective target. Eventually, three zones with high structural permeability which are fertile environment for emplacement of intrusions, circulation of magmatic-hydrothermal fluids and Cu mineralization were delineated on the WPF map and proposed for further exploration.

3D Mineral Prospectivity Modeling for the Low-Sulfidation Epithermal Gold Deposit: A Case Study of the Axi Gold Deposit, Western Tianshan, NW China

The Axi low-sulfidation (LS) epithermal deposit in northwestern China is the result of geological controls on hydrothermal fluid flow through strike-slip faults. Such controls occur commonly in LS epithermal deposits worldwide, but unfortunately, these have not been quantitatively analyzed to determine their spatial relationships with gold distribution and further guide mineral prospecting. In this study, we conduct a 3D mineral prospectivity modeling approach for the Axi deposit involving 3D geological modeling, 3D spatial analysis, and prospectivity modeling. The spatial analysis of geometric features revealed the gold mineralization trends in convex segments (0–20 m) with a specific distance from fault 2, the lower interface of late volcanic phase, and the upper interface of phyllic alteration with steep slopes (>65°), implying that gold deposition was significantly controlled by the morphological characteristics and distance fields of geologic features. The present alteration–mineralization zone at Axi has a larger width in bending sites (sections No. 35–15 and No. 40–56) than elsewhere, indicating the location of two fluid conduits extending to depth. The prediction-area plots and receiver operating characteristic curves demonstrated that (genetic algorithm optimized support vector regression (GA-SVR)) outperformed multiple nonlinear regression and fuzzy weights-of-evidence, which was proposed as a robust method to solve complicated nonlinear and high-dimensional issues in prospectivity modeling. Our study manifests spatial controls of structure, host rock, and alteration on LS epithermal gold deposition, and highlights the capability of GA-SVR for identifying deposit-scale potential epithermal gold mineralization.

Identifying geochemical anomaly through spatially anisotropic singularity mapping: A case study from silver-gold deposit in Pangxidong district, SE China

The anisotropic singularity analysis, also referred to as Spatially Weighted Singularity Mapping (SWSM), was developed by means of multifractal modeling and spatial weighting. The SWSM extends the application of the Ordinary Singularity Mapping (OSM) technique, which is spatially isotropic, to the anisotropic case. In this paper, the SWSM method was demonstrated in a case study where the geochemical anomaly associated with the silver-gold mineralization was identified through mapping the spatially anisotropic singularity of the pathfinder elements including Ag, Au, Cu, Pb, and Zn, to in Pangxidong district, south of the Qinzhou-Hangzhou Metallogenic Belt, SE China. Firstly, using the stream sediment geochemical data and spatial weighting factor linked to NE-trending ore-controlling fault system, the local anisotropic singularity index values (i.e. ϵ-values) were estimated for each of the five elements. Then, Principal Component Analysis (PCA) was applied to the ϵ-values to obtain comprehensive geochemical anomaly of the multiple element (i.e. PC1 scores). It appeared that the comprehensive geochemical anomaly has a better prediction efficiency with the discovered silver-gold occurrences than the one derived from the OSM-PCA approach (PCA applied to singularity index values estimated by the OSM technique). The performance tests were assessed by using the receiver operating characteristics as well as prediction-area plot and concentration-area fractal analysis methods. Finally, the student's t-static method was employed to determine the reasonable threshold values separating the geochemical anomaly and background. The student's t-values indicate that spatial correlation between the locations of the known silver-gold mineral deposits and the geochemical anomaly derived by the SWSM-PCA approach was much stronger than that of the geochemical anomaly derived by the OSM-PCA method. The geochemical anomalies delineated by the SWSM-PCA approach were considered to be the favorable target areas for exploration of similar undiscovered silver-gold polymetallic deposits. This study has demonstrated that the SWSM approach can incorporate the spatial anisotropic information (e.g. direction and range of spatial variability), which exhibits geological controlling features, into the singularity analysis of geo-variables in various geo-spatial datasets such as geochemical, geophysical and remote sensing data.

Delineation of podiform-type chromite mineralization using geochemical mineralization prospectivity index and staged factor analysis in Balvard area (SE Iran)

The aim of this work was to delineate the prospects of podiform-type chromite by staged factor analysis and geochemical mineralization prospectivity index in Balvard area, SE Iran. The stream sediment data and fault density were used as the exploration features for prospectivity modeling in the studied area. In this regard, two continuous fuzzified evidence layers were generated and integrated using fuzzy operator. Then fractal modeling was used for defuzzification of the prospectivity model obtained. Furthermore, the prediction-area plot was used for evaluation of the predictive ability of the generated target areas. The results obtained showed that using the prospectivity model, 82% of mineral occurrences was predicted in 18% of the studied area. In addition, the target areas were correlated with the geological particulars including ultrabasic and serpentinization rocks, the host rocks of the podiform-type chromite deposit type.