Exploration
Mohammad Ebdali; Ardeshir Hezarkhani; Adel Shirazy; Amin Beiranvand Pour
Abstract
This research endeavor concentrates on minerals exploration within the context of a hydrothermal polymetallic vein deposit environment. Stream sediment sampling was executed to acquire geochemical signatures pertinent to mineralization zones. The mineralization nature is classified as epithermal, predominantly ...
Read More
This research endeavor concentrates on minerals exploration within the context of a hydrothermal polymetallic vein deposit environment. Stream sediment sampling was executed to acquire geochemical signatures pertinent to mineralization zones. The mineralization nature is classified as epithermal, predominantly involving polymetallic sulfides. The geochemical analyses yielded multi-element concentration maps, facilitating the identification of anomalies and the establishment of zoning. Although recent developments underscore the efficacy of machine learning, notably deep learning techniques, in the detection of geochemical anomalies, the majority of preceding studies were predicated on univariate statistical methodologies. To address this constraint, a multivariate approach was implemented, incorporating spatial characteristics such as shape, overlap, and zoning within anomalies and halos. Considering the limited availability of validated mineralized samples, unsupervised and semi-supervised methodologies—most notably Generative Adversarial Networks (GANs)—were employed. GANs were trained using multi-element geochemical maps, applying transfer learning to mitigate the challenges posed by restricted deposit data, thereby facilitating the delineation of prospective exploration zones. Quantitative analyses have indicated that the approach utilizing GANs attained an accuracy exceeding 92% alongside a minimal cross-entropy loss of approximately 0.07, thereby surpassing conventional methodologies in detecting of weak anomalies. The model effectively corroborated previously recognized anomalies while simultaneously detecting new prospective mineralization areas, thereby augmenting exploration opportunities. This investigation illustrates that GANs enable a more thorough utilization of geochemical datasets, integrating a wide range of variables and intricate spatial characteristics. Although GANs demonstrate superior proficiency in modeling weak anomalies, conventional techniques continue to be effective for more pronounced anomalies. The integration of both methodologies may enhance the efficiency of mineral exploration endeavors. In summary, the results emphasize the promise of GANs and sophisticated machine learning frameworks in enhancing anomaly detection and expanding mineral exploration within hydrothermal polymetallic systems.
Mineral Processing
Meysam Nikfarjam; Ardeshir Hezarkhani; Farhad Azizafshari; Hamidreza Golchin
Abstract
Geometallurgical modeling (GM) plays a crucial role in the mining industry, enabling a comprehensive understanding of the complex relationship between geological and metallurgical factors. This study focuses on evaluating metallurgical varibles at the Sungun Copper mine in Iran by measuring and predicting ...
Read More
Geometallurgical modeling (GM) plays a crucial role in the mining industry, enabling a comprehensive understanding of the complex relationship between geological and metallurgical factors. This study focuses on evaluating metallurgical varibles at the Sungun Copper mine in Iran by measuring and predicting process properties, including semi-autogenous power index (SPI), recovery (Re), and concentration grade. To overcome the additivity limitations of geostatistical methods, we utilized machine learning algorithms for enhanced predictive modeling, aiming to improve decision-making and optimize mining operations in geometallurgy. The research incorporates crucial data inputs such as sample coordinates, grades, lithology, mineralization zones, and alteration to assess the accuracy and reliability of different machine learning regression methods. The Relative Standard Deviation (RSD) is highlighted as a significant metric for comparing the accuracy of predicted process properties. Evaluation metrics such as Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and coefficient of determination (R2) further confirm the superiority of specific modeling methods in certain scenarios. The K-Nearest Neighbors (KNN) method exhibits superior accuracy, lower error metrics (RMSE and MAE), and a higher R2 for modeling the SPI test. For modeling Cu grade in concentrate, Support Vector Regression (SVR) proves to be effective and reliable, outperforming the Multilayer Perceptron (MLP) method. Despite MLP's high R2, its higher RSD suggests increased uncertainty and variability in the predictions. Therefore, SVR is considered more suitable for modeling Cu grade in concentrate. Findings optimize operations at Sungun Copper mine, improving decision-making, efficiency, and profitability.
Exploration
Mobin Saremi; Abbas Maghsoudi; Reza Ghezelbash; mahyar yousefi; Ardeshir Hezarkhani
Abstract
Mineral prospectivity mapping (MPM) is a multi-step and complex process designed to narrow down the target areas for exploratory activities in subsequent stages. To pinpoint promising zones of porphyry copper mineralization in the Varzaghan district, NW Iran, various exploration evidence layers were ...
Read More
Mineral prospectivity mapping (MPM) is a multi-step and complex process designed to narrow down the target areas for exploratory activities in subsequent stages. To pinpoint promising zones of porphyry copper mineralization in the Varzaghan district, NW Iran, various exploration evidence layers were employed in alignment with the conceptual model of these deposits. These layers encompass fault density, proximity to intrusive rocks, multi-element geochemical anomalies, and distances to phyllic and argillic alterations. The geochemical anomaly maps, recognized as the most effective layers, were generated through staged factor analysis (SFA) and the geochemical mineralization probability index (GMPI). Other layers were weighted using a logistic function, and their values were transformed into 0 -1 interval. Ultimately, to integrate the weighted layers, the fuzzy gamma operator and the geometric average method were applied. The normalized density index and prediction-area (P-A) plot were employed to evaluate the MPM models. The findings indicate that the developed models possess considerable validity and can be effectively utilized for planning future exploration endeavors.
Exploration
Bashir Shokouh Saljoughi; Ardeshir Hezarkhani
Abstract
The porphyry Cu-mineralization potential area studied in this article is located in the southern section of the Central Iranian volcano–sedimentary complex, contains large number of mineral deposits, and occurrences that are currently facing a shortage of resources. Therefore, prospecting potential ...
Read More
The porphyry Cu-mineralization potential area studied in this article is located in the southern section of the Central Iranian volcano–sedimentary complex, contains large number of mineral deposits, and occurrences that are currently facing a shortage of resources. Therefore, prospecting potential areas in the deeper and peripheral spaces has become a high priority in this region. Different direct and indirect methods try to predict promising areas for future explorations that most of them are very time-consuming and costly. The main goal of mineral prospecting is applying a transparent and robust approach for identifying high potential areas to be explored further in the future. This study presents the procedure taken to create two different Cu-mineralization prospectivity maps. This study aims to investigate the results of applying the ANN technique, and to compare them with the outputs of applying GEP method. The geo-datasets employed for creating evidential maps of porphyry Cu mineralization include solid geology map, alteration map, faults, dykes, airborne total magnetic intensity, airborne gamma-ray spectrometry data (U, Th, K and total count), and known Cu occurrences. Based on this study, the ANN technique (10 neurons in the hidden layer and LM learning algorithm) is a better predictor of Cu mineralization compared to the GEP method. The results obtained from the P-A plot showed that the ANN model indicates that 80% (vs. 70% for GEP) of the identified copper occurrences are projected to be present in only 20% (vs. 30% for GEP) of the surveyed area. The ANN technique due to capabilities such as classification, pattern matching, optimization, and prediction is useful in identifying anomalies associated with the Cu mineralization.
Seyyed S. Ghannadpour; A. Hezarkhani
Abstract
In several uranium (U) prospecting projects in Iran, particularly Central Iran, the association and enrichment of rare earth elements (REEs) are known as the usual features. Sometimes the association of REEs and U with high economic perspective has caused that the relation between the rare earth and ...
Read More
In several uranium (U) prospecting projects in Iran, particularly Central Iran, the association and enrichment of rare earth elements (REEs) are known as the usual features. Sometimes the association of REEs and U with high economic perspective has caused that the relation between the rare earth and radioactive elements is taken into consideration in other types of mineralization, and if there is any relation, radioactivity will be applied in the exploration of REEs. In the current work, sampling from Baghak anomaly in the Sangan mines is carried out based on the radioactivity and radiation measurement methods (as the optimal sampling pattern). In fact, the goal of this work is to survey the presence or absence of such a relation in a skarn mine, which is a different case study from Central Iran. In the case of presence, this will lead to a new exploration method and sampling pattern for REEs. The mineralogical studies (based on the optical and electronic microscopic observations), statistical investigations, and geochemical analyses are applied in this research work. The results obtained from the statistical studies show that the Baghak anomaly due to involving a significant amount of U, Ce, and La and a high concentration of REEs can be considered as one of the important mines. Spider diagrams and their geochemical investigations include the features that are typical of the subduction-related magmas in the calcalkaline volcanic arcs of the continental active margins. The chondrite-normalized REE pattern shows the enrichment of LREE, and a positive pattern close to flat HREE due to the entry of LREE ions into the allanites network. The mineralogical study results also confirm that REEs (especially Ce) are accumulated as a solid solution in the allanite minerals. Moreover, from the mineralogical, geochemical, and statistical analyses, it can be observed that in addition to the presence of such a relation in the mentioned mineralization (Central Iran mineralizations), there is an acceptable correlation between these elements in the Baghak iron-skarn mineralization. Eventually, it can be said that the idea and introduced method for the exploration of REEs in this work could present a new viewpoint to the decision-makers of this industry.
B. Shokouh Saljoughi; A. Hezarkhani
Abstract
In this paper, we aim to achieve two specific objectives. The first one is to examine the applicability of wavelet neural network (WNN) technique in ore grade estimation, which is based on integration between wavelet theory and Artificial Neural Network (ANN). Different wavelets are applied as activation ...
Read More
In this paper, we aim to achieve two specific objectives. The first one is to examine the applicability of wavelet neural network (WNN) technique in ore grade estimation, which is based on integration between wavelet theory and Artificial Neural Network (ANN). Different wavelets are applied as activation functions to estimate Cu grade of borehole data in the hypogene zone of porphyry ore deposit, Shahr-e-Babak district, SE Iran. WNN parameters such as dilation and translation are fixed and only the weights of the network are optimized during its learning process. The efficacy of this type of network in function learning and estimation is compared with Ordinary Kriging (OK). Secondly, we aim to delineate the potassic and phyllic alteration regions in the hypogene zone of Cu porphyry deposit based on the estimation obtained of WNN and OK methods, and utilize Concentration–Volume (C–V) fractal model. In this regard, at first C–V log–log plots are generated based on the results of OK and WNN. The plots then are used to determine the Cu threshold values of the alteration zones. To investigate the correlation between geological model and C-V fractal results, the log ratio matrix is applied. The results showed that, Cu values less than 1.1% from WNN have more overlapped voxels with phyllic alteration zone by overall accuracy (OA) of 0.74. Spatial correlation between the potassic alteration zones resulted from 3D geological modeling and high concentration zones in C-V fractal model showed that the alteration zone has Cu values between 1.1% and 2.2% with OA of 0.72 and finally have an appropriate overlap with Cu values greater than 2.2% with OA of 0.7. Generally, the results showed that the WNN (Morlet activation function) with OA greater than OK can be can be a suitable and robust tool for quantitative modeling of alteration zones, instead of qualitative methods.
Exploration
N. Mahvash Mohammadi; A. Hezarkhani
Abstract
Identification and mapping of the significant alterations are the main objectives of the exploration geochemical surveys. The field study is time-consuming and costly to produce the classified maps. Therefore, the processing of remotely sensed data, which provide timely and multi-band (multi-layer) data, ...
Read More
Identification and mapping of the significant alterations are the main objectives of the exploration geochemical surveys. The field study is time-consuming and costly to produce the classified maps. Therefore, the processing of remotely sensed data, which provide timely and multi-band (multi-layer) data, can be substituted for the field study. In this study, the ASTER imagery is used for alteration classification by applying two new methods of machine learning, including Random Forest and Support Vector Machine. The 14 band ASTER and 19 derivative data layers extracted from ASTER including band ratio and PC imagery, are used as training datasets for improving the results. Comparison of analytical results achieved from the two mentioned methods confirmed that the SVM model has sufficient accuracy and more powerful performance than RF model for alteration classification in the study area.
Environment
H. Nikoogoftar; A. Hezarkhani
Abstract
In this paper, we aim to achieve two specific objectives. The first one is to examine the applicability of the Artificial Neural Networks (ANNs) technique in ore grade estimation. Different training algorithms and numbers of hidden neurons are applied to estimate Cu grade of borehole data in the hypogene ...
Read More
In this paper, we aim to achieve two specific objectives. The first one is to examine the applicability of the Artificial Neural Networks (ANNs) technique in ore grade estimation. Different training algorithms and numbers of hidden neurons are applied to estimate Cu grade of borehole data in the hypogene zone of porphyry copper-gold deposit, Masjed-Daghi, East Azerbaijan Province (Iran). The efficacy of ANNs in function-learning and estimation is compared with ordinary kriging (OK). As the kriging algorithms smooth the data, their applicability in the pre-processing of data for fractal analysis is not conducive. ANNs can be introduced as an alternative for this kind of problem. Secondly, we aim to delineate the potassic and phyllic alteration regions in the hypogene zone of Cu-Au porphyry deposit based on the estimation obtained by the ANNs and OK methods, and utilize the Concentration-Volume (C-V) fractal model. In this regard, at first, C-V log-log is generated based on the ANN results. The plots are then used to determine the Cu threshold values for the alteration zones. To investigate the correlation between the geological model and C-V fractal results, the log ratio matrix is applied. The results obtained show that Cu values less than 0.38% from ANNs have more overlapped voxels with phyllic alteration zone by an overall accuracy of 0.72. Spatial correlation between the potassic alteration zones resulting from 3D geological modeling and high concentration zones in C-V fractal model show that Cu values greater than 0.38% have more voxels overlapped with the potassic alteration zone by an overall accuracy of 0.76. Generally, the results obtained show that a combination of the ANNs and C-V fractal methods can be a suitable and robust tool for quantitative modeling of alteration zones instead of the qualitative methods.
Exploitation
O. Gholampour; A. Hezarkhani; A. Maghsoudi; M. Mousavi
Abstract
This paper presents a quantitative modeling for delineating alteration zones in the hypogene zone of the Miduk porphyry copper deposit (SE Iran) based on the core drilling data. The main goal of this work was to apply the Ordinary Kriging (OK), Artificial Neural Networks (ANNs), and Concentration-Volume ...
Read More
This paper presents a quantitative modeling for delineating alteration zones in the hypogene zone of the Miduk porphyry copper deposit (SE Iran) based on the core drilling data. The main goal of this work was to apply the Ordinary Kriging (OK), Artificial Neural Networks (ANNs), and Concentration-Volume (C-V) fractal modelings on Cu grades to separate different alteration zones. Anisotropy was investigated and modeled based on calculating the experimental semi-variograms of Cu value, and then the main variography directions were identified and evaluated. The block model of Cu grade was generated using the kriging and ANN modelings followed by log-log plots of the C-V fractal modeling to determine the Cu threshold values used in delineating the alteration zones. Based on the correlation between the geological models and the results derived via C-V fractal modeling, Cu values less than 0.479% resulting from kriging modeling had more overlapped voxels with the phyllic alteration zone by an overall accuracy (OA) of 0.83. The spatial correlation between the potassic alteration zone in a 3D geological model and the high concentration zones in the C-V fractal model showed that Cu values between 0.479% and 1.023%, resulting from kriging modeling, had the best overall accuracy (0.78). Finally, based on the correlation between classes in the binary geological and fractal models of the hypogene zone, this research work showed that kriging modeling could delineate the phyllic (with lower grades) and potassic (with higher grades) alteration zones more effectively compared with ANNs.
Exploitation
H. Nikoogoftar Safa; A. Hezarkhani
Abstract
In this paper, we aim to present a quantitative modeling for delineating the alteration zones and lithological units in the hypogene zone of Masjed-Daghi Cu-Au porphyry deposit (NW Iran) based on the drill core data. The main goal of this work is to apply Ordinary Kriging (OK) and concentration-volume ...
Read More
In this paper, we aim to present a quantitative modeling for delineating the alteration zones and lithological units in the hypogene zone of Masjed-Daghi Cu-Au porphyry deposit (NW Iran) based on the drill core data. The main goal of this work is to apply Ordinary Kriging (OK) and concentration-volume (C-V) fractal model based on Cu grades in order to separate the different alteration zones and lithological units. Initially, anisotropy was investigated and modeled based on calculating the experimental semi-variograms of the Cu values, and the main variography directions were identified and evaluated. Then a block model of the Cu grades was generated using the kriging, and the estimation obtained for OK was applied to the C-V fractal model. The C–V log–log plot based on the estimation method represents the various alteration and lithological zones via threshold values. The comparison and interpretation of the alteration zones and lithological units based on the C–V fractal modeling proved that the method was acceptable and capable of correctly delineating the alteration and lithological units. Regarding the correlation derived from log ratio matrix (used to compare the geological model with the C-V fractal results), it was observed that Cu values less than 0.4% were obtained for OK overlapped voxels with the phyllic alteration zone by an overall accuracy (OA) of 0.737. The spatial correlation between the potassic alteration zones resulting from a 3D geological modeling and the high concentration zones in the C-V fractal model based on OK indicated that the alteration zone contained Cu values greater than 0.4% with OA of 0.791. Also using this method, trustworthy results were obtained for the rock units.
Environment
B. Shokouh Saljoughi; A. Hezarkhani
Abstract
The Shahr-e-Babak district, as the studied area, is known for its large Cu resources. It is located in the southern side of the Central Iranian volcano–sedimentary complex in SE Iran. Shahr-e-Babak is currently facing a shortage of resources, and therefore, mineral exploration in the deeper and ...
Read More
The Shahr-e-Babak district, as the studied area, is known for its large Cu resources. It is located in the southern side of the Central Iranian volcano–sedimentary complex in SE Iran. Shahr-e-Babak is currently facing a shortage of resources, and therefore, mineral exploration in the deeper and peripheral spaces has become a high priority in this area. This work aims to identify the geochemical anomalies associated with the Cu mineralization using the Spectrum–Area (S–A) multi-fractal and Wavelet Neural Network (WNN) methods. At first, the Factor Analysis (FA) is applied to integrate the multi-geochemical variables of a regional stream sediment dataset related to major mineralization elements in the studied area. Then the S–A model is applied to decompose the mixed geochemical patterns obtained from FA and compare with the results obtained from the WNN method. The S–A model, based on the distinct anisotropic scaling properties, reveals the local anomalies due to the consideration of the spatial characteristics of the geochemical variables. Most of the research works show that the capability (i.e. classification, pattern matching, optimization, and prediction) of an ANN considering its successful application is suitable for inheriting uncertainties and imperfections that are found in mining engineering problems. In this paper, an alternative method is presented for mineral prospecting based on the integration of wavelet theory and ANN or wavelet network. The results obtained for the WNN method are in a good agreement with the known deposits, indicating that the WNN method with Morlet transfer function consists of a highly complex ability to learn and track unknown/undefined complicated systems. The hybrid method of FA, S–A, and WNN employed in this work is useful to identify anomalies associated with the Cu mineralization for further exploration of mineral resources.
B. Shokouh Saljoughi; A. Hezarkhani; E. Farahbakhsh
Abstract
The study area, located in the southern section of the Central Iranian volcano–sedimentary complex, contains a large number of mineral deposits and occurrences which is currently facing a shortage of resources. Therefore, the prospecting potential areas in the deeper and peripheral spaces has become ...
Read More
The study area, located in the southern section of the Central Iranian volcano–sedimentary complex, contains a large number of mineral deposits and occurrences which is currently facing a shortage of resources. Therefore, the prospecting potential areas in the deeper and peripheral spaces has become a high priority in this region. Different direct and indirect methods try to predict promising areas for future explorations, most of which are very time-consuming and costly. The main goal of mineral prospecting is applying a transparent and robust approach for identifying high potential areas to be explored further in the future. This work presents the procedure taken to create two different Cu-mineralization prospectivity maps. The first map is created using a knowledge-driven fuzzy technique and the second one by a data-driven Artificial Neural Network (ANN) approach. In this study aim is to investigate the results of applying the ANN technique and to compare them with the outputs of applying the fuzzy logic method. The geo-datasets employed for creating evidential maps of porphyry Cu mineralization include the solid geology map, alteration map, faults, dykes, airborne total magnetic intensity, airborne gamma-ray spectrometry data (U, Th, K and total count), and known Cu occurrences. Based on this study, the ANN technique is a better predictor of Cu mineralization compared to the fuzzy logic method. The ANN technique, due to capabilities such as classification, pattern matching, optimization, and prediction, is useful in identifying the anomalies associated with the Cu mineralization.
Environment
B. Shokouh Saljoughi; A. Hezarkhani; E. Farahbakhsh
Abstract
The most significant aspect of a geochemical exploration program is to define and separate the anomalous values from the background. In the past decades, geochemical anomalies have been identified by means of various methods. Most of the conventional statistical methods aiming at defining the geochemical ...
Read More
The most significant aspect of a geochemical exploration program is to define and separate the anomalous values from the background. In the past decades, geochemical anomalies have been identified by means of various methods. Most of the conventional statistical methods aiming at defining the geochemical concentration thresholds for separating anomalies from the background have limited the efficiency in the areas with complex geological settings. In this work, three methods including the Concentration-Area (C-A) and Spectrum-Area (S-A) fractal models, and the U-statistic method are applied to identify the geochemical anomalies in Avanj porphyry system due to a complex geological and tectonic setting. The results obtained show that the S-A and U-statistic methods present more acceptable outputs than the C-A method. The C-A model acts well to identify the geochemical anomalies within a region including a simple geochemical background; however, the model has limitations within a region including a complex geological setting, where each sub-area is characterized by different geochemical fields. The U-statistic method, by considering the location of sampling points, their spatial relation, and radius of influence for each point in the estimation of anomaly location, overcomes the limitations of the C-A model. The S-A model is a powerful tool to decompose mixed geochemical patterns into a geochemical anomaly map and a varied geochemical background map. The output of this method shows the analysis of geochemical data in the frequency domain, which can provide new exploratory information that may not be revealed in the spatial domain. Eventually, it can be pointed out that the accuracy of the S-A fractal model for determining the thresholds is higher than the other two methods mentioned.
Kh. Maroufi Naghadehi; A. Hezarkhani; K. Seifpanahi Shabani
Abstract
Taknar deposit is located about 28 km to the north-west of Bardaskan in the Khorasan-e-Razavi province, which is situated in the north-eastern part of Iran. This deposit is unique, formed within the Taknar formation in the Ordovician time. As a result, it is of much interest to many researchers working ...
Read More
Taknar deposit is located about 28 km to the north-west of Bardaskan in the Khorasan-e-Razavi province, which is situated in the north-eastern part of Iran. This deposit is unique, formed within the Taknar formation in the Ordovician time. As a result, it is of much interest to many researchers working in this field. By choosing the lithogeochemical study performed to recognize new exploration targets which a new stage in the field. After pre-processing the lithogeochemical data obtained, the distribution maps were obtained for the element anomalies and alteration indices. The ratios of additive composite haloes were used to study the erosion levels in the Taknar area. In order to produce the favorability map, eight information layers were integrated using the simple overlay method, and four new exploration targets were obtained.
