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.
Exploration
Hossein Mahdiyanfar; Mirmahdi Seyedrahimi-Niaraq
Abstract
In this investigation, the hybrid approach of wavelet transforms and fractal method named Wavelet-Fractal model has been utilized for geochemical contamination mapping as a novel application. For this purpose, the distribution maps of pollutant elements were transformed to the position-scale domain using ...
Read More
In this investigation, the hybrid approach of wavelet transforms and fractal method named Wavelet-Fractal model has been utilized for geochemical contamination mapping as a novel application. For this purpose, the distribution maps of pollutant elements were transformed to the position-scale domain using two-dimensional discrete wavelet transformation (2DDWT). The Symlet2 and Haar mother wavelets were applied for two-dimensional signal analysis of elemental concentrations of As, Pb, and Zn based on soil samples taken from the Irankuh mining district, Central Iran. The Symlet2 and Haar wavelet coefficients of approximate and detail components were obtained at one level frequency decomposition using 2DDWT. The wavelet coefficients of approximate component (WCAC) were modeled using a fractal method for delineating the geochemical contamination populations of toxic elements. Based on the results of wavelet-fractal models, the As, pb, and Zn were classified into three and four populations. Two areas contaminated with metals have been found in the district. These areas are within the limit of mining operations and its surroundings. The wavelet-fractal proposed model has been able to separate environmental areas contaminated with toxic metals accurately. Anomalously intense pollution has spread to one kilometer outside the mining operation limit. This dispersion in the case of Pb and Zn elements is well seen in the geochemical map prepared with the Haar class.
Exploration
Mojtaba Bazargani Golshan; Mehran Arian; Peyman Afzal; Lili Daneshvar Saein; Mohsen Aleali
Abstract
The aim is to use the Concentration-Volume (C-V) fractal model to identify high-quality parts of coal seams based on sulfur and ash concentrations. In the K1 and K7 coal seams in the North Kochakali coal deposit, 5 and 6 different populations of ash and sulfur content were obtained based on the results. ...
Read More
The aim is to use the Concentration-Volume (C-V) fractal model to identify high-quality parts of coal seams based on sulfur and ash concentrations. In the K1 and K7 coal seams in the North Kochakali coal deposit, 5 and 6 different populations of ash and sulfur content were obtained based on the results. According to this model, sulfur and ash concentrations below 1.81% and 33.1% for the K7 seam, and below 4.46% and 37.1% for the K1 seam, respective base on Russian standard for ash and high sulfur content of North Kochakali coals were considered as appropriate values. In order to identify the high-quality parts of K1 and K7 coal seams, plans at different depths were used based on the C-V fractal model. Plans at different depths suggests that the southern part of the K1 seam and the northern part of the K7 seam have the highest-quality based on sulfur and ash concentrations, which should be considered in the extraction operation. The logratio matrix was used to compare the results of the C-V fractal model with the geological data of pyrite veins and coal ash. This matrix indicates that sulfur content above 3.8% for the K7 seam and above 4.41% for the K1 seam have good and very good correlation with pyritic veins of geological data, respectively. There are good overall accuracy (OA) values in the correlation between parts of the seam with ash concentration above 37.1% and 45.7% for the K1 and K7 seams, respectively, and the coal ash obtained from the geological data.
Exploration
Hossein Mahdiyanfar; Mirmahdi Seyedrahimi-Niaraq
Abstract
The primary purpose of this investigation is contamination mapping in surrounding areas of Irankuh Pb–Zn mine, located in central Iran, using an integrated approach of principal component analysis (PCA) with the Concentration-Area (C-A) and Power Spectrum-Area (S-A) fractal models. PCA categorized ...
Read More
The primary purpose of this investigation is contamination mapping in surrounding areas of Irankuh Pb–Zn mine, located in central Iran, using an integrated approach of principal component analysis (PCA) with the Concentration-Area (C-A) and Power Spectrum-Area (S-A) fractal models. PCA categorized the 45 elements into eight principal components. Component 2, containing the toxic elements of Pb, Zn, As, Mn, Cd, and Ba, was identified as the contamination factor. This multivariate contamination factor was modeled using the C-A and S-A fractal methods (in spatial and frequency domains) to delineate pollution areas. Modeling of PCA data using the C-A fractal method showed four main populations for the contamination factors. Two populations with higher fractal dimensions are associated with contamination from mining activities or anthropogenic effects. Low fractal dimensions are considered the background population, which has not been affected or is less affected by these activities. Five geo-chemical populations were obtained for contamination factors using the S-A fractal modeling of PCA in the frequency domain. Therefore, various geo-chemical populations were achieved using geo-chemical filtering and two-dimensional inverse Fourier transformation. The geo-chemical populations related to classes 2, 3, and 4 containing intermediate frequency signals showed the pollution anomaly. The spatial distribution of pollutant geo-chemical signals exhibits excellent conformity with the mining operation limit and tailing dam location as pollutant sources. The results indicate that the elements Pb, Zn, Cd, and As have significant values in the surrounding soils rather than their concentrations in the earth’s crust. The results demonstrate that the S-A fractal models can more precisely delineate the environmental anomaly than the C-A fractal model, especially in intermediate frequency populations.
