Showing papers by "Amin Beiranvand Pour published in 2022"

A Comparative Study of Convolutional Neural Networks and Conventional Machine Learning Models for Lithological Mapping Using Remote Sensing Data

Abstract: Lithological mapping is a critical aspect of geological mapping that can be useful in studying the mineralization potential of a region and has implications for mineral prospectivity mapping. This is a challenging task if performed manually, particularly in highly remote areas that require a large number of participants and resources. The combination of machine learning (ML) methods and remote sensing data can provide a quick, low-cost, and accurate approach for mapping lithological units. This study used deep learning via convolutional neural networks and conventional ML methods involving support vector machines and multilayer perceptron to map lithological units of a mineral-rich area in the southeast of Iran. Moreover, we used and compared the efficiency of three different types of multispectral remote-sensing data, including Landsat 8 operational land imager (OLI), advanced spaceborne thermal emission and reflection radiometer (ASTER), and Sentinel-2. The results show that CNNs and conventional ML methods effectively use the respective remote-sensing data in generating an accurate lithological map of the study area. However, the combination of CNNs and ASTER data provides the best performance and the highest accuracy and adaptability with field observations and laboratory analysis results so that almost all the test data are predicted correctly. The framework proposed in this study can be helpful for exploration geologists to create accurate lithological maps in other regions by using various remote-sensing data at a low cost.

Neuro-Fuzzy-AHP (NFAHP) Technique for Copper Exploration Using Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) and Geological Datasets in the Sahlabad Mining Area, East Iran

Abstract: Fusion and analysis of thematic information layers using machine learning algorithms provide an important step toward achieving accurate mineral potential maps in the reconnaissance stage of mineral exploration. This study developed the Neuro-Fuzzy-AHP (NFAHP) technique for fusing remote sensing (i.e., ASTER alteration mineral image-maps) and geological datasets (i.e., lithological map, geochronological map, structural map, and geochemical map) to identify high potential zones of volcanic massive sulfide (VMS) copper mineralization in the Sahlabad mining area, east Iran. Argillic, phyllic, propylitic and gossan alteration zones were identified in the study area using band ratio and Selective Principal Components Analysis (SPCA) methods implemented to ASTER VNIR and SWIR bands. For each of the copper deposits, old mines and mineralization indices in the study area, information related to exploration factors such as ore mineralization, host-rock lithology, alterations, geochronological, geochemistry, and distance from high intensity lineament factor communities were investigated. Subsequently, the predictive power of these factors in identifying copper occurrences was evaluated using Back Propagation Neural Network (BPNN) technique. The BPNN results demonstrated that using the exploration factors, copper mineralizations in Sahlabad mining area could be identified with high accuracy. Lastly, using the Fuzzy-Analytic Hierarchy Process (Fuzzy-AHP) method, information layers were weighted and fused. As a result, a potential map of copper mineralization was generated, which pinpointed several high potential zones in the study area. For verification of the results, the documented copper deposits, old mines, and mineralization indices in the study area were plotted on the potential map, which is particularly appearing in high favorability parts of the potential map. In conclusion, the Neuro-Fuzzy-AHP (NFAHP) technique shows great reliability for copper exploration in the Sahlabad mining area, and it can be extrapolated to other metallogenic provinces in Iran and other regions for the reconnaissance stage of mineral exploration.

Fusion of Lineament Factor (LF) Map Analysis and Multifractal Technique for Massive Sulfide Copper Exploration: The Sahlabad Area, East Iran

Abstract: Fault systems are characteristically one of the main factors controlling massive sulfide mineralization. The main objective of this study was to investigate the relationship between fault systems and host lithology with massive sulfide copper mineralization in the Sahlabad area, South Khorasan province, east of Iran. Subsequently, the rose diagram analysis, Fry analysis, lineament factor (LF) map analysis and multifractal technique were implemented for geological and geophysical data. Airborne geophysical analysis (aeromagnetometric data) was executed to determine the presence of intrusive and extrusive masses associated with structural systems. Accordingly, the relationship between the formation boundaries and the fault system was understood. Results indicate that the NW-SE fault systems are controlling the lithology of the host rock for copper mineralization in the Sahlabad area. Hence, the NW-SE fault systems are consistent with the main trend of lithological units related to massive sulfide copper mineralization in the area. Additionally, the distance of copper deposits, mines and indices in the Sahlabad area with fault systems was calculated and interpreted. Fieldwork results confirm that the NW-SE fault systems are entirely matched with several massive sulfide copper mineralizations in the area. This study demonstrates that the fusion of lineament factor (LF) map analysis and multifractal technique is a valuable and inexpensive approach for exploring massive sulfide mineralization in metallogenic provinces.

Fusion of Remote Sensing, Magnetometric, and Geological Data to Identify Polymetallic Mineral Potential Zones in Chakchak Region, Yazd, Iran

Abstract: Exploration geologists are urged to develop new, robust, and low-cost approaches to identify high potential zones related to underground/unexplored mineral deposits because of increased depletion of ore deposits and high consumption of basic metal production industries. Fusing remote sensing, geophysical and geological data has great capability to provide a complete range of prerequisite data to accomplish this purpose. This investigation fuses remote sensing data, such as Sentinel-2 and Landsat 7, aerial magnetic geophysical data, and geological data for identifying polymetallic mineralization potential zones in the Chakchak region, Yazd province, Iran. Hydrothermal alteration mineral zones and surface and deep intrusive masses, hidden faults and lineaments, and lithological units were detected using remote sensing, aerial magnetic, and geological data, respectively. The exploratory/information layers were fused using fuzzy logic modeling and the multi-class index overlap method. Subsequently, mineral potential maps were generated for the study area. Some high potential zones of polymetallic mineralization were identified and verified through a detailed field campaign and drilling programs in the Chakchak region. In conclusion, the fusion of remote sensing, geophysical, and geological data using fuzzy logic modeling and the multi-class index overlap method is a robust, reliable, and low-cost approach for mining companies to explore the frontier areas with identical geologic conditions that are alleged to indicate polymetallic mineralization potential.

Targeting local orogenic gold mineralisation zones using data-driven evidential belief functions: the Godarsorkh area, Central Iran

Abstract: ABSTRACT Using GIS-based multi-criteria decision-making techniques, i.e. mineral prospectivity mapping (MPM), specific spatial problems can be solved by combining information from different sources. Orogenic gold mineralisation shows weak exploration signals on the surface that can challenge exploration geologists. This study investigates the ability of a MPM method called evidential belief functions (EBFs) to identify a local orogenic gold mineralisation in the Godaesorkh gold deposit, north of Sanandaj-Sirjan Zone (Central Iran). Several evidential layers such as geological, structural, geophysical, remote sensing, and geochemical layers were generated by applying various processing methods. These layers are integrated to attain a MPM by applying the EBFs based on Dempster-Shafer’s rules. Precise selection of evidential layers and higher number of known mineral occurrences may lead to a higher degree of belief in the mineral prospectivity map. Accordingly, high probability values were correlated with the gold mineralisation in the study area, and three separate areas were identified as promising with N40E and N15W trends. It is concluded that the orogenic gold mineralisation occurred in shear zones, which is mainly controlled by tectonic structures. Consequently, analysing these structures can be considered as a key feature for identifying potential orogenic gold mineralisation zones in the study area.

Detection of alteration zones using the Dirichlet process Stick-Breaking model-based clustering algorithm to hyperion data: the case study of Kuh-Panj porphyry copper deposits, Southern Iran

Abstract: Abstract Detection of hydrothermal alteration zones (HAZs) associated with porphyry copper systems using remote sensing imagery is a crucial stage for discovering high potential zone of ore mineralization. Statistical model-based clustering methods have great potential for automatic and accurate detection of hydrothermal alteration minerals using hyperspectral remote sensing imagery. In this research, the Dirichlet Process based on Stick-Breaking (DPSB) model-based clustering algorithm was implemented to hyperion remote sensing imagery to discriminate HAZs associated with the Kuh-Panj porphyry copper deposit, south, Iran. The DPSB clustering algorithm was implemented and subsequently compared with the k-means algorithm, CLARA clustering, hierarchical clustering, Gaussian finite mixture model (GFMM), Gaussian model for high-dimensional (GMHD) and spectral clustering as well as spectral angle mapping (SAM). Results derived from the DPSB model-based clustering algorithm show 88.6% accuracy in distinguishing propylitic, argillic, advanced argillic, propylitic-argillic and phyllic alteration zones. The DPSB algorithm can be broadly implemented to hyperspectral remote sensing imagery for detecting alteration zones associated with porphyry systems.

Structural Analysis and Paleostress Evolution in the Imiter Silver Mining Region, Eastern Anti Atlas, Morocco: Implications for Mineral Exploration

Abstract: Development and concentration of many ore deposits at the regional and district scales closely depend on structural geology, especially in polydeformed basements. The superposition of many deformation periods highlights the complexity of the structural context and expected potential location of mineralization zones. The formation and concentration of hydrothermal ore deposits is highly dependent on structural controls. On the NE flank of the Saghro massif (Eastern Anti-Atlas, Morocco), the Imiter silver mining region has been affected by multiple tectonic events since the Precambrian and throughout the Phanerozoic. In this investigation, a structural analysis of the different geological units revealed multi-stage deformation, beginning with the late Pan-African-Cadomian event, and ending with the last Cenozoic exhumation of the area. At least eight tectonic regimes have been identified. The Imiter basement, formed by the Cryogenian-early Ediacaran “flysch-like” Saghro Group, has been folded in low-grade metamorphic conditions, followed by an ENE-WSW brittle compressive event. These deformations occurred before to the early Ediacaran during the compressional and/or transpressional late Pan-African-Cadomian events (600–580 Ma). The unconformably overlaying deposition of the late Ediacaran Ouarzazate Group takes place in a WNW-ESE extensional setting and then involved in a NNW-SSE compressional event that occurred concurrently with a regional exhumation and erosion stages. A similar extensional event appears to have controlled the middle Cambrian sedimentation, the oldest Paleozoic deposits in this area. During the late Carboniferous, Variscan shortening was recorded by NW-SE transpressional deformation responsible for combined dextral strike-slip and southward thrusts. The Imiter silver mining region is part of the Moroccan Sub-Meseta Zone along with Paleozoic inliers of the Skoura and Tamlelt on the southern side of the High Atlas. The Mesozoic evolution began with the Late Triassic NNW-SSW transtensional tectonic regime with a northeast trending CAMP (Central Atlantic Magmatic Province) dyke during the Pangea breakup. Ultimately, the Imiter silver mining region experienced NNW-SSE Atlasic shortening during the uplift of the adjacent High Atlas. Over time, the direction of implemented tectonic stress and its effect on various geological units can elucidate the relationship between tectonism and hydrothermal silver mineralization in the Imiter region. In conclusion, structural analysis and investigation of paleostress development can be one of the most important factors for successful exploration plan and resource recovery in the Imiter region. An analysis of geological structures in determining feasible mineralization zones is crucial for future safe mining operation in the study area and can be extrapolated to other ore mining regions.

Assessment of the TsHARP method for spatial downscaling of land surface temperature over urban regions

Abstract: Nowadays, acquiring high spatial and temporal land surface temperature (LST) is one of the significant factors in urban climate studies. This study aims to assess the sharpening thermal imagery (TsHARP) method, which is developed for determining the LST in urban regions. Whereas the original TsHARP method correlates the Normalized Difference Vegetation Index (NDVI) with the LST, the current study seeks to evaluate the performance of the TsHARP method by correlating between the LST and NDVI over urban areas. Additionally, it is intended to investigate the relationship between the impervious surfaces (IS) and LST. At this point, the Advanced Spaceborne Thermal Emission and Reflection Radiometer ASTER image of the year 2003 was used to retrieve the IS as well as the LST of the Kuala Lumpur city, Malaysia. To retrieve the main LST, IS and NDVI, ASTER Level1B data were used. On the other hand, ASTER land surface temperature products (AST08) was utilized to evaluate the downscaled LST (DLST) image. With selection of the ~1/4 of the pixels with lowest coefficient of variation (CV), the LST has more correlation with the IS in comparison with the NDVI, while the correlation between the IS and LST was increased in this study. The IS index illustrates the most optimal correlation for the urban LST (R2 = 0.59). Furthermore, the TsHARPIS-based method depicted a good correlation between the DLST and the ASTER LST product (RMSE = 1.5 °C, R2 = 0.83) compared to the NDVI (RMSE = 4 °C, R2 = 0.73). Consequently, it is found that the application of TsHARPIS-based method to ASTER remote sensing data is a robust/low-cost approach for spatial downscaling of the LST over urban regions.

Editorial for Advances in Geological and Geotechnical Engineering Research

Abstract: Recently, the name of Journal of Geological Research has been changed to “Advances in Geological and Geotechnical Engineering Research’’.

Alteration Detections Using ASTER Remote Sensing data and Fractal Geometry for Mineral prospecting in Hemich Area, NE Iran

Abstract: Nowadays, remote sensing studies are considered as one of the best methods in mineral prospecting. Considering that most of the important deposits of the world, such as porphyry copper and epithermal gold deposits are widely associated with alteration zones. Identification of the alterations can be a significant exploratory guide for these types of deposits. The spectral difference between altered and unaltered rocks is the most important way of detecting alteration areas and thus exploring ore deposits by means of remote sensing. In this research, ASTER image was used to identify alteration areas in the Hemich Area, NE Iran. Geometric corrections were made on images in order to reduce the spatial errors caused by displacements and distortions related to sensors. Radiometric corrections were also applied to reduce the spectral errors caused by atmospheric effects. Subsequently, mineral prospectus areas were identified using false-color composite, band ratio, and principal components analysis. Since the results of these methods are grayscale images, a concentration-area fractal method was used to distinguish the regions containing the alterations. Using the results of these methods, some areas with the highest probability of mineralization were discovered, which were compatible with the ground control points.

DPSB model-based clustering algorithm for mineral mapping in hyperspectral imagery

Abstract: The Dirichlet Process based on Stick-Breaking (DPSB) model-based clustering algorithm was instigated to Hyperion remote sensing imagery to map alteration minerals related to porphyry copper deposit. The DPSB clustering results were evaluated using Normalized Information Distance (NID), Normalized Mutual Information (NMI) and Modified adjusted Rand index (MARI) methods. Comparing the DPSB results with the geological map of the study area reveals the MARI of 0.2253, NMI of 0.1799 and MARI of 0.2253, respectively. To verify the extent of propylitic, argillic, advanced argillic, propylitic-argillic and sericite alteration zones associated with porphyry copper deposit, a total number of 24 rock samples were measured by a SVC XHR-1024i field portable spectroradiometer. Results derived from the DPSB model-based clustering algorithm show high accuracy in distinguishing propylitic, argillic, advanced argillic, propylitic-argillic and sericite alteration zones. It is advocated that the DPSB model-based clustering algorithm can be broadly implemented to hyperspectral and multispectral remote sensing data for detecting alteration zones associated with porphyry mineralization systems in other metallogenic provinces around the world.