Exploration
Abbas Bahroudi; Salman Farahani
Abstract
The increasing depletion of near-surface ore deposits and the growing complexity of subsurface geological environments have intensified the need for data-driven, three-dimensional frameworks in mineral exploration. This study introduces an integrated 3D ore prospectivity modeling approach that combines ...
Read More
The increasing depletion of near-surface ore deposits and the growing complexity of subsurface geological environments have intensified the need for data-driven, three-dimensional frameworks in mineral exploration. This study introduces an integrated 3D ore prospectivity modeling approach that combines a Deep Autoencoder (DAE) with Monte Carlo Dropout (MCD)-based uncertainty quantification to generate both high-resolution prospectivity predictions and robust estimates of model confidence. A multi-source geoscientific dataset—comprising geology, geochemistry, geophysics, and borehole information—from the Siahcheshmeh intrusion-related gold system in northwestern Iran was voxelized into a unified 3D grid. The multi-scale convolutional DAE architecture effectively learned latent spatial patterns associated with alteration zones, structural intersections, and geophysical anomalies, while 50 stochastic forward passes via MCD enabled the decomposition of aleatoric and epistemic uncertainties. The proposed DAE–UQ model achieved an accuracy of 96.8% and an ROC-AUC of 0.96, outperforming conventional autoencoders, CNNs, and Random Forest models by 4–5%. High-prospectivity regions (>0.72) accounted for only 24% of the model volume yet captured 68% of mineralized borehole intercepts. Uncertainty analysis revealed elevated uncertainty at the margins of data-sparse zones, and excluding high-uncertainty voxels increased prediction accuracy to 98.6%. The spatial correspondence between high-prospectivity voxels, Au–Cu anomalies, silicification halos, and transpressive fault systems validates the geological reliability of the model outputs. Overall, the DAE–UQ framework offers a scalable, uncertainty-aware solution for 3D mineral prospectivity analysis in structurally complex metallogenic terrains. Its strong generalizability and robustness highlight its potential for application to other deposit types and emerging multi-source geoscience datasets.
Exploitation
M. Lotfi; H. Arefi; A. Bahroudi
Abstract
Hyperspectral remote sensing records reflectance or emittance data in a large sum of contiguous and narrow spectral bands, and thus has many information in detecting and mapping the mineral zones. On the other hand, the geological and geophysical data gives us some other fruitful information about the ...
Read More
Hyperspectral remote sensing records reflectance or emittance data in a large sum of contiguous and narrow spectral bands, and thus has many information in detecting and mapping the mineral zones. On the other hand, the geological and geophysical data gives us some other fruitful information about the physical characteristics of soil and minerals that have been recorded from the surface. The Sarcheshmeh mining area located in the NW-trending Uromieh-Dokhtar magmatic belt within Central Iran is mainly of porphyry type, and is associated with extensive hydrothermal alterations. Due to the semi-arid type of climate with abundant rock exposure, this area is suitable for application of remote sensing techniques. In this work, we focus on generating the alteration maps around Cu porphyry copper deposits using the spectral angle mapper algorithm on Hyperion data by applying two filters named reduction to pole and analytical signal on a total magnetic intensity map and generating the Kd map from radiometry data. What is clear is the high importance of applying the adequate pre-processing on Hyperion data because of low signal-to-noise ratio. By comparing the known deposits in the region with the results obtained by applying the mentioned methods, it is revealed that not all the higher K radiometric values are entirely associated with the hydrothermal alteration zones, and in contrast, the potassic alteration map extracted from Hyperion imagery successfully corresponds to the alteration zones around the Sarcheshmeh mining area. Finally, the results particularly obtained from processing the Hyperion data are confirmed by indices of Cu porphyry deposits in the region.
Exploitation
S. Barak; A. Bahroudi; G. Jozanikohan
Abstract
The purpose of mineral exploration is to find ore deposits. The main aim of this work is to use the fuzzy inference system to integrate the exploration layers including the geological, remote sensing, geochemical, and magnetic data. The studied area was the porphyry copper deposit of the Kahang area ...
Read More
The purpose of mineral exploration is to find ore deposits. The main aim of this work is to use the fuzzy inference system to integrate the exploration layers including the geological, remote sensing, geochemical, and magnetic data. The studied area was the porphyry copper deposit of the Kahang area in the preliminary stage of exploration. Overlaying of rock units and tectonic layers were used to prepare the geological layer. ASTER images were used for the purpose of recognition of the alterations. The processes used for preparation of the alteration layer were the image-based methods including RGB, band ratio, and principal component analysis as well as the spectrum-based methods including spectral angel mapper and spectral feature fitting. In order to prepare the geochemical layer, the multivariate statistical methods such as the Pearson correlation matrix and cluster analysis were applied on the data, which showed that both copper and molybdenum were the most effective elements of mineralization. Application of the concentration-number multi-fractal modeling was used for geochemical anomaly separation, and finally, the geochemical layer was obtained by the overlaying of two prepared layers of copper and molybdenum. In order to prepare the magnetics layer, the analytical signal map of the magnetometry data was selected. Finally, the FIS integration was applied on the layers. Ultimately, the mineral potential map was obtained and compared with the 33 drilled boreholes in the studied area. The accuracy of the model was validated upon achieving the 70.6% agreement percentage between the model results and true data from the boreholes, and consequently, the appropriate areas were suggested for the subsequent drilling.
