Exploration
Reza Moezzi nasab; Alireza Arab Amiri; Abolghasem Kamkar-Rouhani; Meysam Davoodabadi Farahani
Abstract
Mineral prospectivity modeling in structurally complex and vertically heterogeneous geological systems requires analytical frameworks capable of capturing nonlinear feature interactions and depth-dependent variability. This study evaluates the predictive performance of a deep self-attention neural network ...
Read More
Mineral prospectivity modeling in structurally complex and vertically heterogeneous geological systems requires analytical frameworks capable of capturing nonlinear feature interactions and depth-dependent variability. This study evaluates the predictive performance of a deep self-attention neural network within a fully 3D mineral prospectivity modeling framework applied to the Chah-Mousa copper deposit, Iran. The modeling domain was discretized into twenty-one independent elevation levels to assess depth-consistent predictive behavior. Model performance was evaluated using ROC–AUC analysis, confusion-matrix-derived metrics, and success-rate curve assessment. The deep self-attention model achieved a mean ROC–AUC of approximately 0.83, indicating strong discriminative capability between mineralized and non-mineralized domains. Averaged across elevation slices, classification performance remained stable (Accuracy ≈ 0.83, Precision ≈ 0.69, Recall ≈ 0.75, F1-score ≈ 0.72), demonstrating vertical generalization and resistance to shallow overfitting. Success-rate analysis revealed that more than 50% of known mineralized occurrences are concentrated within the top 10% of predicted prospectivity areas, confirming strong ranking efficiency for exploration prioritization. The probabilistic outputs exhibit spatial coherence aligned with structural corridors and alteration zones, indicating that the attention mechanism effectively captures nonlinear geological relationships. The results demonstrate that deep self-attention architectures provide statistically robust, depth-consistent, and operationally meaningful predictions for 3D mineral exploration targeting in structurally controlled copper systems.
Environment
Amirmahmood Razavian; Alireza Arab Amiri; Abolghasem Kamkar Rouhani; Meysam Davoodabadi Farahani
Abstract
Mining activities cause environmental pollution. Satellite remote sensing is considered an effective strategy for monitoring pollution, as other direct methods of testing soil pollution levels are often costly and face accessibility challenges in certain areas. Unlike optical sensors, radar systems can ...
Read More
Mining activities cause environmental pollution. Satellite remote sensing is considered an effective strategy for monitoring pollution, as other direct methods of testing soil pollution levels are often costly and face accessibility challenges in certain areas. Unlike optical sensors, radar systems can capture data in all weather conditions and operate around the clock. However, radar systems do not display details and borders of zones and lack multispectral data collection capability. Consequently, combining various characteristics of optical images and radar data offers a comprehensive approach to monitoring pollution. Given these pros and cons, a combination of optical and radar images from the Sentinel satellite was employed in this study to identify surface and physical pollution areas caused by mining activities. The proposed method is a combination of Curvelet Transform, Simple Linear Iterative Clustering, Principle Components Analysis, and integration of radar and optical results using a statistical based clustering scheme, which allows the detection of contaminated zones. This research benefits from several innovative strategies, such as the separate processing and integration of optical and radar images, the simultaneous application of the curvelet transform and principle component analysis, and the utilization of two distinct clustering methods. Finally, the results obtained from radar and optical images of the Damghan region in Semnan province, Iran, on a 1 to 100.000 scale showed the proposed methodology can segment the contaminated zone caused by the eastern Alborz coal preparation plant through soil pollution modelling.
