No abstract

Accurate lithological mapping is a crucial juncture for geological studies and mineral exploration. Hyperspectral data provide the opportunity to extract detailed information about the geology and mineralogy of the Earth’s surface. Machine learning (ML) and deep learning (DL) techniques provide an accurate and effective mapping of various types of lithologies in arid and semi-arid regions. This article discusses the use of machine learning algorithms, specifically Support Vector Machines (SVM), one-dimensional Convolutional Neural Network (1D-CNN), random forest (RF), and k-nearest neighbor (KNN), for lithological mapping in a complex area with strong hydrothermal alteration. The study evaluates the performance of the four algorithms in three different zones in the Ameln valley shear zone (AVSZ) area at eastern Kerdous inlier, Moroccan western Anti-Atlas. The results demonstrated that 1D-CNN achieved the best classification results for most lithological units. Additionally, the LK-SVM demonstrated good mapping results compared to the other SVM models, as well as RF and KNN. Our study concludes that the combination of the CNN and HyMap data can provide the most accurate lithologic mapping for the three selected region, with an overall accuracy of ~95%. However, this study highlights the challenges in identifying different lithological units using remotely sensed data due to spectrum similarities induced by similar chemical and mineralogical compositions. This study emphasizes the importance of carefully considering and evaluating ML and DL methods for lithological mapping studies, then recommends the high-resolution hyperspectral data and DL models for accurate results. The implications of this study would be fascinating to exploration geologists for Mineral Prospectivity Mapping (MPM), especially in selecting the most appropriate techniques for highly accurate mineral mapping in metallogenic provinces.

No abstract

<p>Recently, hyperspectral datasets recognized a great interest in mineral exploration studies due to their high accuracy in detecting and mapping hydrothermal alteration minerals. Remote and mountainous regions are hardly accessible by geologists, while the spectral richness of imaging spectroscopy could provide detailed information about geology/mineralogy without having a direct contact with the ground surface. The Kerdous inlier in the Anti-Atlas belt of Morocco is recognized by several occurrences of Cu, Pb, Zn Au, Ag, and Mn mineral deposits. This study is carried out in Eastern Kerdous where the abandoned Idikel mine occurs in order to perform a high-resolution mineral potential map using Gamma-Fuzzy logic approach with twenty HyMap-derived layers. The HyMap-based thematic layers were generated using Directed Principal Component Analysis (DPCA), Relative Absorption Band Depth (RBD), and the Mixture Tuned Matched Filtering (MTMF) for pixel/sub-pixel mineral mapping. The hydrothermally altered regions within the study area reveal several Minerals/Mineral mixtures of hematite, illite, kaolinite, montmorillonite, muscovite, topaz, dolomite, and pyrophyllite. Then, the line density map extracted automatically from the HyMap data image was also integrated. The findings of the image processing were validated using field investigation, petrographic, and XRD analysis. This study demonstrates the great potential of the present research methodology and HyMap as a tool for mineral exploitation in similar areas in Morocco's western Anti-Atlas belt.</p>