article · Minerals
Accurate geological mapping is critical for mineral exploration, particularly in arid and semi-arid terrains. This research assesses machine learning and deep learning algorithms applied to airborne HyMap hyperspectral imagery for lithological mapping across three zones in the Ameln valley shear zone within Morocco's western Anti-Atlas. The tested algorithms comprise one-dimensional convolutional neural networks, support vector machines, random forest, and k-nearest neighbour. Among these approaches, the one-dimensional convolutional neural network yielded the highest performance, achieving an overall classification accuracy of approximately 95 percent. Certain support vector machine models also performed well compared to random forest and k-nearest neighbour. While spectral similarities among rock units with comparable mineral compositions remain challenging, the findings demonstrate that combining deep learning with high-resolution hyperspectral imagery significantly improves geological surface mapping in complex hydrothermal environments.
Locating valuable mineral resources traditionally requires extensive, costly fieldwork in remote terrains. Utilising airborne hyperspectral imaging alongside advanced computer models allows geologists to identify distinct rock types accurately from above. This capability accelerates exploration, lowers survey expenses, and improves baseline geological data in semi-arid and arid landscapes, facilitating targeted prospecting in mineral-rich provinces.
This methodology is applied and tested for mineral exploration workflows and mineral prospectivity mapping. Exploration geologists and mining sector companies can deploy this combination of airborne HyMap hyperspectral data and one-dimensional deep learning models to identify prospective metallogenic zones. While validated on local survey zones with high accuracy, operational commercial adoption would require integrating these classification pipelines into routine exploration software and handling broader datasets across diverse geological environments.
AI-generated from the published abstract. Always read the original work before citing.
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.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.3390/min13060766
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
