Remote Sensing-Based Prospectivity Maps Generation for Exploration of Minerals in Pakistan Using Machine Learning Techniques

Suleman Ehsin ()
Additional contact information
Suleman Ehsin: University of Engineering and Technology Peshawar

International Journal of Innovations in Science & Technology, 2023, vol. 5, issue 4, 677-693

Abstract: The objective of this study is to generate and compare prospectivity maps that show the presence of Limestone in a specific area using remotely sensed data and machine learning techniques, in order to determine the most precise map that accurately depicts the presence of Limestone in that area. Remotely sensed data often utilize machine learning techniques to identify mineral formations and map geological features. Furthermore, machine learning techniques can also be used to generate prospectivity maps for mineral exploration. In this study, we utilized band ratios and principle component analysis (PCA) in conjunction with machine learning techniques to effectively identify Limestone formations and generate prospectivity maps for Limestone exploration using satellite imagery. Support Vector Machines (SVM) and Neural Networks (NN) were the machine learning techniques utilized on multispectral imagery from Sentinel-2 and Landsat-8. To assess the accuracy of the identification, the confusion matrix and kappa coefficient were employed. It was determined that the accuracy of the Neural Networks (NN) techniques was significantly better than the accuracy of the Support Vector Machines (SVM) techniques. The Neural Networks (NN) achieved an accuracy of 94.92% with a kappa value of 0.929, whereas the Support Vector Machine (SVM) had a maximum accuracy of 88.39% with a kappa value of 0.845. These high levels of accuracy and kappa coefficient values suggest that these machine techniques hold great potential for geological mapping and mineral exploration. The generated prospectivity maps can assist geologists and mining companies in identifying areas with a high potential for Limestone exploration, thereby reducing exploration costs and time.

Keywords: Machine Learning; Remote Sensing; Minerals; Multispectral; Prospectivity Maps (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journal.50sea.com/index.php/IJIST/article/view/576/1141 (application/pdf)
https://journal.50sea.com/index.php/IJIST/article/view/576 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:abq:ijist1:v:5:y:2023:i:4:p:677-693

Access Statistics for this article

International Journal of Innovations in Science & Technology is currently edited by Prof. Dr. Syed Amer Mahmood

More articles in International Journal of Innovations in Science & Technology from 50sea
Bibliographic data for series maintained by Iqra Nazeer ().