Abstract:
Mineral detection and geological mapping through conventional ground survey methods based on field observation and other geological techniques are tedious, time-consuming and expensive. Hence, the use of remote sensing in mineral detection and lithological mapping has become a generally accepted augmentative tool in exploration. With the advent of multispectral sensors (e.g. ASTER, Landsat and PlanetScope) having suitable wavelength coverage and bands in the Shortwave Infrared (SWIR) and Thermal Infrared (TIR) regions, multispectral sensors, along with common and advanced algorithms, have become efficient tools for routine lithological discrimination and mineral potential mapping. It is with this paradigm in mind that this project sought to evaluate and discuss the detection and mapping of magnetite on the Eastern Limb of the Bushveld Complex, using specialized common traditional and machine learning algorithms. Given the wide distribution of magnetite, its economic importance, and its potential as an indicator of many important geological processes, the delineation of magnetite is warranted. Before this study, few studies had looked at the detection and exploration of magnetite using remote sensing, although remote sensing tools have been regularly applied to diverse aspects of geosciences. Maximum Likelihood, Minimum Distance to Means, Artificial Neural Networks, Support Vector Machine classification algorithms were assessed for their respective ability to detect and map magnetite using the PlanetScope Analytic Ortho Tiles in ENVI, QGIS, and Python. For each classification algorithm, a thematic landcover map was attained and an error matrix, depicting the user's and producer's accuracies, as well as kappa statistics, was derived, which was used as a comparative measure of the accuracy of the four classification algorithms. The Maximum Likelihood Classifier significantly outperformed the other techniques, achieving an overall classification accuracy of 84.58% and an overall kappa value of 0.79. Magnetite was accurately discriminated from the other thematic landcover classes with a user’s accuracy of 76.41% and a producer’s accuracy of 88.66%. Despite the Maximum Likelihood classification algorithm illustrating better class categorization, a large proportion of the mining activity pixels were erroneously classified as magnetite. However, this observation was not merely limited to the Maximum Likelihood classification algorithm, but all image classifications algorithms. The overall results of this study illustrated that remote sensing techniques are effective instruments for geological mapping and mineral investigation, especially in iron oxide mineralization in the Eastern Limb of Bushveld Complex.
