Electronic Theses and Dissertations (PhDs)

Permanent URI for this collection

https://hdl.handle.net/10539/37976

Browse

Browsing Electronic Theses and Dissertations (PhDs) by Keyword "UCTD"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    A Data Science Framework for Mineral Resource Exploration and Estimation Using Remote Sensing and Machine Learning
    (University of the Witwatersrand, Johannesburg, 2023-08) Muhammad Ahsan, Mahboob; Celik, Turgay; Genc, Bekir
    Exploring mineral resources and transforming them into ore reserves is imperative for sustainable economic growth, particularly in low income developing economy countries. Limited exploration budgets, inaccessible areas, and long data processing times necessitate the use of advanced multidisciplinary technologies for minerals exploration and resource estimation. The conventional methods used for mineral resources exploration require expertise, understanding and knowledge of the spatial statistics, resource modelling, geology, mining engineering and clean validated data to build accurate estimations. In the past few years, data science has become increasingly important in the field of minerals exploration and estimation. This study is a step forward in this field of data science and its integration with minerals exploration and estimation. The research has been conducted to develop a state-of-the-art data science framework that can effectively use limited field data with remotely sensed satellite data for efficient mineral exploration and estimation, which was validated through case studies. Satellite remote sensing has emerged as a powerful modern technology for mineral resources exploration and estimation. This technology has been used to map and identify minerals, geological features, and lithology. Using digital image processing techniques (band ratios, spectral band combinations, spectral angle mapper and principal component analysis), the hydrothermal alteration of potential mineralization was mapped and analysed. Advanced machine learning and geostatistical models have been used to evaluate and predict the mineralization using field based geochemical samples, drillholes samples, and multispectral satellite remote sensing based hydrothermal alteration information. Several machine learning models were applied including the Convolutional Neural Networks (CNN), Random Forest (RF), Support Vector Machine (SVM), Support Vector Regression (SVR), Generalized Linear Model (GLM), and Decision Tree (DT). The geostatistical models used include the Inverse Distance Weighting (IDW) and Kriging with different semivariogram models. IDW was used to interpolate data points to make a prediction on mineralization, while Kriging used the spatial autocorrelation to make predictions. In order to assess the performance of machine learning and geostatistical models, a variety of predictive accuracy metrics such as confusion matrix, a receiver operating characteristic (ROC) curve, and a success-rate curve were used. In addition, Mean Absolute Error, Mean Square Error, and root mean square prediction error were also used. The results obtained based on the 10 m spatial resolution show that Zn is best predicted with RF with significant R2 values of 0.74 (p < 0.01) and 0.7 (p < 0.01) during training and testing. However, for Pb, the best prediction is made by SVR with significant R2 values of 0.72 (p < 0.01) and 0.64 (p < 0.01) for training and testing, respectively. Overall, the performance of SVR and RF outperforms the other machine learning models with the highest testing R2 values. The experimental results also showed that there is no single method that can be used independently to predict the spatial distribution of geochemical elements in streams. Instead, a combinatory approach of IDW and kriging is advised to generate more accurate predictions. For the case study of copper prediction, the results showed that the RF model exhibited the highest predictive accuracy, consistency and interpretability among the three ML models evaluated in this study. RF model also achieved the highest predictive efficiency in capturing known copper (Cu) deposits within a small prospective area. In comparison to the SVM and CNN models, the RF model outperformed them in terms of predictive accuracy and interpretability. The evaluation results have showed that the data science framework is able to deliver highly accurate results in minerals exploration and estimation. The results of the research were published through several peer reviewed journal and conference articles. The innovative aspect of the research is the use of machine learning models to both satellite remote sensing and field data, which allows for the identification of highly prospective mineral deposits. The framework developed in this study is cost-effective and time-saving and can be applied to inaccessible and/or new areas with limited ground-based knowledge to obtain reliable and up- to-date mineral information.
  • No Thumbnail Available
    Item
    Pegmatite investigations in the Karibib district, South West Africa
    (University of the Witwatersrand, Johannesburg, 1963) Roering, Christian
    The outer pegmatitie zone of variable thickness which is essentially a very coarse-grained granite consisting of larger perthite phenocrysts lying in a matrix of albite, quartz and muscovite. The inner portions of this zone may reveal a great enrichment of perthite, so much so, that it may grade into a giant perthite zone, e. g. Rubicon main ore-body; Karlsbrunn close to the Li-bearing ore zones. This outer portion of the pegmatite may also reveal a subdivision into two distinct units: an outermost zone of albite-quartz-muscovite and an inner zone of albite-perthite-quartz-muscovite. This sequence of essentially granitic crystallization is often abruptly broken by the appearance of a zone consisting essentially of cleavelandite with minor quartz and muscovite. This zone is characterized by the appearance of numerous accessory minerals often in economic quantities, e. g. beryl, columbite-tantalite-frondellite, topaz and apatite. The zone is generally of the order 1-5 feet depending on the original size of the pegmatitie and the degree of fractionation. That it is not a late replacement unit is confirmed by observations at Rubicon where corroded crystals of beryl belonging to this zone are found lying in a matrix of lepidolite and albite which is the next unit to form. The lepidolite-albite zone in fact replaces the beryl-bearing zone. The striking symmetry alone of the Rubicon body testifies to this zone preceeding in crystallization sequence the Li-ore zones. The significant fact about this zone is that it marks a distinct break in the crystallization history of the pegmatite, i. e. it marks the change from crystallization of essentially granitic components to the formation of late phase constituents, viz. Li-bearing and associated minerals. It possibly marks the break from magmatic crystallization to late-magmatic conditions when pneumatogenic and even hydrothermal processes begin to operate. The next group of minerals to form are noticeably rich in Li and are frequently associated with sugary albite. The major minerals are petalite, lepidolite and albite, while minor amounts of amblygonite also occur. There is a definite spacial relationship sequence in the formation of these minerals. Petalite crystallizes first and collects in the upper part of this unit generally forming a hood. Amblygonite, albite, quartz, may occur at the same time. Immediately below this petalite hood, and at a somewhat later stage, fine-grained lepidolite crystallizes together with albite and minor quartz. The final phase to form at this general stage is sugary albite which collects at the bottom of the still non-crystalline portion of the magma chamber. The sugary albite phase is able to behave diapirically and can intrude, brecciate, and replace any of the previously crystallized zonal constituents. Each successive stage here can assume corrosive relationships to previously consolidated units. No assessment is made as to the amount of replacement that may take place as the criterion commonly used for such diagnosis are somewhat subjective. During this entire process of complex diffusions and crystallization, silica is apparently being concentrated in the residual fractions of the pegmatite magma. The next zone to form is a cleavelandite-rich rock confined to the quartz core margin. This cleavelandite is able to vein and brecciate and corrode the immediately adjacent lying lepidolite and is often associated with minerals such as beryl, columbite, tantalite, tourmaline, topaz and apatitie. Amblygonite may also belong to this stage of mineralization though in general it tends to be associated close in time with the petalite stage of mineralization. The final stage of the crystallization sequence is the quartz core. Quartz veinlets emanating from the core have been observed to cut across adjacent lepidllite-rich and amblygonite-albite zones. Euhedral crystals of columbite and beryl at the core margin are completely surrounded by quartz. These observations may suggest that quartz, although concentrated in the centre of the dyke, probably existed in some unconsolidated state (e. g. a gel as Brotzen (1959) has suggested). The development of a gas phase at certain stages of the pegmatites consolidation history possibly accounts for the vertical fractionation found in these pegmatites. Finally details of the more important pegmatite minerals are given together with chemical analyses.