Electronic Theses and Dissertations (PhDs)

Permanent URI for this collectionhttps://hdl.handle.net/10539/37976

Browse

Start date: 2023Has files: Yes

Search Results

Now showing 1 - 3 of 3
  • 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.
  • Thumbnail Image
    Item
    Application of derivative techniques to improve the forecasting of price volatility of copper, gold and platinum metals
    (2024) Veriyadi, Veriyadi
    This research investigates the forecasted price volatility of copper, gold and platinum metals based on the selected companies; Palabora Copper Mining Ltd, AngloGold Ashanti Ltd, Gold Fields Ltd, Sibanye-Stillwater, Anglo Platinum Ltd and Impala Platinum Ltd. In responding to the latter sentence, single price volatilities are dual volatilities, where dual volatilities comprise of financial and technical variables. The selected firms either have global operations or they are subsidiaries of global companies. Dual volatility is computed using a Sample Correlation Coefficient and in order to explore the dual volatility, this research introduces three hypotheses. The first hypothesis uses a Decision Tree Analysis to test dual volatility based on financial and technical variables (e.g., mineral commodity price, metal grade, operating cost and production rate) in improving the forecasting of price volatility of copper, gold and platinum metals. For validation, the first hypothesis uses the Markov-Regime Switching Model. The results of this hypothesis illustrate that dual volatilities are more accurate and robust than price only volatilities. Then, the second hypothesis examines dual volatility using a GBM model. This hypothesis tests dual volatility; which is computed based on financial and technical variables (e.g., oil price, copper price, oil production and consumption, copper production and consumption; and the exchange rate from U.S.$ to ZAR and gold and platinum price data). The chosen variables that affect the dual volatility are examined using a Multiple Regression Model and that model confirms that those variables are independent in principle. Finally, the third hypothesis estimates future profits based on a binomial tree, which has risk-neutral probabilities based on dual volatility using mineral commodity price, metal grade, operating cost and production rate. The results of risk-neutral probabilities using dual volatility are less optimal than a mineral commodity price volatility due to not accounting for the mean of logarithmic returns. The robustness test uses the VAR model, which indicates that the profits react differently to different shock stages from revenues, risk-free interest rates and profits. In conclusion, dual volatility can improve future price forecasting performance because duality is underpinned by different variables, which include independent variables from the global commodity markets. The forecasting performance improvement from dual volatility in predicting the future price can be shown by the lower value of the Root Mean Square Error and Mean Absolute Percentage Error results than a mineral commodity price volatility. The findings of this research apply to copper, gold and platinum metals for mining around the globe.
  • Thumbnail Image
    Item
    Analysis of the developmental potential of artisanal and small-scale mining: a strategy for South Africa
    (2024) Twala, Pontsho Francinah
    The mining industry remains central to the socio-economic development of mineral economies. While this is the case, most African countries have been struggling to translate the benefits of mining into positive developmental outcomes. This has been attributed to several factors including the failure to leverage opportunities from the Artisanal and Small-Scale Mining (ASM) sector which has been growing in most countries. As is the case in other African countries, the mining industry continues to play a considerable role in South Africa’s economy. The industry is expected to contribute significantly to the country’s socio-economic agenda which aims to eradicate poverty and inequality by 2030. Despite the positive outlook, the performance of the industry has been declining resulting in the government identifying a series of interventions aimed at reviving the industry’s activities. Amongst these is the formalisation of the ASM which has been earmarked for job creation and poverty alleviation. The objectives of the Thesis were to establish the developmental potential of ASM in the country, and subsequently develop a strategy framework aimed at enabling the sector to contribute to the mining industry and national development plan. The study was conducted using multiple case studies with data collected and analysed using multiple methods. The major finding from the study is that the ASM sector has the potential to contribute towards the country’s development priorities. This is taken from the evidence that shows a direct link between the sector’s activities and the country’s socio-economic landscape. It was established that the main drivers of ASM are socio-economic challenges in the country, mainly growing unemployment and poverty levels. To this end, ASM is playing a role in providing livelihoods to country’s population is that most affected by poverty and unemployment. As a livelihood strategy, ASM has improved the poverty status as well as the living standards of those that participate in its activities. The evidence from the study revealed that most of the miners measure above the country’s subsistence level and can provide for themselves and their families. The benefits of the sector also extend to communities and overall, these can be linked to several objectives as captured in the country’s development plan. The conclusion from the study is that the developmental potential of ASM can only be leveraged if the challenges in the sector are addressed, and these encompass issues relating to the regulation of the sector, mining land and mineral resources; value chain constraints, and related support, responsible practices, institutional arrangements, and ASM stakeholder relationships.