School of Mining Engineering (ETDs)

Permanent URI for this communityhttps://hdl.handle.net/10539/37974

Browse

Filters

2023 - 20242

Settings

Start date: 2020Subject: search.filters.subject.Machine Learning

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Improving grade estimation using machine learning: a comparative study of ordinary kriging against machine learning algorithms
    (University of the Witwatersrand, Johannesburg, 2024) Akpabio, Aniekan
    This study investigated the efficiency of machine learning (ML) methods in the accurate prediction of ore grades, placing them in direct comparison with the established Ordinary Kriging (OK) methodology, a mainstay in geostatistical analysis. Utilising a dataset from a complex platinum group elements (PGE) deposit, the research assessed a suite of ML algorithms—namely, Random Forest (RF), Decision Trees (DT), Support Vector Regression (SVR), and particularly 𝑘- Nearest Neighbours (𝑘NN). The latter is highlighted for its adeptness in assimilating spatial data correlations intrinsically, echoing the insights from Nwalia's analytical explorations. The research engages with detailed swath plot analyses, comparative metric evaluations, and a nuanced understanding of spatial continuity, to illustrate the distinct advantages and operational competencies of the models. 𝑘NN, with its reliance on local data proximities and non-parametric nature, alongside RF, with its ensemble-based approach, emerged as capable in point estimate predictions. These models adeptly delineated local grade variations, demonstrating a high degree of reliability to the observed data and outperforming the OK model in both precision and accuracy. Further, the study examined block estimate predictions, a cornerstone in practical mining and resource estimation, where both 𝑘NN and RF demonstrated a commendable ability to generalise predictions over larger spatial extents. This translates into significant potential for enhancing mineral resource estimation processes, tailoring them to the granular specifics of a given ore body, and refining block model accuracy to inform more strategic mining operations. While the results endorse the ML methodologies as robust alternatives to traditional geostatistical techniques, the research also highlights the nuanced nature of these predictions. Factors such as the ore body's heterogeneity, the appropriateness of the variogram model, and the interplay between prediction scale and algorithmic performance are examined, offering a critical lens through which the suitability of each method is assessed. iv The research suggests that while some models like LR and SVR are bounded by linear assumptions and hyperparameter sensitivities, non-linear models such as DT and RF can innately navigate the complex, multifaceted layers of geological data. The comprehensive evaluation extends to propose a novel set of performance metrics designed to capture the intricacies of grade prediction, thereby aligning closely with the operational demands and decision-making processes in the mining industry.
  • 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.