Spatial prediction of orebody characteristics can often be challenging given the commonly complex geological structure of mineral deposits. For example, a high nugget effect can strongly impact variogram modelling. Geological complexity can be caused by the presence of structural geological discontinuities combined with numerous lithotypes, which may lead to underperformance of grade estimation with traditional kriging. Deep learning algorithms can be a practical alternative in addressing these issues since, in the neural network, calculation of experimental variograms is not necessary and nonlinearity can be captured globally by learning the underlying interrelationships present in the dataset. Five different methods are used to estimate an unsampled 2D dataset. The methods include the machine learning techniques Support Vector Regression (SVR) and Multi-Layer Perceptron (MLP) neural network; the conventional geostatistical methods Simple Kriging (SK) and Nearest Neighbourhood (NN); and a deep learning technique, Convolutional Neural Network (CNN). A comparison of geologic features such as discontinuities, faults, and domain boundaries present in the results from the different methods shows that the CNN technique leads in terms of capturing the inherent geological characteristics of given data and possesses high potential to outperform other techniques for various datasets. The CNN model learns from training images and captures important features of each training image based on thousands of calculations and analyses and has good ability to define the borders of domains and to construct its discontinuities.

Bubble size measurement is a vital part of flotation system analysis and diagnostics. This work evaluates a commercial camera probe as a novel method for in situ bubble size measurement. This device is compared to the conventional Anglo Platinum Bubble Sizer (Stone Three^TM). It was found that, in laboratory applications, the in situ bubble size analysis technology appears to be a more user-friendly and reliable option for determining bubble size in flotation, whereas the Anglo Platinum Bubble Sizer is more applicable for full scale industrial work. This probe was then used to conduct a rigorous comparison of the behavior of different frother chemistries at a variety of background solution ionic strength conditions. The critical coalescence concentrations and the minimum Sauter mean bubble diameters were determined. Five frothers were compared in terms of their ability to reduce bubble size and sensitivity to salinity. In order to adjust plant recipe and control strategy accordingly, it is recommended that the plant would need to use less frother during periods of the high salinity of process water to achieve the minimum Sauter mean bubble size.

This study explores the application of machine learning techniques for predicting generic mill liner wear in semi-autogenous grinding (SAG) mills used in mineral processing. Various models were developed and compared using data from 143 liner measurements across 36 liner cycles from ten different SAG mills. The research initially focused on individual mill modeling, employing simple linear regression, first-order kinetic approach, Multiple Linear Regression (MLR), tree-based methods (Decision Trees, Random Forests, XGBoost), and Multilayer Perceptron (MLP). Results showed that simple linear regression provided sufficient accuracy, with other methods only slightly improving performance. This study then developed a combined model using data from multiple mills. MLR and advanced machine learning techniques were applied for this generic model, with XGBoost emerging as the most successful. In the interpolation scenario involving a mill similar to those in the training data, the XGBoost model achieved a mean absolute percentage error (MAPE) of 5.27%. For the extrapolation scenario, with a mill larger than those in the training set, the MAPE increased slightly to 6.12%. These results demonstrate the potential of machine learning approaches in creating effective generic models for mill liner wear prediction. However, this study also highlights the potential for improving predictive models by incorporating additional key parameters such as liner and ball material properties.

As a versatile metal, nickel will experience increased demand in the coming years, with a specific focus on its importance in the battery industry and its role in achieving net-zero emissions. Recognizing the need to ensure sustainable resource management, this study analyses the flow dynamics of nickel’s supply and demand by employing a modelling approach. This is done with a focus on understanding how recycling can contribute to meeting the growing nickel demand. By considering the interaction between mining production, product applications, and recycling rates, this study contributes to a better understanding of the long-term prospects for meeting the nickel demand. It can assist policymakers, industry stakeholders, and investors in making informed decisions regarding resource management and developing sustainable practices in the nickel industry. The results revealed that mining would still play an important role in the supply of nickel for at least the next 40 years. Nickel mining and recycling practices are sufficient to meet future nickel demand if sufficient recycling practices are (rapidly) implemented. Modelling results show that nickel recycling will account for 90% of the total demand (primary nickel mining accounts for the remaining 10%) between the years 2062 and 2096.