The application of Machine Learning in Mineral Processing and Extractive Metallurgy has important benefits in terms of increasing the predictability and controllability of the processes, optimizing their performance, and improving maintenance. However, this application has significant implementation challenges. This paper analyzes these challenges and proposes ways of addressing them. Among the main identified challenges are data scarcity and the difficulty in characterizing abnormal events/conditions as well as modeling processes, which require the creative use of different learning paradigms as well as incorporating phenomenological models in the data analysis process, which can make the learning process more efficient. Other challenges are related to the need of developing reliable in-line sensors, adopting interoperability data models and tools, and implementing the continuous measurement of critical variables. Finally, the paper stresses the need for training of advanced human capital resources with the required skills to address these challenges.

Froth flotation is a widely used method for the concentration of sulfide minerals. The structure of the superficial froth is an indicator of the performance of froth flotation alongside with the operational conditions in which this process is carried out. The aim of this study is to explore how the different operational conditions that can be managed in a flotation plant could directly influence the observable characteristics of the superficial froth. For this purpose, a froth image database was created using a special laboratory cell, designed to emulate the conditions seen in an industrial flotation cell. The database contains 2250 images, distributed in 45 categories; each category has a specific combination of testing conditions, and the main visual characteristics are observed. It also includes a methodology used to assess the quality of each corresponding category.

The characterisation technologies have advanced rapidly in the last decade. From a qualitative observation of minerals with optical microscopy, more quantitative techniques have emerged. Examples are the SEM-based technologies that focus on mineralogical identification at the microscale and the X-ray microtomography systems that allow identifying rock features in three dimensions.

This study proposes a data-driven framework to predict the rock mass-specific fracture energy distributions using microstructural descriptors extracted from SEM-EDS automated characterization images. Ore textures were encoded through unsupervised k-means clustering to identify six representative mineralogical patterns. The resulting cluster proportions were then used as input features for supervised machine learning models, which seek to estimate the parameters of the log-normal distribution (median and standard deviation) adjusted to the experimental fracture energy data. Both models (XGBoost and decision tree regressor) were validated through Leave-One-Out cross-validation and showed high accuracy ($R^2$ of 0.80 and 0.91, respectively) and predict over 85% of the energy distributions matched the experimental ones according to Kolmogorov–Smirnov and Cramér–von Mises tests. The proposed method outperforms traditional empirical approaches by incorporating mineralogical variability and predicting the complete distribution of fracture behavior, representing a step toward more efficient, texture-aware comminution practices.