Machine Learning—A Review of Applications in Mineral Resource Estimation

Abstract

Mineral resource estimation involves the determination of the grade and tonnage of a mineral deposit based on its geological characteristics using various estimation methods. Conventional estimation methods, such as geometric and geostatistical techniques, remain the most widely used methods for resource estimation. However, recent advances in computer algorithms have allowed researchers to explore the potential of machine learning techniques in mineral resource estimation. This study presents a comprehensive review of papers that have employed machine learning to estimate mineral resources. The review covers popular machine learning techniques and their implementation and limitations. Papers that performed a comparative analysis of both conventional and machine learning techniques were also considered. The literature shows that the machine learning models can accommodate several geological parameters and effectively approximate complex nonlinear relationships among them, exhibiting superior performance over the conventional techniques.

Brownfield-related studies in the context of climate change: A comprehensive review and future prospects

“…Overall, the utilization of remote sensing information and neural network modelling has enhanced the accuracy of pollutant measurement, feature extraction, and identification system construction in brownfield recognition, along with improved accessibility to multi-source and multi-temporal data. Certainly, we also need to consider that certain brownfields do not represent vast areas or extensive industrial sites with a multitude of samples suitable for applying geostatistics and Machine Learning techniques [ [105] , [106] ]. In the future, identifying brownfields with specific spatial locations, properties, and characteristics will require further exploration and research into alternative approaches.…”

Machine Learning, Mechatronics, and Stretch Forming: A History of Innovation in Manufacturing Engineering

“…Conventional estimation methods, such as geometric and geostatistical techniques, continue to be widely used. Nevertheless, the latest developments in computer algorithms have empowered researchers to explore the potential of employing machine learning techniques for mineral resource estimation [175]. In the same year, A. Raza published a paper on fault diagnosis techniques in power transmission systems.…”

Integrated Artificial Neural Network and Discrete Event Simulation Framework for Regional Development of Refractory Gold Systems

“…Regardless, a recent surge in research and development over the last few years has shown that ML techniques can be successfully applied to a broad spectrum of the mineral value chain, from greenfield exploration through to production, mine closure and site reclamation. There are a number of review papers available that summarize a variety of ML applications in the mining space (e.g., [49,50,[67][68][69]), including mineral exploration and resource evaluation, strategic mine planning, machine operations and related automation, drilling and blasting optimization and ore beneficiation, among others. However, there is little published work related to the integration of ML techniques into mine-to-mill framework strategies.…”

“…Recent reviews have shown that neural networks and deep learning models account for ~25% of all ML approaches used in the mining space, with support vector machines (23%) and ensemble methods (22%) close behind [67]. ANNs have been especially useful in mineral resource estimation (e.g., [85][86][87]), comprising ~46% of the ML techniques used in this area [68]. Other prominent applications include mineral prospecting and mapping [88,89], geophysics and remote sensing [90,91], ore classification [92,93], drilling and blasting operations [94,95], mining method selection, equipment utilization and production planning [96,97], ore beneficiation and mineral recovery [98,99] and mine site reclamation [100,101], among others.…”