Search

Machine learning (ML) is increasingly being leveraged by the mining industry to understand how rock properties vary at a mine site. In previously published work, the rock type, granodiorite, was predicted with high accuracy by the random forest (RF) ML method at the Erdenet copper mine in Mongolia. As a result of the optimistic results (86% overall success rate), this paper extended the research to determine if ML would be successful in modeling rock domains. Rock domains are groups of rocks that occur together. There were two additional goals. One was to determine if the variograms could predict or help understand how ML methods would perform on the data. The second was to determine if 2D modeling would perform well given the disseminated nature of the deposit. ML methods, multilayer perceptron (MLP), k-nearest neighborhood (KNN) and RF, were applied to model six rock domains, D0–D5, in 2D and 3D. Modeling performance was poor in 2D. Prediction performance accuracy was high in 3D for the domains D1 (92–94%), D2 (94–96%) and D4 (85–98%). Note that the domains D1 and D2 together constituted about 80% of the samples. Conclusions drawn in this paper are based on the results of 3D modeling since 2D modeling performance was poor. Prediction performance appeared to depend on two factors. It was better for a domain when the domain was not a minuscule proportion of the sample. It was also better for domains whose indicator semi-variogram (ISV) range was high. For example, though D4 only contributed 15% of the samples, the range was high. MLP did not perform as well as KNN and RF, with RF performing the best. The hyperparameters of KNN and RF suggested that performance was best when only a small number of samples were used to make a prediction. One overall summary conclusion is that the two most important domains, D1 and D2, could be predicted with high accuracy using ML. The second summary conclusion is that semi-variograms can provide insight into ML performance. [ABSTRACT FROM AUTHOR]

In this work, the analysis of TerraSAR-X satellite images combining both conventional and advanced Differential Synthetic Aperture Radar Interferometry (DInSAR) approaches has proven to be effective to detect and monitor fast evolving mining subsidence on urban areas in the Upper Silesian Coal Basin (Poland). This region accounts for almost three million inhabitants where mining subsidence has produced severe damage to urban structures and infrastructures in recent years. Conventional DInSAR approach was used to generate 28 differential interferograms between 5 July 2011 and 21 June 2012 identifying 31 subsidence troughs that account up to 245 mm of displacement in 54 days (equivalent to 1660 mm/year). SqueeSARTM processing yielded a very dense measurement point distribution, failing to detect faster displacements than 330 mm/year, which occur within the subsidence troughs detected with conventional DInSAR. Despite this limitation, this approach was useful to delimit stable areas where mining activities are not conducted and areas affected by residual subsidence surrounding the detected subsidence troughs. These residual subsidence mining areas are located approximately 1 km away from the 31 detected subsidence troughs and account for a subsidence rate greater than 17 mm/year on average. The validation of this methodology has been performed over Bytom City were underground mining activity produced severe damages in August 2011. Conventional DInSAR permitted to successfully map subsidence troughs between July and August 2011 that coincide spatially and temporally with the evolution of underground mining excavations, as well as with the demolition of 28 buildings of Karb district. Additionally, SqueeSARTM displacement estimates were useful to delimit an area of 8.3 km2 of Bytom city that is affected by a residual mining subsidence greater than 5 mm/year and could potentially suffer damages in the midterm. The comparison between geodetic data and SqueeSARTM for the common monitoring period yields and average absolute difference of 7 mm/year, which represents 14% of the average displacement rate measured by the geodetic benchmarks. These results demonstrate that the combined exploitation of high-resolution satellite SAR data through both conventional and advanced DInSAR techniques could be crucial to monitor fast evolving mining subsidence, which may severely impact highly populated mining areas such as the Upper Silesia Coal Basin (USCB). [ABSTRACT FROM AUTHOR]

This study focused on the significance of underground mining in Pakistan, resulting in the employment of operational staff to undertake the primary tasks of this sector, such as explosions, rock excavation, mineral research, mining-supporting walls, and mine compactivity. Occupational accidents and illnesses arise due to the activities mentioned above because the working circumstances are not optimal. The decision-matrix risk-assessment (DMRA) approach, in which incidents are evaluated according to their severity and probability, was also utilized to improve working conditions, including public health and environment protection. To assess the risks and to select which actions should continue in the same manner, we highlighted hazards that need control measures and, as the last option, those that must be stopped. By taking into account the results of the study, corrective actions were proposed that can help avoid the occurrence of the presented accidents through applying occupational safety and health regulations issued by the Department of Minerals and Mines, which is a governmental entity responsible for both the issuing and the compliance to those regulations. The current study also outlined the requirements that must be reported under mining-related laws. [ABSTRACT FROM AUTHOR]

In a mine, knowledge of rock types is often desired as they are important indicators of grade, mineral processing complications, or geotechnical attributes. It is common to model the rock types with visual graphics tools using geologist-generated rock type information in exploration drillhole databases. Instead of this manual approach, this paper used random forest (RF), a machine learning (ML) algorithm, to model the rock type at Erdenet Copper Mine, Mongolia. Exploration drillhole data was used to develop the RF models and predict the rock type based on the coordinates of locations. Data selection and model evaluation methods were designed to ensure applicability for real life scenarios. In the scenario where rock type is predicted close to locations where information is available (such as in blocks being blasted), RF did very well with an overall success rate (OSR) of 89%. In the scenario where rock type was predicted for two future benches (i.e., 30 m below known locations), the best OSR was 86%. When an exploration program was simulated, performance was poor with a OSR of 59%. The results indicate that EMC can leverage RF models for short-term and long-term planning by predicting rock types within drilling blocks or future blocks quite accurately. [ABSTRACT FROM AUTHOR]