Local and Target Exploration of Conglomerate-Hosted Gold Deposits Using Machine Learning Algorithms: A Case Study of the Witwatersrand Gold Ores, South Africa

Nwaila, Glen T.; Zhang, Steven E.; Frimmel, Hartwig E.; Manzi, M.; Dohm, Christina; Durrheim, Raymond; Burnett, Mark Thornton; Tolmay, Leon C.K.

doi:10.1007/s11053-019-09498-1

Cited by 16 publications

(6 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another favorable characteristic of ML is that it allows the discovery of new information or a deeper understanding of existing geospatial data. This is evident in the assertion by Nwaila et al [138] that the advent of ML made sedimentological data, which were initially collected for qualitative assessment of gold mineralization, more meaningful and contextually relevant. ML-based estimation algorithms can accommodate a combination of several geospatial parameters for grade prediction and ore classification.…”

Section: Discussion and Future Directionsmentioning

confidence: 99%

Machine Learning—A Review of Applications in Mineral Resource Estimation

Dumakor-Dupey

Arya

2021

Energies

View full text Add to dashboard Cite

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.

show abstract

Section: Discussion and Future Directionsmentioning

confidence: 99%

Machine Learning—A Review of Applications in Mineral Resource Estimation

Dumakor-Dupey

Arya

2021

Energies

View full text Add to dashboard Cite

show abstract

“…The Black Reef Formation is characterized by quartz-pebble conglomerates of varying thickness. The footwall is quartz-arenite whereas the hanging wall is carbonaceous shale (Fuchs et al, 2016;Nwaila et al, 2020aNwaila et al, , 2020c. Minerals present in minor or trace amounts but of significant interest in the Black Reef Formation include pyrite, chromite, zircon, rutile, chalcopyrite, arsenopyrite, gersdorf-fite, cobaltite, pyrrhotite, galena, sphalerite, uraninite, brannerite, monazite and xenotime (Fig.…”

Section: Petrographic Characterization Of Pyrite Grainsmentioning

confidence: 99%

“…Many tasks in the resource extraction and processing cycle are either critical or are becoming critical to the industry's success. These include resource estimation and modeling, material pre-concentration and sorting; leveraging geometallurgy to optimize extraction and processing; and automation (Lishchuk et al, 2020;Nwaila et al, 2020c). In all these tasks, leveraging online sensors, data and machine learning will become a critical differentiator between resource extraction success and failure in the era of digitization.…”

Section: Integration Of Machine Learning For Mineral Classificationmentioning

confidence: 99%

“…The century-long mining history of Witwatersrand-type ore has produced a legacy of readily available datasets about (1) resource location, (2) resource estimation and (3) resource extraction, all of which can be used for 3D visualization and datadriven analytics (Ghorbani et al, 2020;Nwaila, et al, 2020c;Zhang et al, 2021). These latter published studies have targeted ore deposits hosted by the Central Rand Group of the Witwatersrand Basin.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Constraints on the Geometry and Gold Distribution in the Black Reef Formation of South Africa Using 3D Reflection Seismic Data and Micro-X-ray Computed Tomography

Nwaila

Manzi²,

Zhang³

et al. 2022

Nat Resour Res

Self Cite

View full text Add to dashboard Cite

Geological and geophysical models are essential for developing reliable mine designs and mineral processing flowsheets. For mineral resource assessment, mine planning, and mineral processing, a deeper understanding of the orebody's features, geology, mineralogy, and variability is required. We investigated the gold-bearing Black Reef Formation in the West Rand and Carletonville goldfields of South Africa using approaches that are components of a transitional framework toward fully digitized mining: (1) high-resolution 3D reflection seismic data to model the orebody; (2) petrography to characterize Au and associated ore constituents (e.g., pyrite); and (3) 3D micro-X-ray computed tomography (lCT) and machine learning to determine mineral association and composition. Reflection seismic reveals that the Black Reef Formation is a planar horizon that dips < 10°and has a well-preserved and uneven paleotopography. Several large-scale faults and dikes (most dipping between 65°a nd 90°) crosscut the Black Reef Formation. Petrography reveals that gold is commonly associated with pyrite, implying that lCT can be used to assess gold grades using pyrite as a proxy. Moreover, we demonstrate that machine learning can be used to discriminate between pyrite and gold based on physical characteristics. The approaches in this study are intended to supplement rather than replace traditional methodologies. In this study, we demonstrated that they permit novel integration of micro-scale observations into macroscale modeling, thus permitting better orebody assessment for exploration, resource estimation, mining, and metallurgical purposes. We envision that such integrated approaches will become a key component of future geometallurgical frameworks.

show abstract

“…For field (prospect-scale) exploration, portable geochemical analysis tools such as portable X-ray fluorescence instruments (pXRF) and near-infrared/short-wave infrared (VNIR-SWIR) spectrometers have enabled real-time first-pass analysis of soil and rock samples. Machine learning techniques are still being developed, but research so far shows promising results in potential applicability to interpreting complex and multi-scale datasets used in ore exploration (Nwaila et al 2020;Shirmard et al 2022). Machine learning may become particularly important, for example, when exploring for buried deposits whose only surface expression may be a subtle alteration halo, the recognition of which requires a powerful capacity to calculate mathematical patterns in multi-variant data (Shirmard et al 2022).…”

Section: Comparison Of the Most Common Gold Deposit Types And The Too...mentioning

confidence: 99%

An introduction to Recent Advances in Understanding Gold Deposits: from Orogeny to Alluvium: the importance of multi-method approaches and developing a characterization

Torvela

Chapman

Lambert-Smith

2022

View full text Add to dashboard Cite

Gold occurs in many settings but the dynamic nature of Earth's crust means overlapping and overprinting deposit styles are common. Characterisation of mineralisation from an early stage becomes important particularly where the mineralisation is complex, in order to maximise exploration and project development success, and mining productivity. Various techniques are used at different stages of a project to characterise gold deposits. This Special Publication “Recent Advances in Understanding Gold Deposits: From Orogeny to Alluvium” offers a cross-section of some specific techniques to investigate a variety of gold deposit types. In this Introduction, we briefly compare the most common gold deposit types; summarise the techniques used to investigate them; and discuss some of the most important outstanding questions regarding understanding gold deposits. This is followed by a summary of each paper in this Special Publication. Whilst the 15 papers in this book can only showcase some of the many approaches available, they do highlight both the breadth of the available techniques and their utility in deposit characterisation. Several papers include suggestions for avenues for fruitful further research, including a paper suggesting a new approach to classifying orogenic gold deposits, and a paper describing archaeological applications of natural gold analyses.

show abstract

Local and Target Exploration of Conglomerate-Hosted Gold Deposits Using Machine Learning Algorithms: A Case Study of the Witwatersrand Gold Ores, South Africa

Cited by 16 publications

References 41 publications

Machine Learning—A Review of Applications in Mineral Resource Estimation

Machine Learning—A Review of Applications in Mineral Resource Estimation

Constraints on the Geometry and Gold Distribution in the Black Reef Formation of South Africa Using 3D Reflection Seismic Data and Micro-X-ray Computed Tomography

An introduction to Recent Advances in Understanding Gold Deposits: from Orogeny to Alluvium: the importance of multi-method approaches and developing a characterization

Contact Info

Product

Resources

About