Change search
Link to record
Permanent link

Direct link
Publications (10 of 62) Show all publications
Jannesar Niri, A., Poelzer, G. A., Zhang, S. E., Rosenkranz, J., Pettersson, M. & Ghorbani, Y. (2024). Sustainability challenges throughout the electric vehicle battery value chain. Renewable & sustainable energy reviews, 191, Article ID 114176.
Open this publication in new window or tab >>Sustainability challenges throughout the electric vehicle battery value chain
Show others...
2024 (English)In: Renewable & sustainable energy reviews, ISSN 1364-0321, E-ISSN 1879-0690, Vol. 191, article id 114176Article, review/survey (Refereed) Published
Abstract [en]

The global commitment to decarbonizing the transport sector has resulted in an unabated growth in the markets for electric vehicles and their batteries. Consequently, the demand for battery raw materials is continuously growing. As an illustration, to meet the net-zero emissions targets, the electric vehicle market demand for lithium, cobalt, nickel, and graphite will increase 26-times, 6-times, 12-times, and 9-times respectively between 2021 and 2050. There are diverse challenges in meeting this demand, requiring the world to embrace technological and knowledge advancements and new investments without provoking conflicts between competing goals. The uncertainties in a sustainable supply of battery minerals, environmental, social and governance complexities, and geopolitical tensions throughout the whole battery value chain have shaped the global and regional concerns over the success of transport decarbonization. Here, focusing on the entire value chain of electric vehicle batteries, the approaches adopted by regulatory agencies, governments, mining companies, vehicle and battery manufacturers, and all the other stakeholders are evaluated. Bringing together all these aspects, this literature review broadens the scope for providing multifaceted solutions necessary to optimize the goal of transport decarbonization while upholding sustainability criteria. Consolidating the previously fragmented information, a solid foundation for more in-depth research on existing difficulties encountered by governmental and industrial actors is created. The outcomes of this study may serve as a baseline to develop a framework for a climate smart and resource efficient supply of batteries considering the unique impacts of individual players.

Place, publisher, year, edition, pages
Elsevier, 2024
Keywords
Climate change, Automotive industry, Battery minerals, Sustainable supply of minerals, Energy supply
National Category
Transport Systems and Logistics
Research subject
Mineral Processing; Political Science; Law
Identifiers
urn:nbn:se:ltu:diva-103343 (URN)10.1016/j.rser.2023.114176 (DOI)2-s2.0-85180009983 (Scopus ID)
Funder
Swedish Research Council Formas, 2021-02439
Note

Validerad;2024;Nivå 2;2024-02-16 (joosat);

Full text license: CC BY-4.0

Available from: 2023-12-19 Created: 2023-12-19 Last updated: 2024-02-16Bibliographically approved
Zhang, S. E., Nwaila, G. T., Bourdeau, J. E., Ghorbani, Y. & Carranza, E. J. (2023). Deriving big geochemical data from high-resolution remote sensing data via machine learning: Application to a tailing storage facility in the Witwatersrand goldfields. Artificial Intelligence in Geosciences, 4, 9-21
Open this publication in new window or tab >>Deriving big geochemical data from high-resolution remote sensing data via machine learning: Application to a tailing storage facility in the Witwatersrand goldfields
Show others...
2023 (English)In: Artificial Intelligence in Geosciences, E-ISSN 2666-5441, Vol. 4, p. 9-21Article in journal (Refereed) Published
Abstract [en]

Remote sensing data is a cheap form of surficial geoscientific data, and in terms of veracity, velocity and volume, can sometimes be considered big data. Its spatial and spectral resolution continues to improve over time, and some modern satellites, such as the Copernicus Programme's Sentinel-2 remote sensing satellites, offer a spatial resolution of 10 m across many of their spectral bands. The abundance and quality of remote sensing data combined with accumulated primary geochemical data has provided an unprecedented opportunity to inferentially invert remote sensing data into geochemical data. The ability to derive geochemical data from remote sensing data would provide a form of secondary big geochemical data, which can be used for numerous downstream activities, particularly where data timeliness, volume and velocity are important. Major benefactors of secondary geochemical data would be environmental monitoring and applications of artificial intelligence and machine learning in geochemistry, which currently entirely relies on manually derived data that is primarily guided by scientific reduction. Furthermore, it permits the usage of well-established data analysis techniques from geochemistry to remote sensing that allows useable insights to be extracted beyond those typically associated with strictly remote sensing data analysis. Currently, no generally applicable and systematic method to derive chemical elemental concentrations from large-scale remote sensing data have been documented in geosciences. In this paper, we demonstrate that fusing geostatistically-augmented geochemical and remote sensing data produces an abundance of data that enables a more generalized machine learning-based geochemical data generation. We use gold grade data from a South African tailing storage facility (TSF) and data from both the Landsat-8 and Sentinel remote sensing satellites. We show that various machine learning algorithms can be used given the abundance of training data. Consequently, we are able to produce a high resolution (10 m grid size) gold concentration map of the TSF, which demonstrates the potential of our method to be used to guide extraction planning, online resource exploration, environmental monitoring and resource estimation.

Place, publisher, year, edition, pages
Elsevier, 2023
Keywords
Big geochemical data, Dry labs, Machine learning, Remote sensing, Tailing storage facilities, Witwatersrand Basin
National Category
Remote Sensing Physical Geography
Research subject
Mineral Processing; Centre - Centre for Advanced Mining & Metallurgy (CAMM)
Identifiers
urn:nbn:se:ltu:diva-96375 (URN)10.1016/j.aiig.2023.01.005 (DOI)2-s2.0-85150764908 (Scopus ID)
Note

Validerad;2023;Nivå 1;2023-04-12 (hanlid);

Funder: Department of Scienceand Innovation (DSI) - National Research Foundation (NRF) ThuthukaGrant (121,973); SI-NRF CIMERA; Centre for Advanced Miningand Metallurgy (CAMM), Luleå University of Technology; Sibanye-Stillwater Ltd

Available from: 2023-04-12 Created: 2023-04-12 Last updated: 2023-04-12Bibliographically approved
Ghorbani, Y., Zhang, S. E., Nwaila, G. T., Bourdeau, J. E., Safari, M., Hadi Hoseinie, S., . . . Ruuska, J. (2023). Dry laboratories – Mapping the required instrumentation and infrastructure for online monitoring, analysis, and characterization in the mineral industry. Minerals Engineering, 191, Article ID 107971.
Open this publication in new window or tab >>Dry laboratories – Mapping the required instrumentation and infrastructure for online monitoring, analysis, and characterization in the mineral industry
Show others...
2023 (English)In: Minerals Engineering, ISSN 0892-6875, E-ISSN 1872-9444, Vol. 191, article id 107971Article, review/survey (Refereed) Published
Abstract [en]

Dry laboratories (dry labs) are laboratories dedicated to using and creating data (they are data-centric). Several aspects of the minerals industry (e.g., exploration, extraction and beneficiation) generate multi-scale and multivariate data that are ultimately used to make decisions. Dry labs and digitalization are closely and intricately linked in the minerals industry. This paper focuses on the instrumentation and infrastructure that are required for accelerating digital transformation initiatives in the minerals sector. Specifically, we are interested in the ability of current and emerging instrumentation, sensors and infrastructure to capture relevant information, generate and transport high-quality data. We provide an essential examination of existing literature and an understanding of the 21st century minerals industry. Critical analysis of the literature and review of the current configuration of the minerals industry revealed similar data management and infrastructure needs for all segments of the minerals industry. There are, however, differences in the tools and equipment used at different stages of the mineral value chain. As demand for data-driven approaches grows, and as data resulting from each segment of the minerals industry continues to increase in abundance, diversity and dimensionality, the tools that manage and utilize such data should evolve in a way that is more transdisciplinary (e.g., data management, artificial intelligence, machine learning and data science). Ideally, data should be managed in a dry lab environment, but minerals industry data is currently and historically disaggregated. Consequently, digitalization in the minerals industry must be coupled with dry laboratories through a systematic transition. Sustained generation of high-quality data is critical to sustain the highly desirable uses of data, such as artificial intelligence-based insight generation.

Place, publisher, year, edition, pages
Elsevier, 2023
Keywords
Data analytics, Data-centric/data-driven, Dry laboratory, Instrumentation, Mineral industry, Process monitoring
National Category
Metallurgy and Metallic Materials
Research subject
Mineral Processing
Identifiers
urn:nbn:se:ltu:diva-95163 (URN)10.1016/j.mineng.2022.107971 (DOI)000903925000002 ()2-s2.0-85144459629 (Scopus ID)
Note

Validerad;2023;Nivå 2;2023-01-09 (hanlid);

Funder: Swedish government; Centre for Advanced Mining and Metallurgy (CAMM)

Available from: 2023-01-09 Created: 2023-01-09 Last updated: 2023-04-21Bibliographically approved
Zhang, S. E., Nwaila, G. T., Bourdeau, J. E., Ghorbani, Y. & Carranza, E. J. (2023). Machine Learning-Based Delineation of Geodomain Boundaries: A Proof-of-Concept Study Using Data from the Witwatersrand Goldfields. Natural Resources Research, 32(3), 879-900
Open this publication in new window or tab >>Machine Learning-Based Delineation of Geodomain Boundaries: A Proof-of-Concept Study Using Data from the Witwatersrand Goldfields
Show others...
2023 (English)In: Natural Resources Research, ISSN 1520-7439, E-ISSN 1573-8981, Vol. 32, no 3, p. 879-900Article in journal (Refereed) Published
Abstract [en]

Machine-aided geological interpretation provides an opportunity for rapid and data-driven decision-making. In disciplines such as geostatistics, the integration of machine learning has the potential to improve the reliability of mineral resources and ore reserve estimates. In this study, inspired by existing geostatistical approaches that use radial basis functions to delineate domain boundaries, we reformulate the problem into a machine learning task for automated domain boundary delineation to partition the orebody. We use an actual dataset from an operating mine (Driefontein gold mine, Witwatersrand Basin in South Africa) to showcase our new method. Using various machine learning algorithms, domain boundaries were created. We show that based on a combination of in-discipline requirements and heuristic reasoning, some algorithms/models may be more desirable than others, beyond merely cross-validation performance metrics. In particular, the support vector machine algorithm yielded simple (low boundary complexity) but geologically realistic and feasible domain boundaries. In addition to the empirical results, the support vector machine algorithm is also functionally the most resemblant of current approaches that makes use of radial basis functions. The delineated domains were subsequently used to demonstrate the effectiveness of domain delineation by comparing domain-based estimation versus non-domain-based estimation using an identical automated workflow. Analysis of estimation results indicate that domain-based estimation is more likely to result in better metal reconciliation as compared with non-domained based estimation. Through the adoption of the machine learning framework, we realized several benefits including: uncertainty quantification; domain boundary complexity tuning; automation; dynamic updates of models using new data; and simple integration with existing machine learning-based workflows.

Place, publisher, year, edition, pages
Springer Nature, 2023
Keywords
Domain delineation, Geodomains, Geometallurgy, Gold deposits, Machine learning, Resource estimation, Spatial data analytics
National Category
Computer Sciences
Research subject
Mineral Processing
Identifiers
urn:nbn:se:ltu:diva-95861 (URN)10.1007/s11053-023-10159-7 (DOI)000942687400001 ()2-s2.0-85149260078 (Scopus ID)
Note

Validerad;2023;Nivå 2;2023-07-20 (sofila);

Funder: Department of Science and Innovation (DSI)-National Research Foundation (NRF) Thuthuka Grant (UID: 121973); DSI-NRF CIMERA; Wits Mining Institute (WMI)

Available from: 2023-03-13 Created: 2023-03-13 Last updated: 2023-07-20Bibliographically approved
Ghorbani, Y., Nwaila, G. T., Zhang, S. E., Bourdeau, J. E., Cánovas, M., Arzua, J. & Nikadat, N. (2023). Moving towards deep underground mineral resources: Drivers, challenges and potential solutions. Resources policy, 80, Article ID 103222.
Open this publication in new window or tab >>Moving towards deep underground mineral resources: Drivers, challenges and potential solutions
Show others...
2023 (English)In: Resources policy, ISSN 0301-4207, E-ISSN 1873-7641, Vol. 80, article id 103222Article in journal (Refereed) Published
Abstract [en]

Underground mining has historically occurred in surface and near-surface (shallow) mineral deposits. While no universal definition of deep underground mining exists, humanity's need for non-renewable natural resources has inevitably pushed the boundaries of possibility in terms of environmental and technological constraints. Recently, deep underground mining is being extensively developed due to the depletion of shallow mineral deposits. One of the main advantages of deep underground mining is its lower environmental footprint compared to shallow mining. In this paper, we summarise the key factors driving deep underground mining, which include an increasing need for raw materials, exhaustion of shallow mineral deposits, and increasing environmental scrutiny. We examine the challenges associated with deep underground mining, mainly the: environmental, financial, geological, and geotechnical aspects. Furthermore, we explore solutions provided by recent advances in science and technology, such as the integration of mineral processing and mining, and the digital and technological revolution. We further examine the role of legacy data in its ability to bridge current and future practices in the context of deep underground mining.

Place, publisher, year, edition, pages
Elsevier Ltd, 2023
Keywords
4th industrial revolution, Exploration, Legacy data, Mineral resources, Mining, Subsurface
National Category
Other Civil Engineering
Research subject
Mineral Processing; Mining and Rock Engineering
Identifiers
urn:nbn:se:ltu:diva-95240 (URN)10.1016/j.resourpol.2022.103222 (DOI)000901671700001 ()2-s2.0-85145220060 (Scopus ID)
Note

Validerad;2023;Nivå 2;2023-01-16 (sofila);

Funder: Department of Science and Innovation-National Research Foundation (South Africa) Thuthuka Grant (grant no.121973) 

Available from: 2023-01-17 Created: 2023-01-17 Last updated: 2023-05-08Bibliographically approved
Kazemi, F., Bahrami, A., Ghorbani, Y., Danesh, A., Abdollahi, M., Falah, H. & Salehi, M. (2023). The interaction and synergic effect of particle size on flotation efficiency: A comparison study of recovery by size, and by liberation between lab and industrial scale data: [Sinergijski utjecaj djelovanja veličine zrna na učinkovitost flotacije: usporedba laboratorijskih i industrijskih podataka o iskorištenju korisne komponente u koncentratu ovisno o veličini zrna i raščinu (stupnju oslobođenja)]. Rudarsko-Geološko-Naftni Zbornik, 38(1), 1-12
Open this publication in new window or tab >>The interaction and synergic effect of particle size on flotation efficiency: A comparison study of recovery by size, and by liberation between lab and industrial scale data: [Sinergijski utjecaj djelovanja veličine zrna na učinkovitost flotacije: usporedba laboratorijskih i industrijskih podataka o iskorištenju korisne komponente u koncentratu ovisno o veličini zrna i raščinu (stupnju oslobođenja)]
Show others...
2023 (English)In: Rudarsko-Geološko-Naftni Zbornik, ISSN 0353-4529, E-ISSN 1849-0409, Vol. 38, no 1, p. 1-12Article in journal (Refereed) Published
Abstract [en]

The interaction and synergic effect of particle size on flotation efficiency were investigated by a comparison study between laboratories (size-by-size flotation modes) and industrial scale operational data (whole mixed size fraction). For this purpose, sampling was done from the feed, concentrate, and tailing of the flotation rougher cells of the Sungun copper processing complex (located in the northwest of Iran). In the size-by-size flotation mode (lab scale), the sample was first subjected to different size fractions, and then flotation tests were performed for each fraction. On an industrial scale, the particle size distribution of feed, concentrate, and tailing of flotation of the rougher stage have been analyzed. According to the results, in the case of industrial flotation mode (whole mixed size fraction), the particles with d80=84 μm were more likely to reach the tailing of flotation, and the particles within the size range of +63-180 μm constituted the highest amount of concentrate particles. In lab flotation mode (size-by-size), the maximum recovery was in the size fraction of +40-60 μm. By comparing the two flotation modes of industrial (whole mixed size fraction) and lab (size-by-size), for fractions <45 μm, the industrial flotation recovery was approximately 40% greater than the lab flotation recovery. However, for fractions >125 μm, the recovery trend was reversed and the lab flotation recovery was greater than the industrial flotation recovery. Coarse particle flotation has significant economic and technological benefits. By improving the recovery of coarse particles during the flotation process, the amount of grinding requirements will be reduced and consequently, it will considerably decrease the amount of energy consumption.

Abstract [hr]

Interakcija i sinergijski učinak veličine čestica na učinkovitost flotacije istraženi su usporednom studijom laboratorijskih (model flotacije po veličini) i operativnih podataka na industrijskoj razini (cijela frakcija miješane veličine). S tom svrhom uzorkovanje je obavljeno iz sirovine, koncentrata i ostataka iz grubih ćelija flotacije u kompleksu Sungun za preradu bakra (koji se nalazi na sjeverozapadu Irana). U načinu flotacije po veličini (laboratorijsko mjerilo) uzorak je najprije podvrgnut razdvajanju po veličini frakcija, a zatim je za svaku frakciju obavljeno ispitivanje flotacije. U industrijskim razmjerima analizirana je granulometrijska raspodjela čestica u sirovini, koncentratu i jalovini grubljih faza flotacije. Prema rezultatima, u slučaju industrijskoga načina flotacije (cijela mješovita frakcija) veća je vjerojatnost da će čestice d80 = 84 μm dospjeti do ostatka flotacije, a čestice unutar raspona veličine od +63 do 180 μm činile su najveću količinu čestica u koncentratu. U laboratorijskome načinu flotacije (po veličini) najveće iskorištenje bilo je u frakciji veličine od +40 do 60 μm. Uspoređujući dva načina flotacije – industrijske (cijela frakcija miješane veličine) i laboratorijske (po veličini), za frakcije <45 μm, industrijska flotacija bila je približno 40 % veća od laboratorijske flotacije. Međutim, za frakcije >125 μm trend iskorištenja bio je obrnut, a iskorištenje laboratorijskom flotacijom bilo je veće od iskorištenja industrijskom flotacijom. Flotacija grubih čestica ima bitne ekonomske i tehnološke prednosti. Poboljšanjem iskorištenja grubih čestica tijekom procesa flotacije smanjit će se potreba za mljevenjem, a posljedično će se znatno smanjiti količina potrošnje energije.

Place, publisher, year, edition, pages
Faculty of Mining, Geology and Petroleum Engineering, University of Zagreb, 2023
Keywords
copper, flotation, mineralog, particle size distribution, recovery, lotacija, iskorištenje, granulometrijska raspodjela čestica, bakar, mineralogija
National Category
Metallurgy and Metallic Materials
Research subject
Mineral Processing
Identifiers
urn:nbn:se:ltu:diva-96617 (URN)10.17794/rgn.2023.1.1 (DOI)000954580900014 ()2-s2.0-85151023444 (Scopus ID)
Note

Validerad;2023;Nivå 2;2023-04-17 (hanlid)

Available from: 2023-04-17 Created: 2023-04-17 Last updated: 2023-04-17Bibliographically approved
Schmitt, R., Parian, M., Ghorbani, Y., McElroy, I. & Bolin, N. (2022). A geometallurgical approach towards the correlation between rock type mineralogy and grindability: A case study in Aitik mine, Sweden. In: IMPC Asia-Pacific 2022 Conference Proceedings: . Paper presented at IMPC Asia-Pacific 2022, Melbourne, Australia, August 22-24, 2022 (pp. 51-70). The Australian Institute of Mining and Metallurgy
Open this publication in new window or tab >>A geometallurgical approach towards the correlation between rock type mineralogy and grindability: A case study in Aitik mine, Sweden
Show others...
2022 (English)In: IMPC Asia-Pacific 2022 Conference Proceedings, The Australian Institute of Mining and Metallurgy , 2022, p. 51-70Conference paper, Published paper (Refereed)
Abstract [en]

Aitik is a large copper porphyry type deposit located in northern Sweden, currently exploited at an annual rate of approximately 45Mt. The ore’s exceptionally low head grade of 0.25 % Cu and varying degrees of hardness across the entire deposit pose challenges to the two fully autogenous grinding lines, each of which comprises a 25 MW primary autogenous mill in series with a pebble mill. The variability in ore grindability frequently leads to fluctuations in mill throughput. 

Within the framework of a geometallurgical approach, the present study investigated the relationships between ore grindability and modal mineralogy. For this purpose, drill core samples from different lithologies were subjected to Boliden AB’s in-house grindability tests. This fully autogenous laboratory-scale test generates a grindability index mainly related to abrasion breakage, which is a significant breakage mechanism within autogenous mills. The test results suggested divergent degrees of grindability within and across the selected rock types.

A combination of scanning electron microscopy, X-ray powder diffraction, and X-ray fluorescence analyses were performed for the grinding products and bulk mineral samples. The resulting mineralogical and elemental properties were subsequently correlated to the parameters from the grindability tests. It was shown that the main mineral phases, such as plagioclase, quartz, and micas, correlate well with the grindability indices. Similar correlations were found regarding the sample’s chemical composition, attributable to the main mineral phases. A further inverse correlation between the sample’s calculated average Mohs hardness and the grindability indices was established. Moreover, mineral liberation information provided by scanning electron microscopy was associated with the parameters mentioned earlier. The identified relationships between grindability, modal mineralogy, and element grades may help Boliden develop a predictive throughput model for Aitik based on the mine’s block model.

Place, publisher, year, edition, pages
The Australian Institute of Mining and Metallurgy, 2022
Keywords
Geometallurgy, autogenous grindability test, abrasion breakage, process mineralogy, automated mineralogy
National Category
Mineral and Mine Engineering
Research subject
Mineral Processing
Identifiers
urn:nbn:se:ltu:diva-92745 (URN)
Conference
IMPC Asia-Pacific 2022, Melbourne, Australia, August 22-24, 2022
Note

ISBN för värdpublikation: 978-1-922395-08-5

Available from: 2022-09-01 Created: 2022-09-01 Last updated: 2023-09-05Bibliographically approved
Zhang, S. E., Bourdeau, J. E., Nwaila, G. T. & Ghorbani, Y. (2022). Advanced geochemical exploration knowledge using machine learning: Prediction of unknown elemental concentrations and operational prioritization of Re-analysis campaigns. Artificial Intelligence in Geosciences, 3, 86-100
Open this publication in new window or tab >>Advanced geochemical exploration knowledge using machine learning: Prediction of unknown elemental concentrations and operational prioritization of Re-analysis campaigns
2022 (English)In: Artificial Intelligence in Geosciences, E-ISSN 2666-5441, Vol. 3, p. 86-100Article in journal (Refereed) Published
Abstract [en]

While a re-analysis campaign in a geochemical exploration program modernizes legacy geochemical data by providing more trustworthy and higher-dimensional geochemical data, especially where modern data is considerably different than legacy data, it is an expensive exercise. The risk associated with modernizing such legacy data lies within its uncertainty in return (e.g., the possibility of new discoveries, in primarily greenfield settings). Without any advanced knowledge of yet unanalyzed elements, the importance of re-analyses remains ambiguous. To address this uncertainty, we apply machine learning to multivariate geochemical data from different regions in Canada (i.e., the Churchill Province and the Trans-Hudson Orogen) in order to use legacy geochemical data to predict modern and higher dimensional multi-elemental concentrations ahead of planned re-analyses. Our study demonstrates that legacy and modern geochemical data can be repurposed to predict yet unanalyzed elements that will be realized from re-analyses and in a manner that significantly reduces the latency to downstream usage of modern geochemical data (e.g., prospectivity mapping). Findings from this study serve as a pillar of a framework for exploration geologists to predictively explore and prioritize potentially mineralized districts for further prospects in a timely manner before employing more invasive and expensive techniques.

Place, publisher, year, edition, pages
Elsevier, 2022
Keywords
Advanced exploration knowledge, Canada, Geochemical data, Machine learning, Re-purposing legacy data
National Category
Geophysics Geochemistry Computer Sciences
Research subject
Mineral Processing
Identifiers
urn:nbn:se:ltu:diva-94288 (URN)10.1016/j.aiig.2022.10.003 (DOI)2-s2.0-85141989622 (Scopus ID)
Note

Validerad;2022;Nivå 1;2022-11-28 (hanlid);

Funder: Department of Science and Innovation (DSI)-National Research Foundation (NRF) (121973); DSI-NRF CIMERA

Available from: 2022-11-28 Created: 2022-11-28 Last updated: 2022-11-28Bibliographically approved
Nwaila, G. T., Zhang, S. E., Bourdeau, J. E., Ghorbani, Y. & Carranza, E. J. (2022). Artificial intelligence-based anomaly detection of the Assen iron deposit in South Africa using remote sensing data from the Landsat-8 Operational Land Imager. Artificial Intelligence in Geosciences, 3, 71-85
Open this publication in new window or tab >>Artificial intelligence-based anomaly detection of the Assen iron deposit in South Africa using remote sensing data from the Landsat-8 Operational Land Imager
Show others...
2022 (English)In: Artificial Intelligence in Geosciences, E-ISSN 2666-5441, Vol. 3, p. 71-85Article in journal (Refereed) Published
Abstract [en]

Most known mineral deposits were discovered by accident using expensive, time-consuming, and knowledge-based methods such as stream sediment geochemical data, diamond drilling, reconnaissance geochemical and geophysical surveys, and/or remote sensing. Recent years have seen a decrease in the number of newly discovered mineral deposits and a rise in demand for critical raw materials, prompting exploration geologists to seek more efficient and inventive ways for processing various data types at different phases of mineral exploration. Remote sensing is one of the most sought-after tools for early-phase mineral prospecting because of its broad coverage and low cost. Remote sensing images from satellites are publicly available and can be utilised for lithological mapping and mineral exploitation. In this study, we extend an artificial intelligence-based, unsupervised anomaly detection method to identify iron deposit occurrence using Landsat-8 Operational Land Imager (OLI) satellite imagery and machine learning. The novelty in our method includes: (1) knowledge-guided and unsupervised anomaly detection that does not assume any specific anomaly signatures; (2) detection of anomalies occurs only in the variable domain; and (3) a choice of a range of machine learning algorithms to balance between explain-ability and performance. Our new unsupervised method detects anomalies through three successive stages, namely (a) stage I – acquisition of satellite imagery, data processing and selection of bands, (b) stage II – predictive modelling and anomaly detection, and (c) stage III – construction of anomaly maps and analysis. In this study, the new method was tested over the Assen iron deposit in the Transvaal Supergroup (South Africa). It detected both the known areas of the Assen iron deposit and additional deposit occurrence features around the Assen iron mine that were not known. To summarise the anomalies in the area, principal component analysis was used on the reconstruction errors across all modelled bands. Our method enhanced the Assen deposit as an anomaly and attenuated the background, including anthropogenic structural anomalies, which resulted in substantially improved visual contrast and delineation of the iron deposit relative to the background. The results demonstrate the robustness of the proposed unsupervised anomaly detection method, and it could be useful for the delineation of mineral exploration targets. In particular, the method will be useful in areas where no data labels exist regarding the existence or specific spectral signatures of anomalies, such as mineral deposits under greenfield exploration.

Place, publisher, year, edition, pages
Elsevier, 2022
Keywords
Anomaly detection, Exploration, Iron deposit, Lansat-8, Machine learning, Prospecting, Remote sensing
National Category
Geophysics
Research subject
Mineral Processing
Identifiers
urn:nbn:se:ltu:diva-93761 (URN)10.1016/j.aiig.2022.10.001 (DOI)2-s2.0-85140244898 (Scopus ID)
Note

Validerad;2022;Nivå 1;2022-10-31 (hanlid);

Funder: Department of Science and Innovation (DSI)-National Research Foundation (NRF) Thuthuka Grant (121973); DSI-NRF CIMERA

Available from: 2022-10-31 Created: 2022-10-31 Last updated: 2022-10-31Bibliographically approved
Nwaila, G. T., Manzi, M. S. .., Zhang, S. E., Bourdeau, J. E., Bam, L. C., Rose, D. H., . . . Durrheim, R. J. (2022). 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. Natural Resources Research, 31(3), 1225-1244
Open this publication in new window or tab >>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
Show others...
2022 (English)In: Natural Resources Research, ISSN 1520-7439, E-ISSN 1573-8981, Vol. 31, no 3, p. 1225-1244Article in journal (Refereed) Published
Abstract [en]

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 (µCT) 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° and 90°) crosscut the Black Reef Formation. Petrography reveals that gold is commonly associated with pyrite, implying that µCT 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 macro-scale 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.

Place, publisher, year, edition, pages
Springer, 2022
Keywords
Gold, South Africa, 3D seismics, Machine learning, 3D micro-X-ray computed tomography
National Category
Geophysics
Research subject
Mineral Processing
Identifiers
urn:nbn:se:ltu:diva-90485 (URN)10.1007/s11053-022-10064-5 (DOI)000788499300002 ()2-s2.0-85128901443 (Scopus ID)
Note

Validerad;2022;Nivå 2;2022-07-05 (joosat);

Funder: Department of Science and Innovation (DSI)-National Research Foundation (NRF) Thuthuka (grant no. 121973); DSI-NRF CIMERA

Available from: 2022-05-02 Created: 2022-05-02 Last updated: 2022-07-05Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0002-5228-3888

Search in DiVA

Show all publications