Change search
Link to record
Permanent link

Direct link
BETA
Tiu, Glacialle
Publications (3 of 3) Show all publications
Guntoro, P. I., Tiu, G., Ghorbani, Y., Lund, C. & Rosenkranz, J. (2019). Application of machine learning techniques in mineral phase segmentation for X-ray microcomputed tomography (µCT) data. Minerals Engineering, 142, Article ID 105882.
Open this publication in new window or tab >>Application of machine learning techniques in mineral phase segmentation for X-ray microcomputed tomography (µCT) data
Show others...
2019 (English)In: Minerals Engineering, ISSN 0892-6875, E-ISSN 1872-9444, Vol. 142, article id 105882Article in journal (Refereed) Published
Abstract [en]

X-ray microcomputed tomography (µCT) offers a non-destructive three-dimensional analysis of ores but its application in mineralogical analysis and mineral segmentation is relatively limited. In this study, the application of machine learning techniques for segmenting mineral phases in a µCT dataset is presented. Various techniques were implemented, including unsupervised classification as well as grayscale-based and feature-based supervised classification. A feature matching method was used to register the back-scattered electron (BSE) mineral map to its corresponding µCT slice, allowing automatic annotation of minerals in the µCT slice to create training data for the classifiers. Unsupervised classification produced satisfactory results in terms of segmenting between amphibole, plagioclase, and sulfide phases. However, the technique was not able to differentiate between sulfide phases in the case of chalcopyrite and pyrite. Using supervised classification, around 50–60% of the chalcopyrite and 97–99% of pyrite were correctly identified. Feature based classification was found to have a poorer sensitivity to chalcopyrite, but produced a better result in segmenting between the mineral grains, as it operates based on voxel regions instead of individual voxels. The mineralogical results from the 3D µCT data showed considerable difference compared to the BSE mineral map, indicating stereological error exhibited in the latter analysis. The main limitation of this approach lies in the dataset itself, in which there was a significant overlap in grayscale values between chalcopyrite and pyrite, therefore highly limiting the classifier accuracy.

Place, publisher, year, edition, pages
Elsevier, 2019
Keywords
X-ray micro-tomography (µCT), Machine learning, Mineral segmentation, Feature-based classification, Feature matching
National Category
Metallurgy and Metallic Materials Geology
Research subject
Mineral Processing; Ore Geology
Identifiers
urn:nbn:se:ltu:diva-75703 (URN)10.1016/j.mineng.2019.105882 (DOI)000488141400014 ()2-s2.0-85070948239 (Scopus ID)
Note

Validerad;2019;Nivå 2;2019-08-27 (svasva)

Available from: 2019-08-27 Created: 2019-08-27 Last updated: 2020-02-03Bibliographically approved
Tiu, G., Jansson, N., Wanhainen, C. & Ghorbani, Y. (2019). Sulfide chemistry and trace element deportment at the metamorphosed Lappberget Zn-Pb-Ag-(Cu-Au) ore body, Sweden: Implications for Mineral Processing. In: Life with Ore Deposits on Earth: Proceedings of the 15th SGA Biennial Meeting 2019. Paper presented at 15th SGA Biennial Meeting, 27-30 August 2019, Glasgow, Scotland (pp. 1486-1489). Glasgow, Scotland, 4
Open this publication in new window or tab >>Sulfide chemistry and trace element deportment at the metamorphosed Lappberget Zn-Pb-Ag-(Cu-Au) ore body, Sweden: Implications for Mineral Processing
2019 (English)In: Life with Ore Deposits on Earth: Proceedings of the 15th SGA Biennial Meeting 2019, Glasgow, Scotland, 2019, Vol. 4, p. 1486-1489Conference paper, Oral presentation with published abstract (Refereed)
Abstract [en]

The 58 Mt Lappberget Zn-Pb-Ag-(Cu-Au) ore body represents one of the largest and most significant polymetallic base metal sulfide deposits in Sweden. The complex mineralogical characteristics of the ore body pose particularly tough challenges for successful production forecast because of the mixed Zn-Pb-Cu base metals, the complex association of the beneficial Ag and Au, and the presence of influential elements such as Sb, Mn and Mg. Thus, a detailed mineralogical characterization study was conducted, focusing on the deportment of trace and minor elements (including credit and penalty elements). Mineral chemistry data derived from electron microprobe and   laser ablation inductively coupled plasma mass spectrometry (LA-ICP-MS) analyses reveal the complexity in the composition and associations of the ore minerals, consisting of textural and chemical varieties of sphalerite, galena, chalcopyrite, iron sulfides, antimonides and sulfosalts. Recrystallization, re-mobilization and re-concentration of sulfide minerals, compositional banding, and ductile and brittle deformation textures (i.e. deformation twins on sphalerite, brecciation, bent cleavage planes, etc.) are observed throughout the deposit. The mineralogical and textural complexity and heterogeneity of the sulfide ore are reflected in the variability in grades and recovery from the processing plant.

Place, publisher, year, edition, pages
Glasgow, Scotland: , 2019
Keywords
LA-ICPMS, electron microprobe, Garpenberg, mineral deportment
National Category
Geology
Research subject
Ore Geology
Identifiers
urn:nbn:se:ltu:diva-75960 (URN)
Conference
15th SGA Biennial Meeting, 27-30 August 2019, Glasgow, Scotland
Projects
MetalIntelligence Project
Funder
EU, Horizon 2020, 722677
Available from: 2019-09-11 Created: 2019-09-11 Last updated: 2019-09-20Bibliographically approved
Tiu, G. (2018). Extracting Mineralogical and Textural Data through Multi-scale and Multi-dimensional Imaging Techniques. In: Microbeam Analysis in the Earth Sciences: 13th EMAS Regional Workshop. Paper presented at 13th EMAS Regional Workshop on Microbeam Analysis in the Earth Sciences, Bristol, September 4-7 2018 (pp. 398-399). Bristol
Open this publication in new window or tab >>Extracting Mineralogical and Textural Data through Multi-scale and Multi-dimensional Imaging Techniques
2018 (English)In: Microbeam Analysis in the Earth Sciences: 13th EMAS Regional Workshop, Bristol, 2018, p. 398-399Conference paper, Oral presentation with published abstract (Refereed)
Place, publisher, year, edition, pages
Bristol: , 2018
Keywords
micro X-ray computed tomography, scanning electron microscopre (SEM), drill core imaging, segmentation
National Category
Geosciences, Multidisciplinary
Research subject
Mineral Processing
Identifiers
urn:nbn:se:ltu:diva-72328 (URN)
Conference
13th EMAS Regional Workshop on Microbeam Analysis in the Earth Sciences, Bristol, September 4-7 2018
Funder
Vinnova
Available from: 2018-12-19 Created: 2018-12-19 Last updated: 2019-10-22
Organisations

Search in DiVA

Show all publications