Deep-XFCT: Deep Learning 3D-Mineral Liberation Analysis with Micro-X-ray Fluorescence and Computed Tomography
Quantitative characterisation through mineral liberation analysis is required for effective minerals processing in areas such as mineral deposits, tailings and reservoirs in industries for resources, environment and materials science. Current practices in mineral liberation analysis are based on 2D...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/15/15/5326 |
| _version_ | 1797414202731659264 |
|---|---|
| author | Patrick Kin Man Tung Amalia Yunita Halim Huixin Wang Anne Rich Christopher Marjo Klaus Regenauer-Lieb |
| author_facet | Patrick Kin Man Tung Amalia Yunita Halim Huixin Wang Anne Rich Christopher Marjo Klaus Regenauer-Lieb |
| author_sort | Patrick Kin Man Tung |
| collection | DOAJ |
| description | Quantitative characterisation through mineral liberation analysis is required for effective minerals processing in areas such as mineral deposits, tailings and reservoirs in industries for resources, environment and materials science. Current practices in mineral liberation analysis are based on 2D representations, leading to systematic errors in the extrapolation to 3D volumetric properties. The rapid development of X-ray microcomputed tomography (μCT) opens new opportunities for 3D analysis of features such as particle- and grain-size characterisation, determination of particle densities and shape factors, estimation of mineral associations, and liberation and locking. To date, no simple non-destructive method exists for 3D mineral liberation analysis. We present a new development based on combining μCT with micro-X-ray fluorescence (μXRF) using deep learning. We demonstrate successful semi-automated multimodal analysis of a crystalline magmatic rock by obtaining 2D μXRF mineral maps from the top and bottom of the cylindrical core and propagating that information through the 3D μCT volume with deep learning segmentation. The deep learning model was able to segment the core to obtain reasonable mineral attributes. Additionally, the model overcame the challenge of differentiating minerals with similar densities in μCT, which would not be possible with conventional segmentation methods. The approach is universal and can be extended to any multimodal and multi-instrument analysis for further refinement. We conclude that the combination of μCT and μXRF can provide a new opportunity for robust 3D mineral liberation analysis in both field and laboratory applications. |
| first_indexed | 2024-03-09T05:29:40Z |
| format | Article |
| id | doaj.art-c85108db2cd34008886bd0faa45c960f |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-09T05:29:40Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-c85108db2cd34008886bd0faa45c960f2023-12-03T12:34:19ZengMDPI AGEnergies1996-10732022-07-011515532610.3390/en15155326Deep-XFCT: Deep Learning 3D-Mineral Liberation Analysis with Micro-X-ray Fluorescence and Computed TomographyPatrick Kin Man Tung0Amalia Yunita Halim1Huixin Wang2Anne Rich3Christopher Marjo4Klaus Regenauer-Lieb5Tyree X-ray CT Facility, Mark Wainwright Analytical Centre, UNSW Sydney, Sydney, NSW 2052, AustraliaTyree X-ray CT Facility, Mark Wainwright Analytical Centre, UNSW Sydney, Sydney, NSW 2052, AustraliaMark Wainwright Analytical Centre, UNSW Sydney, Sydney, NSW 2052, AustraliaMark Wainwright Analytical Centre, UNSW Sydney, Sydney, NSW 2052, AustraliaMark Wainwright Analytical Centre, UNSW Sydney, Sydney, NSW 2052, AustraliaSchool of Minerals and Energy Resources Engineering, UNSW Sydney, Sydney, NSW 2052, AustraliaQuantitative characterisation through mineral liberation analysis is required for effective minerals processing in areas such as mineral deposits, tailings and reservoirs in industries for resources, environment and materials science. Current practices in mineral liberation analysis are based on 2D representations, leading to systematic errors in the extrapolation to 3D volumetric properties. The rapid development of X-ray microcomputed tomography (μCT) opens new opportunities for 3D analysis of features such as particle- and grain-size characterisation, determination of particle densities and shape factors, estimation of mineral associations, and liberation and locking. To date, no simple non-destructive method exists for 3D mineral liberation analysis. We present a new development based on combining μCT with micro-X-ray fluorescence (μXRF) using deep learning. We demonstrate successful semi-automated multimodal analysis of a crystalline magmatic rock by obtaining 2D μXRF mineral maps from the top and bottom of the cylindrical core and propagating that information through the 3D μCT volume with deep learning segmentation. The deep learning model was able to segment the core to obtain reasonable mineral attributes. Additionally, the model overcame the challenge of differentiating minerals with similar densities in μCT, which would not be possible with conventional segmentation methods. The approach is universal and can be extended to any multimodal and multi-instrument analysis for further refinement. We conclude that the combination of μCT and μXRF can provide a new opportunity for robust 3D mineral liberation analysis in both field and laboratory applications.https://www.mdpi.com/1996-1073/15/15/5326deep learning segmentationmineral liberation analysiscomputed tomographyX-ray fluorescencecorrelative microscopy |
| spellingShingle | Patrick Kin Man Tung Amalia Yunita Halim Huixin Wang Anne Rich Christopher Marjo Klaus Regenauer-Lieb Deep-XFCT: Deep Learning 3D-Mineral Liberation Analysis with Micro-X-ray Fluorescence and Computed Tomography Energies deep learning segmentation mineral liberation analysis computed tomography X-ray fluorescence correlative microscopy |
| title | Deep-XFCT: Deep Learning 3D-Mineral Liberation Analysis with Micro-X-ray Fluorescence and Computed Tomography |
| title_full | Deep-XFCT: Deep Learning 3D-Mineral Liberation Analysis with Micro-X-ray Fluorescence and Computed Tomography |
| title_fullStr | Deep-XFCT: Deep Learning 3D-Mineral Liberation Analysis with Micro-X-ray Fluorescence and Computed Tomography |
| title_full_unstemmed | Deep-XFCT: Deep Learning 3D-Mineral Liberation Analysis with Micro-X-ray Fluorescence and Computed Tomography |
| title_short | Deep-XFCT: Deep Learning 3D-Mineral Liberation Analysis with Micro-X-ray Fluorescence and Computed Tomography |
| title_sort | deep xfct deep learning 3d mineral liberation analysis with micro x ray fluorescence and computed tomography |
| topic | deep learning segmentation mineral liberation analysis computed tomography X-ray fluorescence correlative microscopy |
| url | https://www.mdpi.com/1996-1073/15/15/5326 |
| work_keys_str_mv | AT patrickkinmantung deepxfctdeeplearning3dmineralliberationanalysiswithmicroxrayfluorescenceandcomputedtomography AT amaliayunitahalim deepxfctdeeplearning3dmineralliberationanalysiswithmicroxrayfluorescenceandcomputedtomography AT huixinwang deepxfctdeeplearning3dmineralliberationanalysiswithmicroxrayfluorescenceandcomputedtomography AT annerich deepxfctdeeplearning3dmineralliberationanalysiswithmicroxrayfluorescenceandcomputedtomography AT christophermarjo deepxfctdeeplearning3dmineralliberationanalysiswithmicroxrayfluorescenceandcomputedtomography AT klausregenauerlieb deepxfctdeeplearning3dmineralliberationanalysiswithmicroxrayfluorescenceandcomputedtomography |