Machine Learning for Mineral Identification and Ore Estimation from Hyperspectral Imagery in Tin–Tungsten Deposits: Simulation under Indoor Conditions
This study aims to assess the feasibility of delineating and identifying mineral ores from hyperspectral images of tin–tungsten mine excavation faces using machine learning classification. We compiled a set of hand samples of minerals of interest from a tin–tungsten mine and analyzed two types of hy...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/16/3258 |
| _version_ | 1797522161614716928 |
|---|---|
| author | Agustin Lobo Emma Garcia Gisela Barroso David Martí Jose-Luis Fernandez-Turiel Jordi Ibáñez-Insa |
| author_facet | Agustin Lobo Emma Garcia Gisela Barroso David Martí Jose-Luis Fernandez-Turiel Jordi Ibáñez-Insa |
| author_sort | Agustin Lobo |
| collection | DOAJ |
| description | This study aims to assess the feasibility of delineating and identifying mineral ores from hyperspectral images of tin–tungsten mine excavation faces using machine learning classification. We compiled a set of hand samples of minerals of interest from a tin–tungsten mine and analyzed two types of hyperspectral images: (1) images acquired with a laboratory set-up under close-to-optimal conditions, and (2) a scan of a simulated mine face using a field set-up, under conditions closer to those in the gallery. We have analyzed the following minerals: cassiterite (tin ore), wolframite (tungsten ore), chalcopyrite, malachite, muscovite, and quartz. Classification (Linear Discriminant Analysis, Singular Vector Machines and Random Forest) of laboratory spectra had a very high overall accuracy rate (98%), slightly lower if the 450–950 nm and 950–1650 nm ranges are considered independently, and much lower (74.5%) for simulated conventional RGB imagery. Classification accuracy for the simulation was lower than in the laboratory but still high (85%), likely a consequence of the lower spatial resolution. All three classification methods performed similarly in this case, with Random Forest producing results of slightly higher accuracy. The user’s accuracy for wolframite was 85%, but cassiterite was often confused with wolframite (user’s accuracy: 70%). A lumped ore category achieved 94.9% user’s accuracy. Our study confirms the suitability of hyperspectral imaging to record the spatial distribution of ore mineralization in progressing tungsten–tin mine faces. |
| first_indexed | 2024-03-10T08:25:33Z |
| format | Article |
| id | doaj.art-9575525d42c14cabbd801285716c1ebf |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T08:25:33Z |
| publishDate | 2021-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-9575525d42c14cabbd801285716c1ebf2023-11-22T09:34:41ZengMDPI AGRemote Sensing2072-42922021-08-011316325810.3390/rs13163258Machine Learning for Mineral Identification and Ore Estimation from Hyperspectral Imagery in Tin–Tungsten Deposits: Simulation under Indoor ConditionsAgustin Lobo0Emma Garcia1Gisela Barroso2David Martí3Jose-Luis Fernandez-Turiel4Jordi Ibáñez-Insa5Geosciences Barcelona, GEO3BCN-CSIC, 08028 Barcelona, SpainLithica (SCCL), 17430 Sta Coloma de Farners, SpainRemote Sensing and GIS, Universitat Autònoma de Barcelona, 08193 Cerdanyola del Vallès, SpainLithica (SCCL), 17430 Sta Coloma de Farners, SpainGeosciences Barcelona, GEO3BCN-CSIC, 08028 Barcelona, SpainGeosciences Barcelona, GEO3BCN-CSIC, 08028 Barcelona, SpainThis study aims to assess the feasibility of delineating and identifying mineral ores from hyperspectral images of tin–tungsten mine excavation faces using machine learning classification. We compiled a set of hand samples of minerals of interest from a tin–tungsten mine and analyzed two types of hyperspectral images: (1) images acquired with a laboratory set-up under close-to-optimal conditions, and (2) a scan of a simulated mine face using a field set-up, under conditions closer to those in the gallery. We have analyzed the following minerals: cassiterite (tin ore), wolframite (tungsten ore), chalcopyrite, malachite, muscovite, and quartz. Classification (Linear Discriminant Analysis, Singular Vector Machines and Random Forest) of laboratory spectra had a very high overall accuracy rate (98%), slightly lower if the 450–950 nm and 950–1650 nm ranges are considered independently, and much lower (74.5%) for simulated conventional RGB imagery. Classification accuracy for the simulation was lower than in the laboratory but still high (85%), likely a consequence of the lower spatial resolution. All three classification methods performed similarly in this case, with Random Forest producing results of slightly higher accuracy. The user’s accuracy for wolframite was 85%, but cassiterite was often confused with wolframite (user’s accuracy: 70%). A lumped ore category achieved 94.9% user’s accuracy. Our study confirms the suitability of hyperspectral imaging to record the spatial distribution of ore mineralization in progressing tungsten–tin mine faces.https://www.mdpi.com/2072-4292/13/16/3258hyperspectral imagingmachine learningspectral geology |
| spellingShingle | Agustin Lobo Emma Garcia Gisela Barroso David Martí Jose-Luis Fernandez-Turiel Jordi Ibáñez-Insa Machine Learning for Mineral Identification and Ore Estimation from Hyperspectral Imagery in Tin–Tungsten Deposits: Simulation under Indoor Conditions Remote Sensing hyperspectral imaging machine learning spectral geology |
| title | Machine Learning for Mineral Identification and Ore Estimation from Hyperspectral Imagery in Tin–Tungsten Deposits: Simulation under Indoor Conditions |
| title_full | Machine Learning for Mineral Identification and Ore Estimation from Hyperspectral Imagery in Tin–Tungsten Deposits: Simulation under Indoor Conditions |
| title_fullStr | Machine Learning for Mineral Identification and Ore Estimation from Hyperspectral Imagery in Tin–Tungsten Deposits: Simulation under Indoor Conditions |
| title_full_unstemmed | Machine Learning for Mineral Identification and Ore Estimation from Hyperspectral Imagery in Tin–Tungsten Deposits: Simulation under Indoor Conditions |
| title_short | Machine Learning for Mineral Identification and Ore Estimation from Hyperspectral Imagery in Tin–Tungsten Deposits: Simulation under Indoor Conditions |
| title_sort | machine learning for mineral identification and ore estimation from hyperspectral imagery in tin tungsten deposits simulation under indoor conditions |
| topic | hyperspectral imaging machine learning spectral geology |
| url | https://www.mdpi.com/2072-4292/13/16/3258 |
| work_keys_str_mv | AT agustinlobo machinelearningformineralidentificationandoreestimationfromhyperspectralimageryintintungstendepositssimulationunderindoorconditions AT emmagarcia machinelearningformineralidentificationandoreestimationfromhyperspectralimageryintintungstendepositssimulationunderindoorconditions AT giselabarroso machinelearningformineralidentificationandoreestimationfromhyperspectralimageryintintungstendepositssimulationunderindoorconditions AT davidmarti machinelearningformineralidentificationandoreestimationfromhyperspectralimageryintintungstendepositssimulationunderindoorconditions AT joseluisfernandezturiel machinelearningformineralidentificationandoreestimationfromhyperspectralimageryintintungstendepositssimulationunderindoorconditions AT jordiibanezinsa machinelearningformineralidentificationandoreestimationfromhyperspectralimageryintintungstendepositssimulationunderindoorconditions |