Abstract
A study on the classification of copper concentrates relevant to the copper refining industry is performed by means of reflectance hyperspectral images in the visible and near infrared (VIS-NIR) bands (400–1000 nm) and in the short-wave infrared (SWIR) (900–1700 nm) band. A total of 82 copper concentrate samples were press compacted into 13-mm-diameter pellets, and their mineralogical composition was characterized via quantitative evaluation of minerals and scanning electron microscopy. The most representative minerals contained in these pellets are bornite, chalcopyrite, covelline, enargite, and pyrite. Three databases (VIS-NIR, SWIR, and VIS-NIR-SWIR) containing a collection of average reflectance spectra computed from $9 \times 9\;{\rm pixel}$ neighborhoods in each pellet hyperspectral image are compiled to train the classification models. The classification models tested in this work are a linear discriminant classifier and two non-linear classifiers, a quadratic discriminant classifier, and a fine ${K}$-nearest neighbor classifier (FKNNC). The results obtained show that the joint use of VIS-NIR and SWIR bands allows for the accurate classification of similar copper concentrates that contain only minor differences in their mineralogical composition. Specifically, among the three tested classification models, the FKNNC performs the best in terms of overall classification accuracy, achieving 93.4% accuracy in the test set when only VIS-NIR data are used to construct the classification model, up to 80.5% using only SWIR data, and up to 97.6% using both VIS-NIR and SWIR bands together.
© 2023 Optica Publishing Group
Full Article |
PDF Article
More Like This
Comparison of reflective band (Vis, NIR, SWIR, eSWIR) performance in daytime reduced illumination conditions
Lindsey Wiley, Richard Cavanaugh, Joshua Follansbee, Derek Burrell, Robert Grimming, Rich Pimpinella, Jeff Voss, Orges Furxhi, and Ronald Driggers
Appl. Opt. 62(31) 8316-8326 (2023)
Data availability
The underlying data can be found in Dataset 1, Ref. [21], Dataset 2, Ref. [23], Dataset 3, Ref. [24], Dataset 4, Ref. [25], and Dataset 5, Ref. [26]. Other data underlying the results presented in this paper are not publicly available at this time but may be obtained from the authors upon reasonable request.
21. F. Rivas, F. Pérez, C. Sandoval, B. Sepulveda, J. Yañez, and S. Torres, “QEMSCAN report of 82 copper concentrates,” figshare, 2023, https://doi.org/10.6084/m9.figshare.21984809.
23. F. Rivas, F. Pérez, C. Sandoval, B. Sepulveda, J. Yañez, and S. Torres, “VISNIR-SWIR reflectance dataset of copper concentrates,” figshare, 2023, https://doi.org/10.6084/m9.figshare.21984959.
24. F. Rivas, F. Pérez, C. Sandoval, B. Sepulveda, J. Yañez, and S. Torres, “VISNIR machine learning model for classification of copper concentrates,” figshare, 2023, https://doi.org/10.6084/m9.figshare.22561708.
25. F. Rivas, F. Pérez, C. Sandoval, B. Sepulveda, J. Yañez, and S. Torres, “SWIR machine learning model for classification of copper concentrates,” figshare, 2023, https://doi.org/10.6084/m9.figshare.22561711.
26. F. Rivas, F. Pérez, C. Sandoval, B. Sepulveda, J. Yañez, and S. Torres, “VISNIR-SWIR machine learning model for classification of copper concentrates,” figshare, 2023, https://doi.org/10.6084/m9.figshare.22561705.
Cited By
You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.
Contact your librarian or system administrator
or
Login to access Optica Member Subscription
Tables (4)
You do not have subscription access to this journal. Article tables are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.
Contact your librarian or system administrator
or
Login to access Optica Member Subscription
Equations (4)
You do not have subscription access to this journal. Equations are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.
Contact your librarian or system administrator
or
Login to access Optica Member Subscription