Hyperspectral magnetite grade based on characteristic band screening inversion study
Abstract In order to clarify the relationship between magnetite grade and reflectance spectra, spectral testing of different grades of magnetite was carried out to analyze the effect of iron grade on the reflectance spectra of specimens. The results show that the fluctuation trends of the spectral c...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-08-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-15429-3 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849345003963285504 |
|---|---|
| author | Yang Bai Xiaoxiao Xie Yuna Jia Yunpeng Zhang |
| author_facet | Yang Bai Xiaoxiao Xie Yuna Jia Yunpeng Zhang |
| author_sort | Yang Bai |
| collection | DOAJ |
| description | Abstract In order to clarify the relationship between magnetite grade and reflectance spectra, spectral testing of different grades of magnetite was carried out to analyze the effect of iron grade on the reflectance spectra of specimens. The results show that the fluctuation trends of the spectral curves of different grades of magnetite are slightly different. By screening the characteristic bands of magnetite grade, it was found that the characteristic bands of different grades of magnetite are mainly distributed in the range of 350–1000 nm and 1800–2500 nm. Then based on the relationship between magnetite grade and reflectance spectra, two inversion models of magnetite grade, PLSR(Partial Least Squares Regression) and MLSR(Multiple Linear Stepwise Regression), were established. By comparing and analyzing the inversion models of magnetite grade established by PLSR and MLSR, it was found that the inversion accuracy based on the PLSR model was better than that of the MLSR model, in which the $$\:{\text{R}}^{\text{2}}$$ and the RMSE of validation set of the best model was respectively 0.9982 and 0.95%. |
| format | Article |
| id | doaj-art-3a0f5081dd4e47b1b030dd794aa3d8d7 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-3a0f5081dd4e47b1b030dd794aa3d8d72025-08-20T03:42:33ZengNature PortfolioScientific Reports2045-23222025-08-011511910.1038/s41598-025-15429-3Hyperspectral magnetite grade based on characteristic band screening inversion studyYang Bai0Xiaoxiao Xie1Yuna Jia2Yunpeng Zhang3College of Mining Engineering, North China University of Science and TechnologySchool of Emergency Management and Safety Engineering, North China University of Science and TechnologyCollege of Mining Engineering, North China University of Science and TechnologyCollege of Mining Engineering, North China University of Science and TechnologyAbstract In order to clarify the relationship between magnetite grade and reflectance spectra, spectral testing of different grades of magnetite was carried out to analyze the effect of iron grade on the reflectance spectra of specimens. The results show that the fluctuation trends of the spectral curves of different grades of magnetite are slightly different. By screening the characteristic bands of magnetite grade, it was found that the characteristic bands of different grades of magnetite are mainly distributed in the range of 350–1000 nm and 1800–2500 nm. Then based on the relationship between magnetite grade and reflectance spectra, two inversion models of magnetite grade, PLSR(Partial Least Squares Regression) and MLSR(Multiple Linear Stepwise Regression), were established. By comparing and analyzing the inversion models of magnetite grade established by PLSR and MLSR, it was found that the inversion accuracy based on the PLSR model was better than that of the MLSR model, in which the $$\:{\text{R}}^{\text{2}}$$ and the RMSE of validation set of the best model was respectively 0.9982 and 0.95%.https://doi.org/10.1038/s41598-025-15429-3MagnetiteSpectral signatureCharacteristic bandInversion modelPLSR |
| spellingShingle | Yang Bai Xiaoxiao Xie Yuna Jia Yunpeng Zhang Hyperspectral magnetite grade based on characteristic band screening inversion study Scientific Reports Magnetite Spectral signature Characteristic band Inversion model PLSR |
| title | Hyperspectral magnetite grade based on characteristic band screening inversion study |
| title_full | Hyperspectral magnetite grade based on characteristic band screening inversion study |
| title_fullStr | Hyperspectral magnetite grade based on characteristic band screening inversion study |
| title_full_unstemmed | Hyperspectral magnetite grade based on characteristic band screening inversion study |
| title_short | Hyperspectral magnetite grade based on characteristic band screening inversion study |
| title_sort | hyperspectral magnetite grade based on characteristic band screening inversion study |
| topic | Magnetite Spectral signature Characteristic band Inversion model PLSR |
| url | https://doi.org/10.1038/s41598-025-15429-3 |
| work_keys_str_mv | AT yangbai hyperspectralmagnetitegradebasedoncharacteristicbandscreeninginversionstudy AT xiaoxiaoxie hyperspectralmagnetitegradebasedoncharacteristicbandscreeninginversionstudy AT yunajia hyperspectralmagnetitegradebasedoncharacteristicbandscreeninginversionstudy AT yunpengzhang hyperspectralmagnetitegradebasedoncharacteristicbandscreeninginversionstudy |