Crop classification using spectral indices derived from Sentinel-2A imagery
Optical remote sensing is one of the most attractive options for generating crop cover maps because it enables computation of vegetation indices, which are useful for assessing the condition of vegetation. The Sentinel-2A Multispectral Instrument (MSI), which is a multispectral sensor with 13 bands...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2020-01-01
|
| Series: | Journal of Information and Telecommunication |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/24751839.2019.1694765 |
| _version_ | 1818280885275852800 |
|---|---|
| author | Nobuyuki Kobayashi Hiroshi Tani Xiufeng Wang Rei Sonobe |
| author_facet | Nobuyuki Kobayashi Hiroshi Tani Xiufeng Wang Rei Sonobe |
| author_sort | Nobuyuki Kobayashi |
| collection | DOAJ |
| description | Optical remote sensing is one of the most attractive options for generating crop cover maps because it enables computation of vegetation indices, which are useful for assessing the condition of vegetation. The Sentinel-2A Multispectral Instrument (MSI), which is a multispectral sensor with 13 bands covering the visible, near infrared and short-wave infrared (SWIR) wavelength regions, offers a vast number of vegetation indices. Spectral indices, which are combinations of spectral measurements at different wavelengths, have been used in the previous studies and they sometimes contributed to improve classification accuracies. In this study, 91 published spectral indices were calculated from the MSI data. Additionally, classification algorithms are essential for generating accurate maps and the random forests classifier is one of which possesses the five hyperparameters were applied. The improvements in classification accuracies were confirmed achieving an overall accuracy of 93.1% based on the reflectance at 4 bands and 8 spectral indices. |
| first_indexed | 2024-12-12T23:56:20Z |
| format | Article |
| id | doaj.art-69ca52b8d6b34ed9847eefc227c5f153 |
| institution | Directory Open Access Journal |
| issn | 2475-1839 2475-1847 |
| language | English |
| last_indexed | 2024-12-12T23:56:20Z |
| publishDate | 2020-01-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Journal of Information and Telecommunication |
| spelling | doaj.art-69ca52b8d6b34ed9847eefc227c5f1532022-12-22T00:06:33ZengTaylor & Francis GroupJournal of Information and Telecommunication2475-18392475-18472020-01-0141679010.1080/24751839.2019.16947651694765Crop classification using spectral indices derived from Sentinel-2A imageryNobuyuki Kobayashi0Hiroshi Tani1Xiufeng Wang2Rei Sonobe3Smart Link HokkaidoHokkaido UniversityHokkaido UniversityShizuoka UniversityOptical remote sensing is one of the most attractive options for generating crop cover maps because it enables computation of vegetation indices, which are useful for assessing the condition of vegetation. The Sentinel-2A Multispectral Instrument (MSI), which is a multispectral sensor with 13 bands covering the visible, near infrared and short-wave infrared (SWIR) wavelength regions, offers a vast number of vegetation indices. Spectral indices, which are combinations of spectral measurements at different wavelengths, have been used in the previous studies and they sometimes contributed to improve classification accuracies. In this study, 91 published spectral indices were calculated from the MSI data. Additionally, classification algorithms are essential for generating accurate maps and the random forests classifier is one of which possesses the five hyperparameters were applied. The improvements in classification accuracies were confirmed achieving an overall accuracy of 93.1% based on the reflectance at 4 bands and 8 spectral indices.http://dx.doi.org/10.1080/24751839.2019.1694765croprandom forestsspectral indicessentinel-2avariable selection |
| spellingShingle | Nobuyuki Kobayashi Hiroshi Tani Xiufeng Wang Rei Sonobe Crop classification using spectral indices derived from Sentinel-2A imagery Journal of Information and Telecommunication crop random forests spectral indices sentinel-2a variable selection |
| title | Crop classification using spectral indices derived from Sentinel-2A imagery |
| title_full | Crop classification using spectral indices derived from Sentinel-2A imagery |
| title_fullStr | Crop classification using spectral indices derived from Sentinel-2A imagery |
| title_full_unstemmed | Crop classification using spectral indices derived from Sentinel-2A imagery |
| title_short | Crop classification using spectral indices derived from Sentinel-2A imagery |
| title_sort | crop classification using spectral indices derived from sentinel 2a imagery |
| topic | crop random forests spectral indices sentinel-2a variable selection |
| url | http://dx.doi.org/10.1080/24751839.2019.1694765 |
| work_keys_str_mv | AT nobuyukikobayashi cropclassificationusingspectralindicesderivedfromsentinel2aimagery AT hiroshitani cropclassificationusingspectralindicesderivedfromsentinel2aimagery AT xiufengwang cropclassificationusingspectralindicesderivedfromsentinel2aimagery AT reisonobe cropclassificationusingspectralindicesderivedfromsentinel2aimagery |