Monitoring Lodging Extents of Maize Crop Using Multitemporal GF-1 Images
Maize crop lodging is a recurrent phenomenon which results in significant reduction of grain yield and quality in addition to the impediment of mechanical harvesting. The large-scale monitoring of maize crop lodging is important for production policy adjustment and agricultural insurance compensatio...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9763426/ |
| _version_ | 1818551824893870080 |
|---|---|
| author | Xuzhou Qu Dong Shi Xiaohe Gu Qian Sun Xueqian Hu Xin Yang Yuchun Pan |
| author_facet | Xuzhou Qu Dong Shi Xiaohe Gu Qian Sun Xueqian Hu Xin Yang Yuchun Pan |
| author_sort | Xuzhou Qu |
| collection | DOAJ |
| description | Maize crop lodging is a recurrent phenomenon which results in significant reduction of grain yield and quality in addition to the impediment of mechanical harvesting. The large-scale monitoring of maize crop lodging is important for production policy adjustment and agricultural insurance compensation. In this article, we derived a variety of features from multitemporal GaoFen-1 (GF-1) images before and after maize crop lodging. We screened the most sensitive features of the spectrum, texture, and vegetation index to monitor maize crop lodging. The recursive feature elimination method based on cross-validation and mutual information were compared to obtain the optimal feature combination for monitoring the lodging extents of maize crop. The random forest classifier was used to classify the lodging extents. The results showed that the most sensitive features of the spectrum, texture, and vegetation indices of lodging extents included the difference of reflectance in blue, green, and red bands, the difference of normalized difference vegetation index, the difference of ratio vegetation index, the difference of enhanced vegetation index difference, the difference of mean value of blue band, the difference of mean value of green band, and the difference of mean value of red band. The total accuracy of lodging extents classification was 87.50%, and the Kappa coefficient was 0.83 for testing samples. Based on multiple features derived from GF-1 images before and after lodging, the lodging extents of maize crop can be monitored on a large scale. |
| first_indexed | 2024-12-12T09:05:03Z |
| format | Article |
| id | doaj.art-e8885854888745f7a9d654d4f894b660 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-12T09:05:03Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-e8885854888745f7a9d654d4f894b6602022-12-22T00:29:41ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352022-01-01153800381410.1109/JSTARS.2022.31703459763426Monitoring Lodging Extents of Maize Crop Using Multitemporal GF-1 ImagesXuzhou Qu0https://orcid.org/0000-0002-8425-4352Dong Shi1Xiaohe Gu2https://orcid.org/0000-0002-7102-1939Qian Sun3https://orcid.org/0000-0001-6154-5985Xueqian Hu4Xin Yang5Yuchun Pan6School of Geoscience, Yangtze University, Wuhan, ChinaSchool of Geoscience, Yangtze University, Wuhan, ChinaResearch Center of Information Technology, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaResearch Center of Information Technology, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaResearch Center of Information Technology, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaResearch Center of Information Technology, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaResearch Center of Information Technology, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaMaize crop lodging is a recurrent phenomenon which results in significant reduction of grain yield and quality in addition to the impediment of mechanical harvesting. The large-scale monitoring of maize crop lodging is important for production policy adjustment and agricultural insurance compensation. In this article, we derived a variety of features from multitemporal GaoFen-1 (GF-1) images before and after maize crop lodging. We screened the most sensitive features of the spectrum, texture, and vegetation index to monitor maize crop lodging. The recursive feature elimination method based on cross-validation and mutual information were compared to obtain the optimal feature combination for monitoring the lodging extents of maize crop. The random forest classifier was used to classify the lodging extents. The results showed that the most sensitive features of the spectrum, texture, and vegetation indices of lodging extents included the difference of reflectance in blue, green, and red bands, the difference of normalized difference vegetation index, the difference of ratio vegetation index, the difference of enhanced vegetation index difference, the difference of mean value of blue band, the difference of mean value of green band, and the difference of mean value of red band. The total accuracy of lodging extents classification was 87.50%, and the Kappa coefficient was 0.83 for testing samples. Based on multiple features derived from GF-1 images before and after lodging, the lodging extents of maize crop can be monitored on a large scale.https://ieeexplore.ieee.org/document/9763426/Lodgingmaize cropmultitemporalrandom forest (RF)recursive feature elimination (RFE) method based on cross-validation (RFECV) |
| spellingShingle | Xuzhou Qu Dong Shi Xiaohe Gu Qian Sun Xueqian Hu Xin Yang Yuchun Pan Monitoring Lodging Extents of Maize Crop Using Multitemporal GF-1 Images IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Lodging maize crop multitemporal random forest (RF) recursive feature elimination (RFE) method based on cross-validation (RFECV) |
| title | Monitoring Lodging Extents of Maize Crop Using Multitemporal GF-1 Images |
| title_full | Monitoring Lodging Extents of Maize Crop Using Multitemporal GF-1 Images |
| title_fullStr | Monitoring Lodging Extents of Maize Crop Using Multitemporal GF-1 Images |
| title_full_unstemmed | Monitoring Lodging Extents of Maize Crop Using Multitemporal GF-1 Images |
| title_short | Monitoring Lodging Extents of Maize Crop Using Multitemporal GF-1 Images |
| title_sort | monitoring lodging extents of maize crop using multitemporal gf 1 images |
| topic | Lodging maize crop multitemporal random forest (RF) recursive feature elimination (RFE) method based on cross-validation (RFECV) |
| url | https://ieeexplore.ieee.org/document/9763426/ |
| work_keys_str_mv | AT xuzhouqu monitoringlodgingextentsofmaizecropusingmultitemporalgf1images AT dongshi monitoringlodgingextentsofmaizecropusingmultitemporalgf1images AT xiaohegu monitoringlodgingextentsofmaizecropusingmultitemporalgf1images AT qiansun monitoringlodgingextentsofmaizecropusingmultitemporalgf1images AT xueqianhu monitoringlodgingextentsofmaizecropusingmultitemporalgf1images AT xinyang monitoringlodgingextentsofmaizecropusingmultitemporalgf1images AT yuchunpan monitoringlodgingextentsofmaizecropusingmultitemporalgf1images |