Rice False Smut Monitoring Based on Band Selection of UAV Hyperspectral Data
Rice false smut (RFS) is a late-onset fungal disease that primarily affects rice panicle in recent years. Severe RFS can decrease the yield by 20–30% and severely affect rice quality. This research used hyperspectral remote sensing data from unmanned aerial vehicles (UAV). On the basis of genetic al...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/12/2961 |
| _version_ | 1797592870158336000 |
|---|---|
| author | Yanxiang Wang Minfeng Xing Hongguo Zhang Binbin He Yi Zhang |
| author_facet | Yanxiang Wang Minfeng Xing Hongguo Zhang Binbin He Yi Zhang |
| author_sort | Yanxiang Wang |
| collection | DOAJ |
| description | Rice false smut (RFS) is a late-onset fungal disease that primarily affects rice panicle in recent years. Severe RFS can decrease the yield by 20–30% and severely affect rice quality. This research used hyperspectral remote sensing data from unmanned aerial vehicles (UAV). On the basis of genetic algorithm combined with partial least squares to select the feature bands, this paper creates a new method to use the Pearson correlation coefficient method and Instability Index between Classes (ISIC) method to further select characteristic bands, which further eliminated 27.78% of the feature bands when the model monitoring accuracy was improved overall. The prediction accuracy of the Gradient Boosting Decision Tree model and Random Forest model was the best, which were 85.62% and 84.10%, respectively, and the monitoring accuracy was improved by 2.22% and 2.4% compared with that before optimization. Then, based on the UAV hyperspectral data and the combination of characteristic bands selected by the three band optimization methods, the sensitive band ranges of rice false smut monitoring were determined, which were 698–800 nm and 974–997 nm. This paper provides an effective method of selecting characteristic bands of hyperspectral data and a method of monitoring crop diseases’ using unmanned aerial vehicles. |
| first_indexed | 2024-03-11T01:59:16Z |
| format | Article |
| id | doaj.art-c4b0de2f61934d83bf8f0da128454e47 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T01:59:16Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-c4b0de2f61934d83bf8f0da128454e472023-11-18T12:24:22ZengMDPI AGRemote Sensing2072-42922023-06-011512296110.3390/rs15122961Rice False Smut Monitoring Based on Band Selection of UAV Hyperspectral DataYanxiang Wang0Minfeng Xing1Hongguo Zhang2Binbin He3Yi Zhang4School of Resources and Environment, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Resources and Environment, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Resources and Environment, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Resources and Environment, University of Electronic Science and Technology of China, Chengdu 611731, ChinaKey Laboratory of Space Ocean Remote Sensing and Application, Ministry of Natural Resources, Beijing 100081, ChinaRice false smut (RFS) is a late-onset fungal disease that primarily affects rice panicle in recent years. Severe RFS can decrease the yield by 20–30% and severely affect rice quality. This research used hyperspectral remote sensing data from unmanned aerial vehicles (UAV). On the basis of genetic algorithm combined with partial least squares to select the feature bands, this paper creates a new method to use the Pearson correlation coefficient method and Instability Index between Classes (ISIC) method to further select characteristic bands, which further eliminated 27.78% of the feature bands when the model monitoring accuracy was improved overall. The prediction accuracy of the Gradient Boosting Decision Tree model and Random Forest model was the best, which were 85.62% and 84.10%, respectively, and the monitoring accuracy was improved by 2.22% and 2.4% compared with that before optimization. Then, based on the UAV hyperspectral data and the combination of characteristic bands selected by the three band optimization methods, the sensitive band ranges of rice false smut monitoring were determined, which were 698–800 nm and 974–997 nm. This paper provides an effective method of selecting characteristic bands of hyperspectral data and a method of monitoring crop diseases’ using unmanned aerial vehicles.https://www.mdpi.com/2072-4292/15/12/2961feature band optimizationhyperspectral datarice false smutInstability Index between Classes (ISIC)UAV |
| spellingShingle | Yanxiang Wang Minfeng Xing Hongguo Zhang Binbin He Yi Zhang Rice False Smut Monitoring Based on Band Selection of UAV Hyperspectral Data Remote Sensing feature band optimization hyperspectral data rice false smut Instability Index between Classes (ISIC) UAV |
| title | Rice False Smut Monitoring Based on Band Selection of UAV Hyperspectral Data |
| title_full | Rice False Smut Monitoring Based on Band Selection of UAV Hyperspectral Data |
| title_fullStr | Rice False Smut Monitoring Based on Band Selection of UAV Hyperspectral Data |
| title_full_unstemmed | Rice False Smut Monitoring Based on Band Selection of UAV Hyperspectral Data |
| title_short | Rice False Smut Monitoring Based on Band Selection of UAV Hyperspectral Data |
| title_sort | rice false smut monitoring based on band selection of uav hyperspectral data |
| topic | feature band optimization hyperspectral data rice false smut Instability Index between Classes (ISIC) UAV |
| url | https://www.mdpi.com/2072-4292/15/12/2961 |
| work_keys_str_mv | AT yanxiangwang ricefalsesmutmonitoringbasedonbandselectionofuavhyperspectraldata AT minfengxing ricefalsesmutmonitoringbasedonbandselectionofuavhyperspectraldata AT hongguozhang ricefalsesmutmonitoringbasedonbandselectionofuavhyperspectraldata AT binbinhe ricefalsesmutmonitoringbasedonbandselectionofuavhyperspectraldata AT yizhang ricefalsesmutmonitoringbasedonbandselectionofuavhyperspectraldata |