| Evaluation of drought status of potato leaves based on hyperspectral imaging |
|
View Fulltext View/Add Comment Download reader |
| |
| DOI：10.7606/j.issn.1000-7601.2024.05.25 |
| Key Words: potato drought stress identification hyperspectral imaging characteristic wavelengths model construction |
| Author Name | Affiliation | | MEI Xuanming | College of Agronomy, Northwest A&F University, Yangling, Shaanxi 712100, China | | HU Yaohua | College of Optical，Mechanical and Electrical Engineering, Zhejiang A&F University, Lin’an, Zhejiang 311300, China | | ZHANG Haotian | College of Agronomy, Northwest A&F University, Yangling, Shaanxi 712100, China | | CAI Yuqing | College of Agronomy, Northwest A&F University, Yangling, Shaanxi 712100, China | | LUO Kaitian | College of Agronomy, Northwest A&F University, Yangling, Shaanxi 712100, China | | MENG Yuling | College of Agronomy, Northwest A&F University, Yangling, Shaanxi 712100, China | | SONG Ying | College of Agronomy, Northwest A&F University, Yangling, Shaanxi 712100, China | | SHAN Weixing | College of Agronomy, Northwest A&F University, Yangling, Shaanxi 712100, China |
|
| Hits: 120 |
| Download times: 109 |
| Abstract: |
| To evaluate the drought status of potato leaves accurately and quickly, a hyperspectral imaging method was employed to assess the drought status of potato leaves. In 2022, the original Qingshu No. 9 seed was used as the test material. Three types of drought status were obtained using hyperspectral imaging. A total of 420 spectral reflectance measurements from various samples were extracted and the influence of four spectral data preprocessing methods on modeling was discussed. A classification model for the drought status of potato leaves was constructed using the random forest cross\|validation recursive feature elimination algorithm (RF-RFECV) and the feature wavelength selection method of competitive adaptive reweighted sampling (CARS) methods combined with extremely randomized trees (EXT). The results showed that the three drought status classification models constructed in this study had accuracy higher than 85% in the test set, among which the SNV-RF-RFECV-EXT model performed the best with a prediction accuracy of 92.14% in the test set. To visually assess the drought status of potato leaves, the SNV-RF-RFECV-EXT model was applied to depict the degree of drought. Different colors were used to represent varying levels of drought, offering a novel approach for distinguishing the drought conditions of potato leaves. |
|
|
|