By Topic

Detecting Aphid Density of Winter Wheat Leaf Using Hyperspectral Measurements

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

6 Author(s)
Juhua Luo ; State Key Lab. of Lake Sci. & Environ., Nanjing Inst. of Geogr. & Limnology, Nanjing, China ; Wenjiang Huang ; Jinling Zhao ; Jingcheng Zhang
more authors

Wheat aphid, Sitobion avenae F. is one of the most destructive pests that emerge in northwest China almost every year, impacting on the production of winter wheat. Hyperspectral remote sensing has been demonstrated to be superior to a traditional method in detecting diseases and pests. In this study, spectral features (SFs) were examined by four methods to detect aphid density of wheat leaf and model was established to estimate aphid density using partial least square regression (PLSR). A total of 60 wheat leaves with different aphid densities were selected. Aphid density of the leaves was first visually estimated, and then the reflectance of leaves was measured in the spectral range of 350-2500 nm using a spectroradiometer coupling with a leaf clip. A total of 48 spectral features were obtained and examined via correlation analysis, independent t-test by spectral derivative method, continuous removal method, continuous wavelet analysis (CWA) and commonly used vegetation indices for stress detection. Based on variable importance in projection (VIP), five spectral features (VIP ≥ 1) were selected from 17 spectral features due to their strong correlation with aphid density (R2 ≥ 0.5) to establish the model for estimating aphid density by PLSR. The result showed that the model had a great potential in detecting aphid density with a relative root mean square error (RMSE) of 15 and a coefficient of determination (R2) of 0.77.

Published in:

Selected Topics in Applied Earth Observations and Remote Sensing, IEEE Journal of  (Volume:6 ,  Issue: 2 )