Detection of wheat powdery mildew by differentiating background factors using hyperspectral imaging

Authors: ZHANG, DONGYAN - National Engineering Research Center For Information Technology In Agriculture; LIN, FEBFANG - Nanjing Tech University; Huang, Yanbo; ZHANG, LIFU - Chinese Academy Of Sciences

Submitted to: International Journal of Agriculture and Biology
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 6/30/2016
Publication Date: 7/30/2016
Citation: Zhang, D., Lin, F., Huang, Y., Zhang, L. 2016. Detection of wheat powdery mildew by differentiating background factors using hyperspectral imaging. International Journal of Agriculture and Biology. 18:747-756.

Interpretive Summary: Crop sensing is important for pesticide applicators to target the spray area as needed. In this study scientists in National Engineering Research Center for Information Technology in Agriculture in Beijing, China, Anhui University, USDA-ARS Crop Production Systems Research Unit, Stoneville, Mississippi, and Chinese Academy of Sciences collaboratively developed the technique of hyperspectral imaging for in-field detection of wheat powdery mildew. With the technique the detection considered the impacts of wheat ears and shadowed leaves on measuring the infected and healthy wheat leaves. The results indicated that the wheat ears could be differentiated from the leaves with the accuracy of 80% and the shadowed leaves with 100%. Further the disease severities could be categorized into mildly infected, moderately infected and healthy with the accuracies of 87.8%, 88.2% and 99.2%, respectively. Overall, the technique developed could be useful for practical crop sensing to provide guidance for pesticide spray.

Technical Abstract: Accurate assessment of crop disease severities is the key for precision application of pesticides to prevent disease infestation. In-situ hyperspectral imaging technology can provide high-resolution imagery with spectra for rapid identification of crop disease and determining disease infestation pattern. In this study, a hyperspectral imager was used to detect wheat powdery mildew with considering the impacts of wheat ears and the leaves under shadow to identify infected and healthy plant leaves. Through comparing the spectral differences between wheat ears and shadowed, healthy, and infected plant leaves, 23 sensitive bands were chosen to distinguish different background targets. Five vegetation indices (VIs) and three red edge parameters were calculated based on screened sensitive bands. Then, 40 identification features were determined to distinguish different background factors and disease severities. Moreover, the classification and regression tree (CRT) was utilized to develop the prediction model of wheat powdery mildew. The identification accuracy was assessed by cross-validation with the accuracies that shadowed leaves can be perfectly recognized while the healthy and infected leaves, wheat ears could be identified with the rates of 98.4%, 98.4%, and 80.8%, respectively. For identification of different disease severities, the healthy leaves have the highest accuracy of 99.2%, while moderately and mildly infected leaves were determined as 88.2% and 87.8%, respectively. Overall, it was found that wheat ears could affect identification accuracy of wheat powdery mildew. At the same time, in order to provide guidance for application of pesticides, improved accuracy for detecting mildly infected disease is expected.