Powdery mildew (PM, Blumeria graminis f. sp. tritici) is a devastating disease for wheat growth and production. It is highly meaningful that the disease severities can be objectively and accurately identified by image visualization technology. In this study, an integral method was proposed based on a hyperspectral imaging dataset and machine learning algorithms. The disease severities of wheat leaves infected with PM were quantitatively identified based on hyperspectral images and image segmentation techniques. A technical procedure was proposed to perform the identification and evaluation of leaf-scale wheat PM, specifically including three primary steps of the acquisition and preprocessing of hyperspectral images, the selection of characteristic bands, and model construction. Firstly, three-dimensional reduction algorithms, namely principal component analysis (PCA), random forest (RF), and the successive projections algorithm (SPA), were comparatively used to select the bands that were most sensitive to PM. Then, three diagnosis models were constructed by a support vector machine (SVM), RF, and a probabilistic neural network (PNN). Finally, the best model was selected by comparing the overall accuracies. The results show that the SVM model constructed by PCA dimensionality reduction had the best result, and the classification accuracy reached 93.33% by a cross-validation method. There was an obvious improvement of the identification accuracy with the model, which achieved an 88.00% accuracy derived from the original hyperspectral images. This study can provide a reference for accurately estimating the disease severity of leaf-scale wheat PM and other plant diseases by non-contact measurement technology.
The development of ground-based, airborne and spaceborne remote sensing has greatly facilitated the identification and diagnosis of various objects. Corresponding algorithms and methods of removing interference from remotely sensed imagery have been proposed. Nevertheless, the studies on anti-interference ability of selected features have not been fully considered. In our study, the hyperspectral reflectance of leaf-scale powdery mildew (Erysiphe graminis) on winter wheat were collected as the testing dataset. A total of seven representative spectral features of Landsat-8 Operational Land Imager (OLI) and GaoFen-1 Wide-Field-View (WFV) was selected, namely, original blue, green, red, near-infrared (NIR) bands and normalized difference vegetation index (NDVI), normalized difference greenness index (NDGI), structure insensitive pigment index (SIPI). Four hyperspectral vegetation indices including red edge (MSR) simple ratio index, NDVI, green band and SIPI were also selected. Three primary background noises including soil, cloud and white poplar (Populus alba L.) were added into the spectral signal. The correlation coefficient (R) between disease severities (0, 1, 2, 3 and 4) and spectral features was used to estimate the anti-interference ability. The results show that there is a generally similar spectral performance for the two sensors, but Landsat-8 OLI is superior to GF-1 WVF in terms of spectral response. The green band was greatly affected with the R values decreasing from 0.77 to 0.35. The MSR and NDVI showed a gradual decrease with the increase of three background noises. The study shows that background noises must be removed when acquiring spectral data and stable spectral features should be also selected by evaluating the anti-interference ability.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.