Hyperspectral signal decomposition and symptom detection of wheat rust disease at the leaf scale using pure fungal spore spectra as reference

Abstract

This study establishes a method to detect and distinguish between brown rust and yellow rust on wheat leaves based on hyperspectral imaging at the leaf scale under controlled laboratory conditions. A major problem at this scale is the generation of representative and correctly labelled training data, as only mixed spectra comprising plant and fungal material are observed. For this purpose, the pure spectra of rust spores of Puccinia triticina and P. striiformis, causal agents of brown and yellow rust, respectively, were used to serve as a spectral fingerprint for the detection of a specific leaf rust disease. A least-squares factorization was used on hyperspectral images to unveil the presence of the spectral signal of rust spores in mixed spectra on wheat leaves. A quantification of yellow and brown rust, chlorosis and healthy tissue was verified in time series experiments on inoculated plants. The detection of fungal crop diseases by hyperspectral imaging was enabled without pixel-wise labelling at the leaf scale by using reference spectra from sporescale observations. For the first time, this study shows an interpretable decomposition of the spectral reflectance mixture during pathogenesis. This novel approach will support a more sophisticated and precise detection of foliar diseases of wheat by hyperspectral imaging.

Technical workflows for hyperspectral plant image assessment and processing on the greenhouse and laboratory scale

“…The Savitzky-Golay smoothing algorithm [ 47 ] is the most established one for hyperspectral data. Bohnenkamp et al [ 48 ] showed the applicability for use of 15 centered points and a third-degree polynomial for a Specim FX10 camera providing 220 bands within \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}$400\!-\!1,000\, \mathrm{nm}$\end{document} . Furthermore multiplicative signal correction [ 49 ] and standard normal variate [ 50 ] are well-established routines for signal correction.…”

“…Time-series measurements are essential for accurate capturing of developing disease symptoms. This leads to the development of hyperspectral dynamics over time (TL 3) [ 27 , 48 ]. Hyperspectral data cubes are affected by distance and the inclination of the measured object, so the hyperspectral information needs to be corrected for these factors.…”

Identification of Leaf-Scale Wheat Powdery Mildew (Blumeria graminis f. sp. Tritici) Combining Hyperspectral Imaging and an SVM Classifier

“…More attention has been paid to hyperspectral imaging technology due to its integration of spectra and images. In comparison with visible-band and wide-band images, hyperspectral imaging technology can provide more objective and accurate results due to its integration of images and spectra [15]. It has been widely used in the detection of crop diseases in recent years.…”

In-Field Detection of Yellow Rust in Wheat on the Ground Canopy and UAV Scale

“…Healthy wheat canopies appear dark green because of high amounts of chlorophyll in the leaves [10]. With YR infection in the leaf tissue, a degradation of chlorophyll happens, while the urediniospores of rust fungi are pigmented through the formation of carotenoids [49]. This could explain the importance of certain absorption or reflection bands of pigments for YR detection in the visible range.…”