Utilising pure fungal spore spectra as reference for a hyperspectral signal decomposition and symptom detection of wheat rust diseases on leaf scale

Autor/in: Bohnenkamp D., M.T. Kuska, A.-K. Mahlein, J. Behmann
Jahr: 2019
Zeitschrift: Plant Pathology
Seite/n: doi.org/10.1111/ppa.13020
Stichworte: brown rust, yellow rust, hyperspectral imaging, close range imaging, spectral unmixing, non-negative least-squares fit

Published in Projekt Veröffentlichungen, die keinem Projekt und keiner Abteilung zugeordnet sind / Abteilung Additional projects and publications

Abstract

In this study, we established a method to detect and distinguish between brown rust and yellow rust on wheat leaves based on hyperspectral imaging at leaf scale under controlled conditions in a laboratory. A major problem at this scale is the generation of representative and correctly labelled training data as only mixed spectra comprising plant material and fungal material are observed. For this purpose, the pure spectra of rust spores of Puccinia triticina and Puccinia striiformis 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 spore scale observations. For the first time, we showed 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.

FaLang translation system by Faboba