Hyperspectral imaging detects biological stress of wheat for early diagnosis of crown rot disease

Abstract

Crown rot, caused by a stubble-soil fungal pathogen, threatens wheat production, leading to significant yield losses. The challenge lies in the absence of early visible symptoms for timely detection and management. While hyperspectral imaging technologies have been successfully applied to improve screening for some plant health indicators and diseases, they have not yet been successfully used for crown rot disease detection. This study endeavoured to harness hyperspectral imaging technologies for early-stage, high-throughput, accurate, economical, and non-destructive detection of crown rot disease. Four common Australian commercial wheat varieties with different resistance levels were chosen for study, including Aurora, Yitpi, Emu Rock and Trojan. Three different hyperspectral cameras, covering various wavelength ranges, were tested from both side-view and top-view. Four types of input data for support vector machine classification were tested, including reflectance and the other three derived forms namely hyper-hue, standard normal variate, and principal components. The experimental results showed that hyperspectral imaging technologies can successfully diagnose infected plants in a greenhouse approximately 30 days after infection when there were no visible symptoms on shoots, and the hyper-hue and standard normal variate data transformation methods achieved high F1 scores above 0.75. By discovering key wavelengths, we found that hyperspectral imaging achieved early detection by uncovering biological stress related to photosynthetic activities, and limited absorption of water, protein and starch synthesis. These findings represent a critical advance towards establishing a hyperspectral imaging system for crown rot detection, thereby facilitating disease management and breeding resistant varieties.