Detecting the Minimum Limit on Wheat Stripe Rust in the Latent Period Using Proximal Remote Sensing Coupled with Duplex Real-Time PCR and Machine Learning

• Published in: Plants (Basel) Vol. 12; no. 15; p. 2814
• Main Authors: Liu, Qi, Sun, Tingting, Wen, Xiaojie, Zeng, Minghao, Chen, Jing
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 29.07.2023; MDPI
• Subjects: Algorithms; Artificial intelligence; Chlorophyll; Comparative analysis; Correlation analysis; Cultivars; Diagnosis; Disease control; Diseases and pests; duplex real-time PCR; Fungal diseases of plants; Infections; Latent period; Machine learning; minimum detection limit; Model accuracy; Morphology; Multispectral photography; Pathogens; Physiology; Plant diseases; Polymerase chain reaction; proximal remote sensing; Quantitative analysis; Real time; Regression analysis; Remote sensing; Stripe rust; Testing; Wheat; wheat stripe rust; China; duplex real-time PCR; minimum detection limit; wheat stripe rust; proximal remote sensing; latent period
• ISSN: 2223-7747; 2223-7747
• DOI: 10.3390/plants12152814

Wheat stripe rust (WSR) is an airborne disease that causes severe damage to wheat. The rapid and early detection of WSR is essential for the prevention and control of this disease. The minimum detection limit (MDL) is one of the most important characteristics of quantitative methods that can be used to determine the scope and applicability of a measurement technique. Three wheat cultivars were inoculated with f.sp. ( ), and a spectrometer was used to collect the canopy hyperspectral data, and the content was obtained via a duplex real-time polymerase chain reaction (PCR) during the latent period, respectively. The disease index (DI) and molecular disease index (MDI) were calculated. The regression tree algorithm was used to determine the MDL of the based on hyperspectral feature parameters. The logistic, IBK, and random committee algorithms were used to construct the classification model based on the MDL. The results showed that when the MDL was 0.7, IBK had the best recognition accuracy. The optimal model, which used the spectral feature R_2nd.dv ((the second derivative of the original hyperspectral value)) and the modeling ratio 2:1, had an accuracy of 91.67% on the testing set and 90.67% on the 10-fold cross-validation. Thus, during the latent period, the MDL of was determined using hyperspectral technology as 0.7.