Abstract
Early detection of plant diseases, prior to symptom development, can allow for targeted and more proactive disease management. The objective of this study was to evaluate the use of near-infrared (NIR) spectroscopy combined with machine learning for early detection of rice sheath blight (ShB), caused by the fungus Rhizoctonia solani. We collected NIR spectra from leaves of ShB-susceptible rice (Oryza sativa L.) cultivar, Lemont, growing in a growth chamber one day following inoculation with R. solani, and prior to the development of any disease symptoms. Support vector machine (SVM) and random forest, two machine learning algorithms, were used to build and evaluate the accuracy of supervised classification-based disease predictive models. Sparse partial least squares discriminant analysis was used to confirm the results. The most accurate model comparing mock-inoculated and inoculated plants was SVM-based and had an overall testing accuracy of 86.1% (N = 72), while when control, mock-inoculated, and inoculated plants were compared the most accurate SVM model had an overall testing accuracy of 73.3% (N = 105). These results suggest that machine learning models could be developed into tools to diagnose infected but asymptomatic plants based on spectral profiles at the early stages of disease development. While testing and validation in field trials are still needed, this technique holds promise for application in the field for disease diagnosis and management.
Highlights
Plant disease diagnosis can be time-consuming and resourceintensive, requiring trained personnel to either scout for disease symptoms in the field or to run laboratory tests ranging from isolation to more modern molecular identification of pathogens [1, 2]
Presymptomatic disease detection based on NIR spectral profiles was achieved for rice plants artificially inoculated with the fungus R. solani under growth chamber conditions
NIR spectra were collected one day following inoculation, three days before symptoms first developed, and in tissues away from the site of inoculation. This suggests that systemic changes are occurring inside the plant following pathogen infection, and that NIR spectroscopy combined with machine learning is sensitive enough to detect those changes
Summary
Plant disease diagnosis can be time-consuming and resourceintensive, requiring trained personnel to either scout for disease symptoms in the field or to run laboratory tests ranging from isolation to more modern molecular identification of pathogens [1, 2]. Approaches that require minimal training are relatively inexpensive and have the potential to be used in a rapid and high-throughput manner are attractive alternatives, especially if they are capable of diagnosing diseased plants prior to the development of symptoms [3]. Detection and diagnosis of plant diseases may allow for targeted disease management, i.e., applying treatments selectively and only to diseased plants rather than applying treatments to an entire area where not all plants may be diseased. This in turn can lead to reductions in the time and money spent managing for plant diseases, since only smaller areas would need to be treated. While there are field-based methods for PCR (e.g., Loop-mediated isothermal amplification) [4], these methods are not always available, require active sampling, and may not be amenable to high-throughput disease diagnosis in the field
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
