Evaluation of stem rust disease in wheat fields by drone hyperspectral imaging

Authors: ABDULRIDHA, JAAFAR - University Of Minnesota; MIN, AN - University Of Minnesota; Rouse, Matthew; Kianian, Shahryar; ISLER, VOLKAN - University Of Minnesota; YANG, CE - University Of Minnesota

Submitted to: Sensors
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 4/15/2023
Publication Date: 4/21/2023
Citation: Abdulridha, J., Min, A., Rouse, M.N., Kianian, S., Isler, V., Yang, C. 2023. Evaluation of stem rust disease in wheat fields by drone hyperspectral imaging. Sensors. 23(8). Article 4154. https://doi.org/10.3390/s23084154.
DOI: https://doi.org/10.3390/s23084154

Interpretive Summary: Wheat is grown on over 37 million acres in the United States. Stem rust disease of wheat can cause devastating yield losses. Emerging strains of the wheat stem rust pathogen such as Ug99 threaten global and United States wheat production. However, research-based tools that can help forecast incidence of stem rust disease affecting U.S. wheat could help mitigate this threat. In this study, a hyperspectral camera mounted on an unmanned aerial vehicle (UAV) was utilized to evaluate severity of wheat stem rust disease in a replicated trial included 960 plots. Plots included wheat lines with variable levels of resistance to stem rust from very susceptible to very resistant, as well as plots protected from stem rust by fungicide treatments. Various analyses methods were used to identify specific wavelengths and spectral vegetation indices (SVIs) that were predictive of wheat stem rust. Random forest classifier applied to the select wavelengths and SVIs predicted stem rust disease classifications at 82-96% accuracy. Importantly, binary classification of non-diseased versus mildly diseased plots was 96% indicating an ability to accurately detect low levels of stem rust disease. Based on this study, it is possible to build a new inexpensive multispectral camera to diagnose wheat stem rust disease accurately. With accurate early detection of stem rust, growers will be able to make better informed management decisions to protect U.S. wheat production.

Technical Abstract: Detecting plant disease severity could help growers and researchers’ study how disease impacts cereal crops to make timely decisions. Advanced technology is needed to protect cereals to feed the increasing population with less chemical usage. This may lead to reduced labor usage and cost in the field. A hyperspectral camera mounted on an unmanned aerial vehicle (UAV) was utilized in this study to evaluate the severity of wheat stem rust disease in a disease trial containing 960 plots. Quadratic data analysis (QDA) and random forest classifier (RFC), decision tree classification, and support vector machine (SVM) were applied to select the wavelengths and spectral vegetation indices (SVIs). The trial plots were divided into four levels based on ground truth disease severities: class 0 (healthy, severity 0), class 1 (mildly diseased, severity 1-15), class 2 (moderately diseased, severity 16-34) and class 3 (severely diseased, highest severity observed). The RFC method achieved the highest overall classification accuracy (85%). For the SVIs the highest classification rate was recorded by RFC, and the accuracy ranged between 82%-96%. Green NDVI (GNDVI), Photochemical Reflectance Index (PRI), Red-Edge Vegetation Stress Index (RVS1) and Chlorophyll Green (Chl green) were selected from 14 SVIs. In addition, binary classification of mildly diseased vs. non-diseased was also conducted using the classifiers and achieved a 96% classification accuracy. This highlighted that hyperspectral imaging was sensitive enough to discriminate between low levels of stem rust disease vs. no disease. Based on this study, it is possible to build a new inexpensive multispectral camera to diagnose wheat stem rust disease accurately.