Proximal Hyperspectral Imaging to Classify Herbicide-Resistant and -Susceptible Kochia (Bassia Scoparia)
Citation
Prabahar Ravichandran, Keshav D. Singh, Charles M. Geddes, Manoj Natarajan, Austin Jaster, and Hongquan Wang, "Proximal Hyperspectral Imaging to Classify Herbicide-Resistant and -Susceptible Kochia (Bassia Scoparia)", 11th International Conference of Agro-Geoinformatics, Wuhan, China, July 2023
Plain language summary
The model results indicated that the hyperspectral imaging approach is a promising alternative for screening herbicides, however, the accuracy could vary with the herbicide/ active ingredients. In this study, we obtained a significant classification accuracy ( 80%) on images acquired prior to the treatment (baseline spectra), although we could see an increasing trend in accuracy with increasing DAT.
Abstract
Kochia (Bassia scoparia) is an invasive broadleaf weed species that has been reported to be responsible for up to 90% yield losses in some major field crops. Herbicides are the primary method being used to control kochia. However, in recent years the incidence of herbicide-resistant kochia has been increasing in the North American Great Plains. New techniques to recognize herbicide-resistant from susceptible kochia biotypes are warranted to promptly inform site-specific kochia management strategies. In this study, we assessed two different herbicides (glyphosate and fluroxypyr) with 6 different kochia populations each. Hyperspectral imagery of the treated kochia plants was obtained immediately prior to the treatment along with 1 and 3 days after treatment. The classification models that were built to identify resistant and susceptible kochia biotypes were able to classify with an accuracy of 75.11% for glyphosate and 82.14% for fluroxypyr.