Westminster, Colorado, USA
14 April 2023
Progress is being made in the race to deploy highly targeted, machine-based weed control solutions. But one gating factor is the inability of sensors to reliably distinguish weeds from crops. Researchers in Brazil, though, have demonstrated how spectroscopy and data analysis may provide a path forward.
In an article featured in the journal Weed Science, the research team describes their success in using technology to distinguish among three hard to control species of morningglory found in Brazil’s economically important sugarcane fields – ivyleaf, Japanese and hairy woodrose.
The team used near infrared spectroscopy to collect spectral data from lab-grown specimens of the three weeds and then developed classification models based on differences detected among them. With the classification data as a guide, they were able to use spectroscopy to achieve identification accuracy rates of 99.3 percent for ivyleaf morningglory, 98.5 percent for Japanese morningglory, and 98.7 percent for hairy woodrose morningglory.
“Developing reliable sensor-based techniques for the identification of weed species is an important first step towards highly targeted weed management,” says Andreisa Flores Braga, Ph.D., of Sao Paulo State University. “With smart sensors that can reliably distinguish weeds from crops in the field, we will have the information needed to guide mechanized sprayers and apply post-emergent herbicides to specific weeds.”
More information is available in the article “Discrimination of morningglory species using near-infrared spectroscopy and multivariate analysis”.
Species
