Smutgrass can spread quickly and take over grazing lands, leaving cattle with little left to eat.
“It can completely invade a pasture within three years, if left untreated. It is quite common to see pastures in Southern Florida that are 100% smutgrass,” said Brent Sellers, a University of Florida agronomy professor and director of the UF/IFAS Range Cattle Research and Education Center (RCREC).
But for newly published research, scientists from around the world, including Sellers, teamed up to use artificial intelligence to identify and help control the invasive weed.
Eventually, scientists envision ranchers using this information to help reduce the herbicides they use to mitigate the invasive plant. Ranchers also can cut the cost to spray the chemicals.
The human eye can’t see smutgrass as well as a drone can.
Knowing that, Sellers, one of his former doctoral students and other researchers flew a drone over two pastures – one at, and one near the RCREC. They found they can use drones to identify small smutrgrass patches, which is the first step for site-specific weed control, where scientists can spray only small, infested areas of pastures.
“Right now, controlling smutgrass comes down to a rancher making a visual estimation, which can be off quite a bit if only a certain part of the pasture is inspected as opposed to the entire property,” Sellers said
In the study, the drones took thousands of images of smutgrass, and researchers used algorithms to teach computers to identify the weed from the images. From there, they discovered how much smutgrass covers an area.
Using the AI technology, researchers hope ranchers will eventually have the tools to be able to focus their chemical treatment on smaller, identified areas.
Cost-savings to ranchers depends on the level of infestation. As an example, it costs $5,000 to treat a 100-acre pasture, but spot treatment could cost $1,500, a savings of $3,500, Sellers said.
Because drones have GPS, scientists can use them to spray herbicides only on the areas that have been invaded by smutgrass. The amount of herbicide savings will depend on the level of smutgrass infestation in each field, but that data will come with future research.
Jose Dias, one of Sellers’ former doctoral students and a Ph.D. graduate of the UF/IFAS College of Agricultural and Life Sciences, said the study is a great first step toward precision weed management in improved pastures in Florida. One day, scientists hope to give ranchers the ability to use low-cost drones to map and treat smutgrass patches in their pastures. But more research needs to be done.
“We need to make the mapping process more user-friendly and integrate it with the drones that can read weed maps and to perform the precision spray applications only to the infested areas,” said Dias, an assistant professor and Extension weed science specialist at the University of Arizona and the lead author on the study. “The weed infestation maps could also be used by tractor-mounted or self-propelled sprayers that can read and use this technology.”
The mission of the University of Florida Institute of Food and Agricultural Sciences (UF/IFAS) is to develop knowledge relevant to agricultural, human and natural resources and to make that knowledge available to sustain and enhance the quality of human life. With more than a dozen research facilities, 67 county Extension offices, and award-winning students and faculty in the UF College of Agricultural and Life Sciences, UF/IFAS brings science-based solutions to the state’s agricultural and natural resources industries, and all Florida residents.
About AI at UF
The University of Florida is making artificial intelligence the centerpiece of a major, long-term initiative that combines world-class research infrastructure, cutting-edge research and a transformational approach to curriculum. UF is home to the most powerful, university-owned supercomputer in the nation, according to 2021 rankings released by TOP500, contributing to innovative research and education opportunities.