(Photo courtesy of Yiannis Ampatzidis, UF/IFAS)
University of Florida Institute of Food and Agricultural Sciences (UF/IFAS) researchers are using artificial intelligence (AI) to help citrus growers better forecast their seasonal yield.
A preliminary study showed that the AI technology predicts yields with 98% accuracy. That’s way better than the 75% to 85% accuracy growers get when they count trees manually, said Yiannis Ampatzidis, UF/IFAS associate professor of agricultural and biological engineering.
“Citrus yield predictions give growers, packinghouses and other distributors critical information before the farmers harvest the fruit,” said Ampatzidis, a faculty member at the Southwest Florida Research and Education Center. “Such predictions help growers know what resources such as workers, storage and transportation will be needed for the harvest.”
In a preliminary study presented to the American Society of Agricultural and Biological Engineers, UF/IFAS researchers showed how they used AI technology to generate two citrus yield-prediction models. So far, scientists prefer one of those models, which they tested during the 2019-2020 citrus harvest season. It combines data from unmanned aerial vehicles (also known as UAVs, or drones) with manually gathered ground-based data. Specifically, the technology uses an AI-based model that combines UAV multispectral images with ground-collected color – red, green and blue – images to predict citrus yield.
Currently, growers manually count fruit from randomly selected trees, then they harvest immature fruit from those trees. They use simple mathematical models to extrapolate and predict yield for a block, Ampatzidis said. Some growers also hire consulting companies to predict yield, he said. The accuracy of these traditional models varies, but is well below the 98% of the AI-based model.
UF/IFAS researchers used Agroview, a novel cloud-based technology that was named a UF Invention of the Year in 2020, to analyze the multispectral images and to determine tree characteristics, such as height, canopy size, leaf density and health, in addition to the number of fruit.
“We plan to continue this research, collecting more data to further develop and evaluate the model and this yield prediction technique,” Ampatzidis said.
Source: University of Florida Institute of Food and Agricultural Sciences
Share this Post
Sponsored Content