With that in mind, Yiannis Ampatzidis is engaging artificial intelligence (AI) to develop a low-cost, smart tree-crop sprayer that can automatically detect citrus trees, calculate their height and leaf density, and count fruit. That way, growers target their spray more efficiently, so it lands on trees and leaves and reduces chemical use by about 30% compared to traditional spray methods.
“These smart technologies can save the fruit-tree industry millions of dollars per year by optimizing chemical applications,” said Ampatzidis, a University of Florida Institute of Food and Agricultural Sciences associate professor of agricultural and biological engineering. Ampatzidis works at the Southwest Florida Research and Education Center (SWFREC) in Immokalee.
Smart spray technology lets the grower vary the amount applied based on tree size and leaf density, and it will not spray if there is no tree or if a tree appears dead. It also does not spray if it finds other objects, such as a water pump, a pole or a person.
“This new technology will further enhance the tree-profiling systems we have in place today, with the ability to detect and only spray the target foliage,” Ampatzidis said. “Our data, collected by smart sensors, can control the amount of spray applied to the tree, in real time, and is stored in the controller to be downloaded for further processing.”
The system utilizes machine vision, GPS and a light detection and ranging (LiDAR) remote sensing system. Ampatzidis developed algorithms to process the data as well as software to control the sensors.
The technology, cited in new research Ampatzidis published, can also help farmers predict their crop yields. Ampatzidis conducted several experiments in citrus groves at SWFREC and in commercial groves and found the system used less pesticide and fertilizer.
Protecting citrus trees and their fruit makes up a significant chunk of any grower’s budget. In Southwest Florida orange groves, plant-protection product applications cost about 34% of the total production costs.
An industry partner, Chemical Containers Inc, has evaluated the technology and entered an agreement with UF Innovate | Tech Licensing to license and commercialize the smart spray technology.
As they continue to evaluate the system’s efficiency, Ampatzidis and his team will study how well it detects and sprays trees in groves with tall weeds.
“We also plan to develop smart fertilizer-spreader applicators to improve nutrient management,” he said. “Target-based management can help farmers apply nutrients as needed within the field, rather than applying fertilizers uniformly.”
Source: University of Florida Institute of Food and Agricultural Sciences
Share this Post