Traditional data collection for pest and disease detection relies on manual sampling, which can be time consuming and labor intensive. But now, Florida citrus growers could have artificial intelligence (AI) technology to simplify the process, better care for their crops and save money.
Yiannis Ampatzidis, University of Florida Institute of Food and Agricultural Sciences (UF/IFAS) assistant professor, discussed several new technologies during a Sept. 15 virtual citrus seminar. The UF/IFAS Southwest Florida Research and Education Center hosted the event.
The Agroview system developed by Ampatzidis and his team utilizes AI along with images from drones, satellites and from the ground to assess plant stress, count and categorize plants based on their height and canopy area, and estimate plant nutrient content. According to Ampatzidis, Agroview can reduce data collection and analysis time and cost by up to 90 percent compared to manual data collection.
During experimental trials, the system was tested on a large-scale commercial citrus grove with 175,977 citrus trees on 1,871 acres. In the experiment, Agroview achieved an overall tree detection error of 2.29 percent in addition to estimating tree height and canopy area with high accuracy.
Ampatzidis also touched on a smart sprayer system using AI technology, which would greatly benefit citrus growers. He said the issue with most smart sprayer systems is that they have only been able to detect tree height, not leaf density. In other words, even dead trees get sprayed.
A newly developed smart sprayer system utilizes AI to detect leaf density with high accuracy (over 95 percent) to determine the amount of chemicals to apply to a given tree. Ampatzidis said his team is also working to develop a yield prediction model based on drone-collected information.
Ashley Robinson, AgNet Media communications intern, wrote this article.