UF/IFAS Digital Twin Simulates Strawberry Farms, Enhances AI and Reduces Costs
UF/IFAS Digital Twin Simulates Strawberry Farms, Enhances AI and Reduces Costs
Florida’s strawberry production runs from November through April, but with digital twin technology, The University of Florida Institute of Food and Agricultural Sciences (UF/IFAS) researchers simulate growth year-round, accelerating innovation.
Digital twins are virtual replicas of physical systems that allow researchers to model interactions and predict outcomes in simulated environments.
Dana Choi (in the feature picture) and her team at the University of Florida have proven the effectiveness of their AI-powered robotic system. It saves time and labor—vital to Florida’s $500 million strawberry industry and the $2 billion national market.
Choi, assistant professor of agricultural and biological engineering at the UF/IFAS Gulf Coast Research and Education Center, built a full-scale virtual replica of a strawberry field. The simulated farm, modeled after one in Hillsborough County, includes every row, leaf, and berry.
Their robot navigated the virtual field, capturing thousands of images. The research shows that AI trained entirely on this digital twin environment reached 92% accuracy in fruit detection—without real-world data.
“With computer-simulated fields never out of season, we can develop berry-detection tools in summer, cutting costs and speeding up progress,” Choi explained. New technology like robotic pickers or smart sprayers can be tested virtually, reducing the cost of real-life trials.
In another result, the robot trained on synthetic images estimated fruit diameter with just 1.2mm error—accurate enough for commercial grading using simulated data alone.
This confirms that virtual training can support AI models in tasks like yield prediction and fruit classification based on size and quality.
Knowing fruit size and volume in advance enables growers to forecast yields and plan harvests efficiently.
“The study shows how digital twins can fast-track AI tools for strawberry farms, making robotics innovation faster and more affordable,” said Choi.
“Without digital twins, we’d need thousands of field photos, each labeled, and we’d have to wait for the right season. It’s costly and time-consuming,” she added. “Now, we generate and label images instantly.”
Training AI in virtual environments also removes the need for real photo handling and labeling, saving weeks of effort.
Ultimately, this technology helps create, test, and refine tools virtually before deploying them in real life—cutting costs and accelerating development.
The platform can also be used for operator training and rapid prototyping of autonomous farm machines, improving the transition from concept to field.
ABOUT UF/IFAS
The University of Florida Institute of Food and Agricultural Sciences (UF/IFAS) advances knowledge in agriculture, natural resources, and human systems to enhance quality of life. With 67 Extension offices, over a dozen research facilities, and a top-tier College of Agricultural and Life Sciences, UF/IFAS supports Florida’s agri-industries and communities. This is a remarkable breakthrough in technology for manufacturing of goods and serves.
More info here – Have a Story? Submit it here
Disclaimer
The information provided in this article is for general informational purposes only and from publicly available sources. While we strive for accuracy, we do not make any representations or warranties, express or implied, regarding the completeness, reliability, or validity of the content. This article does not make any direct claims about specific companies, individuals, or organizations. Any references to reports or external sources are for context and do not imply endorsement or verification of any specific allegations. Readers are encouraged to conduct their own research and seek professional advice before making business decisions. We disclaim any liability for any losses or damages incurred as a result of reliance on the information provided.