UF/IFAS Scientists Use AI to Improve Strawberry Disease Detection

Clint ThompsonFlorida, Strawberry

Florida’s strawberry season doesn’t return until December. But University of Florida Institute of Food and Agricultural Sciences (UF/IFAS) researchers work year-round to support an industry with a $500 million-a-year farm-gate value in Florida.

Among their research endeavors, UF/IFAS scientists search for ways to help growers control diseases that threaten strawberries.

The AI system that uses an algorithm to detect leaf wetness on strawberries. Leaf wetness is an indication of fungal diseases. Courtesy, Daniel Lee, UF/IFAS

Most of Florida’s 13,500 acres of strawberries are grown in Hillsborough, Polk and Manatee counties. For more than a decade, Florida farmers have used the UF/IFAS-designed Strawberry Advisory System (SAS) to know when to spray fungicides that prevent plant diseases.

SAS works with data generated by Florida Automated Weather Network stations near farms – in this case, near strawberry fields. SAS uses leaf wetness duration to help growers estimate the risk of their fruit becoming infected with a fungal disease.

Documented Research

In newly published research, Won Suk “Daniel” Lee, a professor of agricultural and biological engineering and Natalia Peres, a professor of plant pathology, show how artificial intelligence (AI) can improve leaf wetness detection.

Continuous moisture and temperatures higher than 65 degrees Fahrenheit, provide growers a sign that damaging diseases are imminent.

Lee and Peres conducted the research at the Plant Science Research and Education Center in Citra, the Gulf Coast Research and Education Center in Balm and at farms in Dover and Plant City.

Scientists trained the algorithm to use the images and detect wetness. They found that AI technology improves the accuracy of wetness detection.

Nearly 96% of the time, the algorithm found moisture on the reference plate in comparison with manual observations, and a nearly 84% accuracy rate was observed when compared with the current sensors and models in SAS.

“Ultimately, we want to replace the current wetness sensors with an imaging system because the current sensors are difficult to calibrate and not always reliable,” said Lee. “Using the AI system, we can detect wetness and consequently forecast the disease better, so we can help growers. The implementation of this advanced detection system within SAS may improve decisions about fungicide applications and may facilitate the implementation of leaf wetness detection for disease forecasting to other crop systems.”

Source: UF/IFAS