A doctoral student at Florida State University is working to address food waste by using artificial intelligence to assess avocado quality. Zhengao Li, a Ph.D. candidate in measurement and statistics, collaborated with researchers from Oregon State University to develop a smartphone-based AI system that predicts the firmness and internal quality of avocados.
Their research was published in Current Research in Food Science and received support from the U.S. Department of Agriculture’s National Institute of Food and Agriculture.
Li explained his approach: “The biggest thing I learned was how to connect model performance with real scientific processes. From collecting samples, preparing Raman spectra and image data, training the model, to checking how the model explains its results, I learned that every step should reflect how fruits move from being ripe to spoiled.”
The team used 1,400 images of avocados collected over eight days at room temperature. Firmness measurements were taken using a texture analyzer as an indicator of ripeness. The AI system predicted firmness with nearly 92 percent accuracy and determined whether avocados were fresh or rotten with just over 84 percent accuracy.
Avocados were chosen for this study because they have a high waste rate—about 40 percent—while maintaining strong market demand. In the United Kingdom alone, more than 50,000 tons of avocados are wasted annually due to challenges in managing their freshness. The global avocado market is projected to reach $23 billion by 2029.
According to Li, “If used widely, the system could help farmers avoid harvesting too early or too late, help companies plan stock rotation and delivery, and help consumers judge ripeness more accurately.” He added, “In the long run, this can support a more sustainable and less wasteful food system.”
Li believes there is potential for expanding this technology beyond avocados: “The system now uses both visual and spectral data to tell how ripe food is and whether it has any damage or dryness,” he said. He noted that future models could operate on smaller devices for real-time detection across different types of food by adjusting specific features for each product.
At Florida State University (FSU), Li works as a research assistant in both the Educational Psychology & Learning Systems department at Anne Spencer Daves College of Education, Health, and Human Sciences (Anne’s College) and previously in FSU’s Department of Health, Nutrition, and Food Sciences. He earned his master’s degree in computer science earlier this year.
“This research is my starting point for learning more about how to make AI models smaller, faster and more reliable.” Li said. “In my Ph.D., I plan to focus on topics like model compression, knowledge transfer, reinforcement learning and interpretability. I want to find ways for AI models to stay accurate while using fewer resources.”
More information about Anne’s College can be found at annescollege.fsu.edu.
