Avocados are delicious, good with a variety of meals and nutrient-dense. But I don’t buy them anymore. Without a doubt, I’ve pitched whole avocados more than any other produce. Why? Because there’s seemingly only a 15-second window between when the avocado is rock hard and complete mush. And I always miss it.
But those days may be numbered and it’s shockingly thanks to AI.
Researchers at Oregon State University and Florida State University have developed a smartphone-powered AI that can tell exactly when an avocado is perfectly ripe. Using more than 1,400 iPhone photos of Hass avocados, the team trained a deep-learning model that can predict firmness, the key sign of ripeness, with over 90% accuracy. The AI analyzes subtle cues in texture, color and shape that most humans would miss.
“Avocados are among the most wasted fruits globally due to overripeness,” said Luyao Ma, an assistant professor at OSU. “Our goal was to create a tool that helps consumers and retailers make smarter decisions about when to use or sell avocados.”
Food waste is one of the most critical global issues. Nearly a third of everything grown, harvested and produced for human consumption never makes it to the table and goes to waste. In the US, federal agencies have pledged to cut that loss in half by 2030, a goal that calls for innovation across the food system, such as an app that can tell you when it’s time to eat a fruit.
“Avocados are just the beginning,” Ma said. “This technology could be applied much more broadly, helping consumers, retailers and distributors make smarter decisions and reduce waste.”