Did you know that there’s a job in the banana industry called a ripener?
It makes sense, right? After all, anyone who eats bananas knows the time it takes to go from rock-hard green banana to brown mushy mess can be as short as a week. This means the banana industry has to work hard to ensure bananas ripen at the right time so they are peaking in bright, beautiful yellow by the time they show up on grocery store shelves.
Like many jobs, the ripener role relies heavily on judgment. Not that they don’t use some modern tools when monitoring and managing the ripening cycle of the banana, but from the looks of it, the ripener job seems ripe (sorry) for a Moneyball-style analytics and technology revolution.
Enter Strella. The company, which has gained traction in the apple industry for its IoT monitoring technology over the past few years, has gone bananas. According to company CEO Katherine Sizov, the company’s new AI-powered model helps them (and those working as ripeners) better decipher the signals the bananas send.
“We’ve built a machine learning model that helps us get bananas from that green to that perfectly yellow color every single time,” Sizov told The Spoon. “And the way that we do that is we measure what the bananas are telling us.”
According to Sizov, the hardware they use for banana monitoring is the same as for apples. The difference is software.
“The hardware is the same, but the algorithms are different,” Sizov said.
Sizov says that whether it’s apples or pears (fruit with longer ripening cycles) or avocadoes or bananas (fruit with shorter ripening cycles), the key indicators sending signals around the ripening stage are ethylene and CO2 emitted from the produce. The Strella hardware module has eight different sensors, sensing ethylene, CO2, and other environmental factors such as heat and moisture.
And just as with apples, the Strella technology can help determine what exactly is needed to slow down or accelerate the ripening cycle of a banana. The only difference is that things move much more quickly with bananas or avocados, which is why a job explicitly focuses on managing the process of ripening the produce.
“Unlike bananas, apples are picked perfect off the tree,” Sizov said. “And they can last a whole year in gigantic storage rooms.”
With bananas or avocadoes, the ripening process is much more closely managed. They are picked before they are ripe and then stored cold to slow the ripening until they get near the point of consumption. From there, they go into ripening rooms, and the ripener introduces ethylene gas and CO2 and adjusts the temperature to kick the ripening process into gear. And now, according to Strizov, Strella’s new banana and avocado machine-learning algorithms can help determine precisely how much of each is needed to adjust the ripening cycle to get the desired output.
Should ripeners be worried about technology taking their jobs away? Sizov doesn’t think so.
“When people are very good at their jobs, they’re always looking for tools to do better,” Sizov said. “Ripeners have a ton on their plate, they’re working 12 to 14-hour shifts, so I think they’re always looking for ways to get a little more sleep. Our tool is one way to do that.”
According to Sizov, Strella has worked with 85% of the US market for apple and pears suppliers and estimates the company has saved 20 million pounds of apples and pears from going to waste. Now, she hopes they can replicate that success in bananas and avocados.
“We’re growing pretty quickly, and we’re excited to get into bananas and avocados after having had our foray into apples for five years now.”
If you’d like to hear Katherine discuss how AI can perfect the ripening of bananas, she will be speaking at the Spoon’s Food AI Summit on October 25th in Alameda, CA! Get your early bird tickets today!
Leave a Reply