For avocado lovers: This device designed by Harvard students predicts when an avocado will ripen
News > World
By STEM Caribbean | Posted on July 28, 2020
Of the many challenges around the world today, food wastage is among the most concerning. According to the Food and Agriculture Organization of the United Nations, every year, the amount of food lost or wasted could feed approximately 2 billion people.
A group of engineering students at Harvard University recently looked into ways to help lessen food waste. This was done for a school project that challenges students to come up with solutions to real-world problems using engineering. The students’ solution is a device that predicts when produce will be ripe. It was tested mainly on avocados.
A news release by Harvard highlights a report by the Natural Resources Defense Council (NRDC), which states that grocery stores and distributors are responsible for around 13% of food wastage in the United States. Product overstocking is one of the causes, which results in products becoming overripe with undesirable appearances, eventually causing them to be discarded.
According to the news release, the students decided to focus their efforts on the retail industry to address the considerable amount of food waste. They choose the avocado as a test subject, due to its high net value—grossing approximately USD 2.28 billion annually, a value which is predicted to have a growth rate of 10% per year.
“In order to prevent produce from being discarded, what we need is metrics in order to know which produce are going to ripen faster,” said project co-lead Mark Meneses.
Savormetrics, a company that develops biophysical and biochemical food analyzers, partnered with the students and provided support for the device. In the news release, Harjeet Bajaj, president and CEO of the company, expressed how impressed he was by the students’ work.
“Savormetrics will be polishing this off and bringing this product into market. I am very surprised at the efficacy of the students on our project,” he said. “We are planning on presenting a stock option opportunity to the students to bring this product to market, by providing them access to our office in Boston and other resources.”
The device uses sensors that measure specific chemical properties of avocados. The resulting information is integrated into a machine-learning model that predicts when the avocado will be ripe. The output from the model, such as the number of days until ripeness, is displayed on an app.
“Ripeness prediction is really difficult for avocados, and because they are so valuable, it is really a critical point for retailers,” said Juliet Nwagwu Ume-Ezeoke, one of the students involved in the project. “We hope this information would allow retailers to take very decisive actions.”
Despite the difficulties the students faced in developing the device, including transitioning to remote learning, the prototype produced 60% estimates accurate within one day and 30% within two days.
“The predictive model worked fairly well, which was great to see because we really weren’t sure with all of the moving parts in our project. The success of the modeling was contingent on our sensing approach and our avocado testing procedure which were both difficult to implement,” said co-lead Jonas LaPier.
The news release notes ways that this device could be useful in the retail industry. Retailers could display the level of ripeness of products to help consumers make purchasing decisions. Also, the retailers could set prices accordingly, discounting the riper produce.