MIT researchers use machine learning to grow better basil

A study found that providing light 24-hours-a-day leads to the tastiest basil plants

Spotted: Researchers from MIT are growing better basil, with no help from genetic modification. Instead, they used machine learning to determine optimum growing conditions (24-hour exposure to light helps). The plants were grown in modified shipping containers. The environmental factors – like temperature, light, humidity – were controlled automatically. The study’s findings were published earlier this month.

“We were trying to use the machine learning to learn how to change the climate,” Caleb Harper, principal research scientist at MIT’s Media Lab, told the Boston Globe. “Could it look through all these variables and come up with alternative recipes that would change the climate to express more of what we wanted?“

The team will use the data from the basil project to study how to improve plants’ ability to fight diseases. The data will also be used to study how plants could respond to climate change.