MIT researchers hacked into agriculture to create what could be the tastiest basil in the world

Want the best Caprese salad or pesto you've ever tasted?

The MIT researchers say that they might be able to help. They say they created what could be the most delicious basil ever developed, after testing different light conditions on the plants.

Their surprising discovery: a 24-hour light is the most succulent herb.

But the researchers also say that it's not what they learned about basil, it's how they got their results that's important.

The researchers, who published their findings on Wednesday in the journal PLOS One, grew 2,000 plants in an expedition container and varied lighting conditions, including color, intensity and intensity. the duration.

They also collected plant data as they grew under various conditions, including analyzing plant chemistry with gas chromatography and mass spectrometry, said Caleb Harper, principal investigator at the Media Lab. MIT and Director of the Open Agriculture Initiative.

The researchers then introduced the data into machine-learning algorithms and asked the computer what growth conditions, or "climate recipes," would produce the tastiest basil, defined by the volatile compounds measurements in the leaves of the plant.

"We were trying to use the machine to learn to learn to change the climate," said Harper, one of the lead authors of the paper. "Could he look at all these variables and come up with alternative recipes that would change the climate to express more what we wanted?"

The experiment was a "proof of concept", he said, showing that "we can use a controlled environment and machine learning to predict the forward-thinking flavor".

No genetic modification was involved. The researchers simply optimized the growing conditions for the production of a plant with certain properties.

According to John de la Parra, director of research for the Open Agriculture group and author of the study, the suggestion of algorithms that 24-hour light was the optimal condition for obtaining a delicious basil would not have been discovered.

"You could not have discovered that otherwise. Unless in Antarctica, there is no 24-hour photoperiod to test in the real world, "he said in a statement from the university. "You had to have artificial circumstances to discover that."

The method "allows to discover new and unforeseen [growth] recipes that can produce better results, "said the study." It can find growth recipes both effective and surprising – and difficult and time consuming to find through traditional hand-crafted experiences. "

Researchers are working to determine the optimal conditions for growing basil plants containing more compounds that can help fight diseases such as diabetes. They are also interested in using this approach to increase yields of medicinal plants such as Madagascar periwinkle, which is the only source of anticancer compounds, vincristine and vinblastine, the university said.

"You can see this document as the starting point for many applications that can be applied.This is an exhibition of the power tools we have built so far," said of the Parra. "It was the archetype of what we can now do on a larger scale."

While the basil study focused on the effect of light conditions, researchers are also studying how to adjust other variables affecting plant growth, including temperature, humidity, atmospheric carbon dioxide, bacteria and the nutrients of the plants. a plant to grow, "said Harper.

The Open Agriculture Initiative has developed "personal computers for food", temperature-controlled housings that can be used to grow plants under specified conditions and monitor their progress. , all data is returned to the cloud. Hundreds of PFCs are currently in use, including middle and high school students who are taking science classes.

Harper hopes that thousands of researchers, amateurs, students and others will one day use thousands of software packages that will generate an open source mine of the impact of growing conditions on plants.

"I want thousands of people to work with us," he said. And when the data was analyzed, he asked: "What will we discover about the plants around us?"