Researchers Use Machine Learning To 'Optimize' Flavor Of Basil


A new kind of basil plant with more delicious flavors has been grown during the recent study made by MIT's Media Lab.

In their first bout of "cyber agriculture," the research yielded the most optimized and ideal growing conditions needed by basil plants to grow in their most superior state.

The results were made using machine-learning algorithms, a little bit of chemistry, and the principles of botany. Dubbed as "cyber agriculture," producing basil plants with stronger flavors was just the first goal.

Because of its success, the researchers are now aiming to study and research other possibilities of the field, such as helping farmers adapt their growing techniques to climate change and increasing human disease-fighting properties of various herbs.

Digitizing Plant-Environment Interaction

"Our goal is to design open-source technology at the intersection of data acquisition, sensing, and machine learning, and apply it to agricultural research in a way that hasn't been done before," says Caleb Harper, principal research scientist in MIT's Media Lab and director of the OpenAg group.

"We're really interested in building networked tools that can take a plant's experience, its phenotype, the set of stresses it encounters, and its genetics, and digitize that to allow us to understand the plant-environment interaction."

Utilizing Artificial Circumstances

In the April 3 issue of PLOS One, it was stated that exposing the basil plants to light 24 hours a day is what made them more flavorful, doubling its flavorful molecules known as "volatile compounds." It was quite a surprising result, as according to John de la Parra, the research lead for the OpenAg group, there is no other way possible for this data to be discovered.

There is no place on Earth, aside from Antarctica, where light shines for 24 hours a day. As everyone knows, Antarctica's environment is not necessarily the best place to grow crops. Only by using the artificial circumstances involved did they deduce the said results.

Working Beyond Flavor

Although the experiment was successful, the researchers were happier that the software and platform they used works and are validated. Now, they are moving on to more ambitious experiments, such as increasing the production of medicinal plants and carrying out trials on exposing plant hormones or other nutrients on different plants and crops.

De la Parra is hopeful that this new field of study would yield more exciting discoveries in agriculture such as adapting to climate change. If successful, the traditional way of food production would be harnessed more efficiently, something to look forward to in the 21st century.

ⓒ 2018 All rights reserved. Do not reproduce without permission.
Real Time Analytics