Researchers in MIT’s Open Agriculture Initiative grow basil under controlled environmental conditions to study how taste and other features are affected.
Machine learning to optimise growth and taste of plants
B BY HUGO CLAVER
otany, machine-learning algorithms and old-fashioned chemistry make plants taste good, according to re- searchers in the Massachusetts Institute
of Technology (MIT). They used computer algo- rithms to determine the optimal growing condi- tions to maximise the concentration of flavour- ful molecules, known as volatile compounds. According to researcher and director Caleb Harper of MIT’s OpenAg group, their goal is to design open-source technology at the intersec- tion of data acquisition, sensing, and machine learning, and apply it to agricultural research. “We’re really interested in building networked tools that can take a plant’s experience, its phe- notype, the set of stresses it encounters, and its genetics, and digitise that to allow us to under- stand the plant-environment interaction.”
Basil plants In their study of basil plants the researchers found that exposing plants to light 24 hours a day generated the best flavour. Traditional ag- ricultural techniques would never have yielded that insight. The OpenAg plants are grown in shipping containers that have been retrofitted so that environmental conditions, including light, temperature, and humidity, can be care- fully controlled. Once the plants were full- grown, the researchers evaluated the taste of the basil by measuring the concentration of volatile compounds found in the leaves. These molecules include valuable nutrients and anti- oxidants, so enhancing flavour can also offer health benefits. All of the information from the plant experi- ments was then fed into machine-learning al- gorithms that the MIT and Cognizant (formerly Sentient Technologies) teams developed. The
algorithms evaluated millions of possible com- binations of light and UV duration, and gener- ated sets of conditions that would maximise flavour, including the 24-hour daylight regime.
Networked science One goal of MIT is to overcome the secrecy in this industry by making all of the OpenAg hardware, software, and data freely available. “There is a big problem right now in the agri- cultural space in terms of lack of publicly avail- able data, lack of standards in data collection, and lack of data sharing,” Mr Harper says. “So while machine learning and artificial intelli- gence and advanced algorithm design have moved so fast, the collection of well-tagged, meaningful agricultural data is way behind. Our tools being open-source, hopefully they will get spread faster and create the ability to do networked science together.”
▶ FUTURE FARMING | 24 May 2019 7
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52
