I completed my master’s degree in Plant Sciences in 2018. My research project is entitled : ‘Development of a protocol for the proliferation of in vitro axillary buds in avocado (Persea americana) cv. ‘edranol’ ‘ (It can be found here).

This may sound like a mouthful, so simply put, I worked on methods of growing avocados using tissue culture for the purpose of conservation.

Back in 2018, I didn’t know much about Data Science. Even though my project was considered to be ‘Biotechnology’ it was more about the Bio and less about the Tech. This is to be expected as the role of a scientist is to understand biological systems, and technology is used as a tool to support this exploration.

Still, I think of my master’s project as my first Data Science project because it has similar components - identifying a problem, conducting research, designing experiments, collecting data, analysing the data and presenting findings.

My research was empirical and required a lot of experimentation. Every plant growth medium had to be tested and optimised, and I remember wondering if there was an easy way to go about this optimisation because it was practically impossible to test all the combinations of plant growth regulators, nutrients and vitamins.

After learning more about the capabilities of machine learning, I realise that this was perhaps the missing piece of the puzzle. Through collaboration with the available technology, it is possible to collect more data and discover deeper insights. And with this capability, I look forward to what the future holds.