CDT Student Interviews – Spotlight on Luana Parsons Franca

Published on

Image of Luana
Luana Parsons Franca

In October 2020, LIV.DAT welcomed its 4th cohort of students into the Centre. Since they started their PhD’s, we have asked them a few questions as part of the CDT Spotlight Interview series. This will give you a more personal insight into work, motivation and challenges of our new students. Be sure to have a look at their personal profiles as well.

For the final interview in the Cohort 2020 Spotlight series we have spoken with Luana Parsons Franca who is using machine learning in her research into the optimization of Secondary Emission Monitors (SEMs) at the Super Proton Synchrotron (SPS) at CERN. The SPS provides beams for the Large Hadron Collider as well as for other CERN experiments such as AWAKE. Some of these experiments require slow extraction and the slow extraction lines SEMs are used for an in detail characterization of the primary beam. Luana’s project is split between the University of Liverpool/Cockcroft Institute and CERN.

Why are you interested in Physics?

“I am curious about understanding the fundamental processes and interactions that exist in the universe. I like to know how things work, how they came to be discovered and where they will progress. I am fascinated by the evolving nature of science and how new discoveries come to change and shape our understanding and perception of the world we live in.”

How did you end up in Liverpool?

“I applied to study in Liverpool for my undergraduate. I really enjoyed my time studying Physics at the University of Liverpool. When I was ready to apply for a PhD I was lucky enough to find a position that very closely matched my interests, combining both accelerator physics and data science. This position happened to be in Liverpool, so I returned.”

Which contribution to your field do you consider to be the most significant? 

“There are many developments that I consider to be important, but if I had to pick one it would be the introduction of machine learning techniques for accelerator applications. From what I understand this is not a new idea, but only recently have we had the computational power necessary to make these techniques fast enough to be useful for many accelerator applications. These techniques are beginning to revolutionise the field of accelerators and I am excited to see what new developments will be proposed as a result in the coming years.”

What do you hope to contribute to your field?

“As far as I am aware the use of machine learning in optimising accelerator diagnostics, is a relatively new and quickly expanding field. I hope to successfully apply data analysis and machine learning techniques to optimise secondary emission monitors, showcasing the potential of these data analysis tools, and in doing so be a part of the larger ongoing process of incorporating machine learning into accelerator design and control.”

Where do you hope to end up after your PhD?

“I am currently in the process of deciding this. I like to let my experiences inform my plans for the future and to be open to new ideas and opportunities that present themselves along my career path. I imagine I will either continue with my career in research or start a career as a data scientist working in industry. The most important consideration for me, is that I continue to work in a field with interesting problems, that challenge my understanding and push me to grow my knowledge and skills.”

Why do you think Big Data is important?

“Data has always been at the heart of research and innovation. Historically data collection and analysis was a slow and lengthy process. Recently possibilities for data collection and sharing have advanced tremendously, giving us unprecedented access to data at ever increasing speeds. Access to data on this scale opens the door to many exciting new applications and will accelerate development in many areas, but data alone will not give us insights. We need strategies to select, process and analyse the data, in order to draw conclusions, make predictions and extract useful information. The challenge is how do we go about processing increasingly large and complex data sets? This is a field with many challenges and interesting opportunities that will play a big role in shaping our future.”