May 2023 Graduate Student Spotlight: Katherine Cheng

Katherine Cheng is a Ph.D. candidate at UC Davis.

Read on to learn about Katherine's adventures up and down the West coast and her passion for machine learning in earthquake engineering.

Tell us about yourself in a few words.

I received my B.S. at UC Berkeley in Civil Engineering, then worked in industry for a few years for Keller in ground improvement traveling up and down the west coast implementing everything from micropiles to soil mixing. I returned to pursue a M.S. at UC Davis in geotechnical engineering then switched to a Ph.D. after my 1st year as I enjoyed the research and learning I was experiencing.

What is your research about and why is it important?

My research focuses on the intersection of machine learning (ML) and earthquake engineering, with the usage of ML as a probe rather than a predictor. Earthquake induced phenomenon are often still not well understood, with multiple participating physical input factors that makes prediction of earthquake behavior of engineered structures difficult. With the advent of data sharing hubs and a push towards open-source datasets, there now exists more data to run these powerful ML algorithms on to connect potential input variables with predictions. By exploring these complex connections with an equally complex ML algorithm there is the potential to uncover new connections that were previously missed due to lack of data at the time of study.

Why did you choose UC Davis to pursue your degree?

As I had done my undergrad at UC Berkeley and had a strong mentorship and colleague network there already, I wanted to expand my viewpoints of the geotechnical world and opted to go to a different school for my graduate degree. UC Davis is one of the powerhouses of geotechnical engineering with an excellent spread of faculty all participating in various cutting-edge research, which allowed me to have a breadth of topics to pick from when it came time to decide on a research path (originally for my M.S. but expanded to my Ph.D.).

How would you describe your graduate life journey so far?

It has been quite slow and steady, as I had started in the pandemic year and did my entire 1st year online. My 2nd year I spent taking courses in statistics and machine learning in the other graduate departments, and now I am focusing on my research after passing my Qualifying Exam in February of this year. Time passes quicker than one would think.

What has been your favorite part of graduate school?

I enjoy having the time to truly think and delve into rabbit holes of research that would normally not be entertained when working in industry. The focus here is to research, regardless if it would make money or not, so there is less pressure to create a product to sell. Having this freedom is valuable, and many of the questions I had in my industry days have been answered during this time.

What do you think is the greatest challenge that graduate students face and how have you been able to address it?

I think the greatest challenge is balancing socialization and studying. My first year was slightly lucky in the sense that I had no opportunities for socialization due to being online only, so I spent all my time studying or sleeping and built a strong technical base. With the number of events and opportunities available at the graduate level, it’s hard to balance it all without compromising on another aspect. Being able to selectively say no to events to protect the time I have to research is something I had to adopt early on to keep up my research productivity while still participating in graduate school society.

What is your plan after graduation?

Currently I am interested in helping companies utilize the existing data they have with ML and statistical techniques to learn new aspects of their work and optimize their processes.

What advice do you have for current and prospective CEE graduate student?

Understand what skill sets you would like to polish or learn in graduate school and focus the courses and projects chosen to enhance these skills. For example, I wanted to learn statistics, so I chose a Ph.D. path that relies heavily on statistics to have the opportunities to learn and use this new skill.

These thoughts are written by Katherine Cheng.