Patrick Kasl

About Me

I primarily use a scientific Python stack: Numpy, Scipy, Pandas, Sklearn, and PyTorch. Academic data scientists get to wear a lot of hats. Across many of my projects (see my CV for more details!), I learned to focus on data-cleaning and -engineering prior to model development. I particularly enjoy the marriage of creativity and technology that is creating beautiful data visualizations.

I am currently a PhD student in the Department of Bioengineering at the University of California–San Diego. My academic research focuses on the development and application of novel machine learning models for illness onset detection using wearable device data. I am honored to be advised by Prof. Benjamin Smarr and work with all the amazing and talented people in the Smarr Lab. Previously, I studied Biomedical Engineering at the University of Wisconsin–Madison, where I was the 2020 Theodore Herfurth Awardee. I was also a student athlete on the football team there (On Wisconsin!).

2022-23 Bioengineering Graduate Society (BEGS) President.

I am also an ardent urbanist. By studying place, we can start to understand how our built environment affects our lives. In my free time, I enjoy learning more about the public transportation in the city I live in. I particularly admire some of the data science work by other practitioners in the public transportation realm (i.e., Nate Wessel). Real-time GTFS data is also a rich source of of data that I use to develop my skills with real-time, online algorithms (see below). As far as I know, no one outside the public transit agencies logs real-time GTFS data. I've been querying and storing San Diego's real-time GTFS data since early 2023 and am using it to develop better arrival time prediction algorithms. If you or someone you know is doing something similar in San Diego or any other city, please reach out to me, I would love to talk with them! (Note: the below display of San Diego's trolley locations sometimes breaks when the MTS updates their trip IDs. I check this website periodically, but certainly don't depend on it for a regular commute.)