I am a planetary scientist and space physicist at the University of British Columbia’s Data Science Institute and Earth, Ocean and Atmospheric Sciences department (DSI, EOAS). I am passionate about applying and developing statistical techniques to enable data-driven discovery in Earth and planetary sciences. My work naturally draws from techniques in statistics, data visualization, and computer science.

Most of my work focuses on understanding current planetary space environments, and their previous conditions, by studying newly available large datasets from planetary missions. My current research is focused on analyzing spacecraft data and physical models with machine learning to understand current and past planetary conditions on the solar system planets including Mars.

I was formerly at the University of California Berkeley’s Space Sciences Lab (SSL) supported by the MAVEN mission and a new NASA program in interdiscplinary AI applications. My PhD thesis focused on developing interpretable methods for machine learning in planetary science with applications to plasma transport around Saturn and was supported by an NSF Graduate Research Fellowship and a NASA Earth and Space Sciences Fellowship.

I am interested in supporting the use of statistical and large-data methods for science and developing educational resources in these practices. These efforts have included co-creating the Machine Learning for Planetary Space Physics seminar series, leading a community generated white paper for incorporating machine learning in planetary science for the next decade of missions, and serving on the Planetary Data Ecosystem Independent Review Board Subcommittee on Mining and Automation. Additionally, I have co-developed a geoscience visualization and statistics course for physical science students new to computer programming which received an award from the University of Michigan for outstanding instruction.