Skip to main content

Machine Learning Lunch Meeting

Can ML help me find an exoplanet in my data?

Event Details

Thursday, April 18, 2024
1 p.m.

Everyone is invited to the weekly machine learning lunch meetings, where our faculty members from Computer Science, Statistics, ECE, and other departments will discuss their latest groundbreaking research in machine learning. This is an opportunity to network with faculty and fellow researchers while learning about the cutting-edge research being conducted at our university. See for more information.

Speaker: Jessi Cisewski-Kehe (STAT)

Abstract: Thousands of planets have been discovered orbiting stars other than our Sun (i.e., exoplanets) contributing to an improved understanding of our universe.  However, a critical challenge remains related to the limited number of low-mass exoplanet detections.  When a planet has a low mass (akin to the mass of the Earth or lower), the small signal is difficult to detect. Furthermore, stellar activity may hide a planetary signal or mimic a planetary signal leading to false detections.  

Though a variety of methods have been developed to address these challenges, a sufficient and general methodology to uncover the population of low-mass exoplanets is not available.  During this presentation, I plan to introduce the statistical/ML/data science challenge in the detection of low-mass exoplanets in the presence of stellar activity using extreme precision radial velocity spectra.  I will discuss some approaches that have promising results, but hope to hear from you of possible new ideas for solving this important problem in astronomy!