Title: "Finding Needles in the Haysatck: Outlier Detection for Astronomical Light Curves Using Machine Learning" 

Rafael Martínez-Galarza, Center for Astrophysics | Harvard & Smithsonian

Upcoming large observational time-domain surveys such as the Large Synoptic Survey Telescope (LSST) and the Transiting Exoplanet Survey Satellite (TESS) will produce millions of regularly- and irregularly-sampled astronomical light curves. The enhanced sensitivity and time-sampling strategies of these surveys will open new discovery windows in diverse  fields of astronomy, from exomoons to precision cosmology. The large volume of the resulting datasets, however, implies that processing, classification, and interpretation of the light curves will require sophisticated algorithms involving statistical learning. In this context, one important question to answer is: how do we discover the unexpected when we are presented with a large dataset? How do we find scientifically interesting light curves (or any kind of astronomical data) that are not explained by current models? In this talk I will discuss state-of-the-art anomaly detection methods that use machine learning to find needles in this upcoming haystack of data, and will show the results of applying them to a dataset of Kepler light curves. After a brief introduction to machine learning and its application in time-domain astronomy, I will delve into the workings of two methods: Unsupervised Random Forest and Persistence Homology. I will then show how these methods can be adapted for time-domain astronomy, and present the results of applying them to a large dataset of Kepler light curves. I will describe the astrophysical implications of our findings in terms of where the most extreme outliers live in the Hertzprung-Russell diagram, and discuss the potential of the algorithms for discovery in the era of large astronomical datasets.