Jeroen Audenaert

Jeroen obtained his PhD in Artificial Intelligence for Astronomy & Astrophysics from KU Leuven (Belgium) in 2023, of which he spent the last year at MIT. He also holds a M.Sc. in Artificial Intelligence, and M.Sc. and B.Sc. in Commercial Science. Jeroen’s research focuses on the development of machine learning techniques to gain insights into the millions of stars that are being observed by space missions and large ground-based surveys. He is in particular using machine learning to classify the photometric light curves that are being observed by NASA’s Transiting Exoplanet Survey Satellite (TESS) according to their stellar variability types. These space-based photometric observations and classifications (from e.g, TESS, Kepler, PLATO, Gaia,..) can then also be combined with ground-based spectroscopic observations (from e.g, HERMES, SDSS,..) to form the basis for novel data-driven architectures that aim to probe the physics of pulsating stars. Pulsating stars are the focus of the field of asteroseismology, and are of prime importance for astrophysics as they can be used to improve stellar structure and evolution models. Hence, by first classifying the observed stars according to their physical characteristics and then using this information to determine their astrophysical parameters in more detail, we can ultimately try to unravel their complete physical structure and gain a better understanding of the evolution of stars. This not only improves our understanding of physics of stars, but can also provide us with new insights into their role as exoplanet host stars.