Automated Exoplanet Transit Detection from Stellar Light Curves

Tommaso Dall'Amico, Mikhail Kuvakin, Lamat Foschini Antichi

Keywords: Time Series Intelligence, Transit Photometry

Abstract:

The discovery of exoplanets is a crucial frontier in modern astrophysics. It expands our understanding
of planetary formation, contextualizes the uniqueness of our own solar system, and drives the search
for potentially habitable worlds. Just as ancient explorers like Herodotus gathered knowledge about
islands of habitability outside the known world, modern astronomers seek out habitable zones beyond
our local cosmic neighborhood. Until recent years, the field relied heavily on classical approaches
and manual interpretation of potential exoplanet candidates. These methods are labor-intensive,
subject to human error, and often struggle to isolate weak signals hidden in noise. The recent
introduction of Machine Learning has driven significant progress, leading to the automated discovery
of many new potential exoplanets. In this course project, we aim to contribute to this intersection of
Planetary Science and ML by bringing state-of-the-art Time-Series Intelligence techniques into the
existing framework of exoplanet discovery. Specifically, we plan to focus on the automated search for
smaller exoplanets with weak or non-periodic transit signals, which are currently difficult for existing
architectures to recognize.

Submission Number: 8