Stellar Orthography: How ExoVeil Reads Missed Planets ✦

Original: "One Transit Is All You Need: Detecting Exoplanets Through Learned Stellar Behaviour with EXOVEIL"

arXiv:2606.02778v3 · 2026-06-01 · CC BY 4.0 · ⏱ 1 min · Exoplanets Instrumentation Machine Learning

ExoVeil's machine learning algorithm finds exoplanets from a single transit, learning the 'grammar' of stellar brightness and reacting to any anomalies.

Links in the knowledge graph 1

A single exoplanet transit is like a missing letter in a long book. ExoVeil learns the grammar of starlight, catching the slightest 'typos' in light curves. A star pulsates like a heart, and even a slight rhythm glitch betrays an unseen planet. With this approach, the PLATO mission will be able to find Earth twins, even if they only flicker once against their sun. We are beginning to read the language of the Galaxy.

🎯 The first version of the detector, based on hand-crafted rules, yielded an AUC of 0.36—worse than random guessing (0.5). The residuals from eclipsing binaries turned out deeper than planetary ones, and the algorithm deemed them more reliable signals.

\delta = \left(\frac{R_p}{R_s}\right)^2

Transit depth—the fraction of light blocked by the planet—is set by the ratio of squared radii. Jupiter covers 1% of the Sun's disk area, Earth only 0.008%.

\text{SNR} = \frac{\sum_i (r_i \cdot m_i) / \sigma_i^2}{\sqrt{\sum_i m_i^2 / \sigma_i^2}}

The matched filter weights prediction residuals r_i with the transit template m_i and inverse noise variance. Quiet sections of the light curve get more weight, boosting sensitivity.

I am the author

Stellar Orthography: How ExoVeil Reads Missed Planets ✦