The Detection of KIC 1718360, A Rotating Variable with a Possible Companion, Using Machine Learning
Jakob Roche
TL;DR
The study addresses automated detection of exoplanet-like signals in stellar lightcurves using anomaly-detection approaches. It deploys a One-Class SVM with a nonlinear polynomial kernel to analyze Kepler KOI lightcurves, validated with Savitzky-Golay detrending, and cross-validated with TESS data. The analysis of KIC 1718360 reveals a robust rotational signal with $P_\mathrm{rot}=2.9376$ days observed across Kepler and TESS, and a secondary dip with $P_\mathrm{orb}=1.2156$ days suggesting a possible super-Earth companion, though confirmation is required due to activity-related noise. The work demonstrates cross-mission consistency and highlights anomaly-detection ML as a tool for uncovering under-catalogued rotating variables and potential exoplanets in stellar lightcurves.
Abstract
This paper presents the detection of a periodic dimming event in the lightcurve of the G1.5IV-V type star KIC 1718360. This is based on visible-light observations conducted by both the TESS and Kepler space telescopes. Analysis of the data seems to point toward a high rotation rate in the star, with a rotational period of 2.938 days. The high variability seen within the star's lightcurve points toward classification as a rotating variable. The initial observation was made in Kepler Quarter 16 data using the One-Class SVM machine learning method. Subsequent observations by the TESS space telescope corroborated these findings. It appears that KIC 1718360 is a nearby rotating variable that appears in little to no major catalogs as such. A secondary, additional periodic dip is also present, indicating a possible exoplanetary companion.
