NotPlaNET: Removing False Positives from Planet Hunters TESS with Machine Learning

TL;DR

This paper presents NotPlaNET, a CNN-based method that effectively filters false positives from TESS exoplanet candidate data, significantly reducing manual vetting while maintaining high detection accuracy.

Contribution

We develop a CNN model trained on citizen scientist-labeled TESS light curves that accurately distinguishes false positives from true exoplanet signals, improving efficiency in exoplanet detection.

Findings

Median false positive flag rate of 18% across test sectors

Model retains 100% of known planets in most sectors

Potential to reduce manual vetting by up to one-third

Abstract

Differentiating between real transit events and false positive signals in photometric time series data is a bottleneck in the identification of transiting exoplanets, particularly long-period planets. This differentiation typically requires visual inspection of a large number of transit-like signals to rule out instrumental and astrophysical false positives that mimic planetary transit signals. We build a one-dimensional convolutional neural network (CNN) to separate eclipsing binaries and other false positives from potential planet candidates, reducing the number of light curves that require human vetting. Our CNN is trained using the TESS light curves that were identified by Planet Hunters citizen scientists as likely containing a transit. We also include the background flux and centroid information. The light curves are visually inspected and labeled by project scientists and are minimally pre-processed, with only normalization and data augmentation taking place before training. The median percentage of contaminants flagged across the test sectors is 18% with a maximum of 37% and a minimum of 10%. Our model keeps 100% of the planets for 16 of the 18 test sectors, while incorrectly flagging one planet candidate (0.3%) for one sector and two (0.6%) for the remaining sector. Our method shows potential to reduce the number of light curves requiring manual vetting by up to a third with minimal misclassification of planet candidates.