Identifying Exoplanets with Deep Learning. III. Automated Triage and Vetting of TESS Candidates

Abstract

NASA's Transiting Exoplanet Survey Satellite (TESS) presents us with an unprecedented volume of space-based photometric observations that must be analyzed in an efficient and unbiased manner. With at least ∼1,000,000 new light curves generated every month from full-frame images alone, automated planet candidate identification has become an attractive alternative to human vetting. Here we present a deep learning model capable of performing triage and vetting on TESS candidates. Our model is modified from an existing neural network designed to automatically classify Kepler candidates, and is the first neural network to be trained and tested on real TESS data. In triage mode, our model can distinguish transit-like signals (planet candidates and eclipsing binaries) from stellar variability and instrumental noise with an average precision (the weighted mean of precisions over all classification thresholds) of 97.0% and an accuracy of 97.4%. In vetting mode, the model is trained to identify only planet candidates with the help of newly added scientific domain knowledge, and achieves an average precision of 69.3% and an accuracy of 97.8%. We apply our model on new data from Sector 6, and present 288 new signals that received the highest scores in triage and vetting and were also identified as planet candidates by human vetters. We also provide a homogeneously classified set of TESS candidates suitable for future training.

Nigraha: Machine-learning-based pipeline to identify and evaluate planet candidates from TESS

“…Our method differs from previously explored methods for constructing secondary views. Yu et al (2019) construct a secondary view by searching the light curves for the mid-point of the most likely secondary eclipse (i.e. masking the transits from the light curve and then using BLS to fit a box to find a transit) and then generate a binned/phase-folded view as input to their Astronetvetting model.…”

“…Of these systems, the Autovetter (McCauliff et al 2015), which is a random forest classifier that makes decisions based on the metrics generated by the Kepler pipeline, has been successfully used to E-mail: sriramsrao@gmail.com (SR); aam@astro.caltech.edu (AM) make initial dispositions for Kepler/K2 candidates. Convolutional neural networks (CNNs) that are effective at image recognition tasks have been explored as an alternate approach for classifying light curves (Pearson, Palafox & Griffith 2017;Ansdell et al 2018;Shallue & Vanderburg 2018;Zucker & Giryes 2018;Dattilo et al 2019;Schanche et al 2019;Yu et al 2019;Osborn et al 2020). These models use supervised learning with a CNN where the neural network learns the characteristics from light curves.…”

“…However, the systematics with individual TESS sectors are significantly different when compared to Kepler/K2 (viz., 27 d of data versus 4 yr/81 d of data). Hence, prior deep-learning approaches for classifying TESS data such as Yu et al (2019), Osborn et al (2020) adapt and modify Astronet and Exonet, respectively, and identify new candidates. Our work is similar in spirit in that we start with a hybrid of these two models and develop novel extensions that allow us to explore different aspects of the input parameter space to identify candidates.…”

A Habitable-zone Earth-sized Planet Rescued from False Positive Status

“…than the entire 10yr Kepler mission (Guerrero et al 2019). Expecting humans to keep up with such vast quantities of data is unsustainable, and automatic vetting techniques have already taken the bulk of the triage/vetting workload (Yu et al 2019;Guerrero et al 2019). However, as our rescue of Kepler-1649c reinforces, careful human inspection will remain valuable going forward.…”

SuperWASP dispositions and false positive catalogue

“…To help process the high rate of incoming data, automated methods are being developed to vet the TESS data, e.g. Yu et al (2019), Osborn et al (2019). However, these methods do not provide perfect classifications, and many false positives can be earmarked for further follow-up.…”