Accurately and rapidly classifying exoplanet candidates from transit surveys
is a goal of growing importance as the data rates from space-based survey
missions increases. This is especially true for NASA's TESS mission which
generates thousands of new candidates each month. Here we created the first
deep learning model capable of classifying TESS planet candidates. We adapted
the neural network model of Ansdell et al. (2018) to TESS data. We then trained
and tested this updated model on 4 sectors of high-fidelity, pixel-level
simulations data created using the Lilith simulator and processed using the
full TESS SPOC pipeline. We find our model performs very well on our simulated
data, with 97% average precision and 92% accuracy on planets in the 2-class
model. This accuracy is also boosted by another ~4% if planets found at the
wrong periods are included. We also performed 3- and 4-class classification of
planets, blended & target eclipsing binaries, and non-astrophysical false
positives, which have slightly lower average precision and planet accuracies,
but are useful for follow-up decisions. When applied to real TESS data, 61% of
TCEs coincident with currently published TOIs are recovered as planets, 4% more
are suggested to be EBs, and we propose a further 200 TCEs as planet
candidates.
Description
Rapid Classification of TESS Planet Candidates with Convolutional Neural Networks
%0 Generic
%1 osborn2019rapid
%A Osborn, Hugh P.
%A Ansdell, Megan
%A Ioannou, Yani
%A Sasdelli, Michele
%A Angerhausen, Daniel
%A Caldwell, Douglas A.
%A Jenkins, Jon M.
%A Räissi, Chedy
%A Smith, Jeffrey C.
%D 2019
%K Methods
%T Rapid Classification of TESS Planet Candidates with Convolutional Neural
Networks
%U http://arxiv.org/abs/1902.08544
%X Accurately and rapidly classifying exoplanet candidates from transit surveys
is a goal of growing importance as the data rates from space-based survey
missions increases. This is especially true for NASA's TESS mission which
generates thousands of new candidates each month. Here we created the first
deep learning model capable of classifying TESS planet candidates. We adapted
the neural network model of Ansdell et al. (2018) to TESS data. We then trained
and tested this updated model on 4 sectors of high-fidelity, pixel-level
simulations data created using the Lilith simulator and processed using the
full TESS SPOC pipeline. We find our model performs very well on our simulated
data, with 97% average precision and 92% accuracy on planets in the 2-class
model. This accuracy is also boosted by another ~4% if planets found at the
wrong periods are included. We also performed 3- and 4-class classification of
planets, blended & target eclipsing binaries, and non-astrophysical false
positives, which have slightly lower average precision and planet accuracies,
but are useful for follow-up decisions. When applied to real TESS data, 61% of
TCEs coincident with currently published TOIs are recovered as planets, 4% more
are suggested to be EBs, and we propose a further 200 TCEs as planet
candidates.
@misc{osborn2019rapid,
abstract = {Accurately and rapidly classifying exoplanet candidates from transit surveys
is a goal of growing importance as the data rates from space-based survey
missions increases. This is especially true for NASA's TESS mission which
generates thousands of new candidates each month. Here we created the first
deep learning model capable of classifying TESS planet candidates. We adapted
the neural network model of Ansdell et al. (2018) to TESS data. We then trained
and tested this updated model on 4 sectors of high-fidelity, pixel-level
simulations data created using the Lilith simulator and processed using the
full TESS SPOC pipeline. We find our model performs very well on our simulated
data, with 97% average precision and 92% accuracy on planets in the 2-class
model. This accuracy is also boosted by another ~4% if planets found at the
wrong periods are included. We also performed 3- and 4-class classification of
planets, blended & target eclipsing binaries, and non-astrophysical false
positives, which have slightly lower average precision and planet accuracies,
but are useful for follow-up decisions. When applied to real TESS data, 61% of
TCEs coincident with currently published TOIs are recovered as planets, 4% more
are suggested to be EBs, and we propose a further 200 TCEs as planet
candidates.},
added-at = {2019-02-25T17:46:31.000+0100},
author = {Osborn, Hugh P. and Ansdell, Megan and Ioannou, Yani and Sasdelli, Michele and Angerhausen, Daniel and Caldwell, Douglas A. and Jenkins, Jon M. and Räissi, Chedy and Smith, Jeffrey C.},
biburl = {https://www.bibsonomy.org/bibtex/2cf2f44249ab1db5a2762da6e8a4c89b2/superjenwinters},
description = {Rapid Classification of TESS Planet Candidates with Convolutional Neural Networks},
interhash = {a51c0c48de7c11de86428c46327011a7},
intrahash = {cf2f44249ab1db5a2762da6e8a4c89b2},
keywords = {Methods},
note = {cite arxiv:1902.08544Comment: 11 pages, 10 figures, Submitted to A&A},
timestamp = {2019-02-25T17:46:31.000+0100},
title = {Rapid Classification of TESS Planet Candidates with Convolutional Neural
Networks},
url = {http://arxiv.org/abs/1902.08544},
year = 2019
}