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

The Transiting Exoplanet Survey Satellite (TESS) has now been operational for a little over two years, covering the Northern and the Southern hemispheres once. The TESS team processes the downlinked data using the Science Processing Operations Center pipeline and Quick Look pipeline to generate alerts for follow-up. Combined with other efforts from the community, over two thousand planet candidates have been found of which tens have been confirmed as planets. We present our pipeline, Nigraha, that is complementary to these approaches. Nigraha uses a combination of transit finding, supervised machine learning, and detailed vetting to identify with high confidence a few planet candidates that were missed by prior searches. In particular, we identify high signal to noise ratio (SNR) shallow transits that may represent more Earth-like planets. In the spirit of open data exploration we provide details of our pipeline, release our supervised machine learning model and code as open source, and make public the 38 candidates we have found in seven sectors. The model can easily be run on other sectors as is. As part of future work we outline ways to increase the yield by strengthening some of the steps where we have been conservative and discarded objects for lack of a datum or two.

[1]  M. R. Haas,et al.  OVERVIEW OF THE KEPLER SCIENCE PROCESSING PIPELINE , 2010, 1001.0258.

[2]  E. Agol,et al.  Analytic Light Curves for Planetary Transit Searches , 2002, astro-ph/0210099.

[3]  Mark Clampin,et al.  Transiting Exoplanet Survey Satellite (TESS) , 2014, Astronomical Telescopes and Instrumentation.

[4]  Kyle A. Pearson,et al.  Searching for exoplanets using artificial intelligence , 2017, Monthly Notices of the Royal Astronomical Society.

[5]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[6]  Ming Zhao,et al.  Toward Space-like Photometric Precision from the Ground with Beam-shaping Diffusers , 2017, 1710.01790.

[7]  Raja Giryes,et al.  Shallow Transits—Deep Learning. I. Feasibility Study of Deep Learning to Detect Periodic Transits of Exoplanets , 2017, 1711.03163.

[8]  Christopher J. Shallue,et al.  Identifying Exoplanets with Deep Learning: A Five-planet Resonant Chain around Kepler-80 and an Eighth Planet around Kepler-90 , 2017, 1712.05044.

[9]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[10]  T. Morton.  AN EFFICIENT AUTOMATED VALIDATION PROCEDURE FOR EXOPLANET TRANSIT CANDIDATES , 2012, 1206.1568.

[11]  M. R. Haas,et al.  A MACHINE LEARNING TECHNIQUE TO IDENTIFY TRANSIT SHAPED SIGNALS , 2015, 1509.00041.

[12]  Keivan G. Stassun,et al.  The First Habitable-zone Earth-sized Planet from TESS. I. Validation of the TOI-700 System , 2020 .

[13]  Michael C. Liu,et al.  197 CANDIDATES AND 104 VALIDATED PLANETS IN K2's FIRST FIVE FIELDS , 2016, 1607.05263.

[14]  Daniel Angerhausen,et al.  Rapid classification of TESS planet candidates with convolutional neural networks , 2019, Astronomy & Astrophysics.

[15]  Shuliang Wang,et al.  Data Mining and Knowledge Discovery , 2005, Mathematical Principles of the Internet.

[16]  Michael Shao,et al.  CHIMERA: a wide-field, multi-colour, high-speed photometer at the prime focus of the Hale telescope , 2016, 1601.03104.

[17]  Peter Tenenbaum,et al.  The TESS science processing operations center , 2016, Astronomical Telescopes + Instrumentation.

[18]  P. Tenenbaum,et al.  AUTOMATIC CLASSIFICATION OF KEPLER PLANETARY TRANSIT CANDIDATES , 2014, 1408.1496.

[19]  P. Berlind,et al.  PLANETARY CANDIDATES FROM THE FIRST YEAR OF THE K2 MISSION , 2015, 1511.07820.

[20]  David J Armstrong,et al.  Machine-learning approaches to exoplanet transit detection and candidate validation in wide-field ground-based surveys , 2018, Monthly Notices of the Royal Astronomical Society.

[21]  David J Armstrong,et al.  Transit shapes and self-organizing maps as a tool for ranking planetary candidates: application to Kepler and K2 , 2016, 1611.01968.

[22]  G. Kov'acs,et al.  A box-fitting algorithm in the search for periodic transits , 2002, astro-ph/0206099.

[23]  Mark Goadrich,et al.  The relationship between Precision-Recall and ROC curves , 2006, ICML.

[24]  Liang Yu,et al.  Identifying Exoplanets with Deep Learning. II. Two New Super-Earths Uncovered by a Neural Network in K2 Data , 2019, The Astronomical Journal.

[25]  M. Hippke,et al.  Optimized transit detection algorithm to search for periodic transits of small planets , 2019, Astronomy & Astrophysics.

[26]  G. Mulders,et al.  Wōtan: Comprehensive Time-series Detrending in Python , 2019, The Astronomical Journal.

[27]  Keivan G. Stassun,et al.  The TESS Input Catalog and Candidate Target List , 2017, The Astronomical Journal.

[28]  Natalie M. Batalha,et al.  Transit least-squares survey , 2020, Astronomy & Astrophysics.

[29]  Frederic Pont,et al.  The effect of red noise on planetary transit detection , 2006, astro-ph/0608597.

[30]  Sara Seager,et al.  Identifying Exoplanets with Deep Learning. III. Automated Triage and Vetting of TESS Candidates , 2019, The Astronomical Journal.

[31]  J. J. González-Vidal,et al.  Gaia Data Release 2 , 2018, Astronomy & Astrophysics.

[32]  Jessie L. Dotson,et al.  Lightkurve: Kepler and TESS time series analysis in Python , 2018 .

[33]  David J Armstrong,et al.  Automatic vetting of planet candidates from ground based surveys: Machine learning with NGTS , 2018, 1805.07089.

[34]  Avi Shporer,et al.  Diffuser-assisted Infrared Transit Photometry for Four Dynamically Interacting Kepler Systems , 2019, The Astronomical Journal.

[35]  M. R. Haas,et al.  FALSE POSITIVE PROBABILITIES FOR ALL KEPLER OBJECTS OF INTEREST: 1284 NEWLY VALIDATED PLANETS AND 428 LIKELY FALSE POSITIVES , 2016, 1605.02825.

[36]  M. Sasdelli,et al.  Scientific Domain Knowledge Improves Exoplanet Transit Classification with Deep Learning , 2018, The Astrophysical Journal.