Abstract
Spatial missions such as the Kepler mission, and the Transiting Exoplanet Survey Satellite (TESS) mission, have encouraged data scientists to analyze light curve datasets. The purpose of analyzing these data is to look for planet transits, with the aim of discovering and validating exoplanets, which are planets found outside our Solar System. Furthermore, transiting exoplanets can be better characterized when light curves and radial velocity curves are available. The manual examination of these datasets is a task that requires big quantities of time and effort, and therefore is prone to errors. As a result, the application of machine learning methods has become more common on exoplanet discovery and categorization research. This survey presents an analysis on different exoplanet transit discovery algorithms based on machine learning, some of which even found new exoplanets. The analysis of these algorithms is divided into four steps, namely light curve preprocessing, possible exoplanet signal detection, and identification of the detected signal to decide whether it belongs to an exoplanet or not. We propose a model to create synthetic datasets of light curves, and we compare the performance of several machine learning models used to identify transit exoplanets, with inputs preprocessed with and without using the Discrete Wavelet Transform (DWT). Our experimental results allow us to conclude that multiresolution analysis in the time-frequency domain can improve exoplanet signal identification, because of the characteristics of light curves and transiting exoplanet signals.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Notes
NASA Exoplanet Archive: http://exoplanetarchive.ipac.caltech.edu
https://faculty.washington.edu/agol/transit.html
Fig. 2 
Example of a light curve. As the exoplanet orbits the star, different brightness values are obtained. Some parameters that can be extracted from a light curve are: Beginning of ingress (t1); end of ingress (t2); beginning of egress (t3); end of egress (t4); transit length; and transit depth
https://www.cfa.harvard.edu/~avanderb/tutorial/tutorial.html
Fig. 4 
Real light curve extracted from the planetary system around the star HIP 41378 in the MAST archive. The x-axis represents a measure of time called Barycentric Julian Day (BJD); the value 2454833 that accompanies the x-axis title, is to be summed to the x-axis value in order to calculate the BJD for each measurement. The y-axis represents the brightness of the star. This figure was created by following the Transit Light Curve Tutorial
http://exoplanets.nasa.gov retrieved in 20/01/2019.
References
Aigrain S, Favata F (2002) Bayesian detection of planetary transits. a modified version of the Gregory-Loredo method for bayesian periodic signal detection. Astron Astrophys 395:625–636. https://doi.org/10.1051/0004-6361:20021290
Aigrain S, Parviainen H, Roberts S, Reece S, Evans T (2017) Robust, open-source removal of systematics in Kepler data. Mon Not R Astron Soc 471:759–769. https://doi.org/10.1093/mnras/stx1422
Akeson RL, et al. (2013) The NASA Exoplanet Archive: Data and Tools for Exoplanet Research. Publ Astron Soc Pac 125:989. https://doi.org/10.1086/672273
Alarcon-Aquino V, Barria J (2009) Change detection in time series using the maximal overlap discrete wavelet transform. Lat Am Appl Res 39:145–152
Alarcon-Aquino V, Barria JA (2001) Anomaly detection in communication networks using wavelets. In: IEE Proceedings - Communications, 148:355–362, DOI https://doi.org/10.1049/ip-com:20010659, (to appear in print)
Alarcon-Aquino V, Barria JA (2006) Multiresolution fir neural-network-based learning algorithm applied to network traffic prediction. IEEE T Syst Man Cy C 36:208–220. https://doi.org/10.1109/TSMCC.2004.843217
Alarcon-Aquino V, Ramirez-Cortes J, Gomez-Gil P, Starostenko O, Garcia-Gonzalez Y (2014) Network intrusion detection using self-recurrent wavelet neural network with multidimensional radial wavelons. Inf Technol Control 43:347–358. https://doi.org/10.5755/j01.itc.43.4.4626
Anglada-Escudé, et al. (2016) A terrestrial planet candidate in a temperate orbit around proxima centauri. Nature 536:437–440. https://doi.org/10.1038/nature19106
Ansdell M, et al. (2018) Scientific Domain Knowledge Improves Exoplanet Transit Classification with Deep Learning. Astrophys J Lett 869:L7. https://doi.org/10.3847/2041-8213/aaf23b
Armstrong D, et al. (2015) K2 variable catalogue II: Machine learning classification of variable stars and eclipsing binaries in K2 fields 0-4. Mon Not R Astron Soc 456:2260–2272. https://doi.org/10.1093/mnras/stv2836
Armstrong D, et al. (2018) Automatic vetting of planet candidates from ground-based surveys: Machine learning with NGTS. Mon Not R Astron Soc 478:4225–4237. https://doi.org/10.1093/MNRAS/STY1313
Armstrong DJ, Pollacco D, Santerne A (2016) Transit shapes and self-organizing maps as a tool for ranking planetary candidates: application to Kepler and K2. Mon Not R Astron Soc 465:2634–2642. https://doi.org/10.1093/mnras/stw2881
Auvergne M, et al. (2009) The CoRoT satellite in flight: description and performance. Astronomy & Astrophysics 506:411–424. https://doi.org/10.1051/0004-6361/200810860
Baluev R (2018) Planetpack3: A radial-velocity and transit analysis tool for exoplanets. Astronomy and Computing 25:221–229. https://doi.org/10.1016/j.ascom.2018.10.005
Baluev RV (2013) Detecting multiple periodicities in observational data with the multifrequency periodogram—ii. frequency decomposer, a parallelized time-series analysis algorithm. Astronomy and Computing 3-4:50–57. https://doi.org/10.1016/j.ascom.2013.11.003
Barclay T, et al. (2013) A sub-Mercury-sized exoplanet. Nature 494:452–454. https://doi.org/10.1038/nature11914
Basri G, Borucki WJ, Koch D (2005) The Kepler Mission: A wide-field transit search for terrestrial planets. New Astronomy Reviews 49:478–485. https://doi.org/10.1016/j.newar.2005.08.026
Beck T, et al. (2017) The CHEOPS characterising exoplanet satellite mission: telescope optical design, development status and main technical and programmatic challenges, vol 10562
Beuzit JL, et al. (2019) SPHERE: The exoplanet imager for the Very Large Telescope. Astronomy and Astrophysics 631:A155. https://doi.org/10.1051/0004-6361/201935251. arXiv:1902.04080
Bonse MJ, Quanz SP, Amara A (2018) Wavelet based speckle suppression for exoplanet imaging - Application of a de-noising technique in the time domain. arXiv:1804.05063
Borucki WJ, et al. (2010) Kepler planet-detection mission: Introduction and first results. Science 327:977–980. https://doi.org/10.1126/science.1185402
Bravo JP, Roque S, Estrela R, Leão I. C., De Medeiros JR (2014) Wavelets: a powerful tool for studying rotation, activity, and pulsation in Kepler and CoRoT stellar light curves. Astronomy & Astrophysics 568:A34. https://doi.org/10.1051/0004-6361/201323032
Burrows A, et al. (2001) The theory of brown dwarfs and extrasolar giant planets. Reviews of Modern Physics 73:719–765. https://doi.org/10.1103/RevModPhys.73.719
Campbell B, et al. (1988) A search for substellar companions to solar-type stars. Astrophysical Journal 331:902–921. https://doi.org/10.1086/166608
Carpano S, Aigrain S, Favata F (2003) Detecting planetary transits in the presence of stellar variability, optimal filtering and the use of colour information. Astronomy and Astrophysics 401:743–753. https://doi.org/10.1051/0004-6361:20030093
Carter J, Nathan Winn J (2009) Parameter estimation from time-series data with correlated errors: A wavelet-based method and its application to transit light curves. Astrophys J Lett 704:51–67. https://doi.org/10.1088/0004-637X/704/1/51
Catanzarite JH (2015) Autovetter planet candidate catalog for Q1-Q17 data release 24 Astronomy & Astrophysics
Charbonneau D, et al. (2000) Detection of planetary transits a cross a sun-like star. Astrophys J Lett 529:L45–L48. https://doi.org/10.1086/312457
Chauvin G, et al. (2004) A giant planet candidate near a young brown dwarf. direct VLT/NACO observations using ir wavefront sensing. Astronomy and Astrophysics 425:L29–L32. https://doi.org/10.1051/0004-6361:200400056
Chintarungruangchai P, Jiang I.-G. (2019) Detecting exoplanet transits through machine-learning techniques with convolutional neural networks. Publ Astron Soc Pac 131:064502. https://doi.org/10.1088/1538-3873/ab13d3
Cochran WD, et al. (2002) A Planetary Companion to the Binary Star Gamma Cephei. In: AAS/Division for Planetary Sciences Meeting Abstracts #34 p. infopages 916. volume info volume 34 of info series Bulletin of the American Astronomical Society
Coughlin JL (2017) Planet Detection Metrics: Robovetter Completeness and Effectiveness for Data Release 25 info type Technical Report NASA
Coughlin JL, et al. (2016) Planetary candidates observed by Kepler. VII. the first fully uniform catalog based on the entire 48-month data set Q1–Q17 DR24. Astrophys J Lett Supplement Series 224:12. https://doi.org/10.3847/0067-0049/224/1/12
Dattilo A, et al. (2019) Identifying Exoplanets with Deep Learning. II. Two New Super-Earths Uncovered by a Neural Network in K2 Data. The Astronomical Journal 157:169. https://doi.org/10.3847/1538-3881/ab0e12
Daubechies I (1992) Ten Lectures on Wavelets Society for Industrial and Applied Mathematics
Emmanoulopoulos D, et al. (2013) Generating artificial light curves: revisited and updated. Mon Not R Astron Soc 433:907–927. https://doi.org/10.1093/mnras/stt764
von Essen C, et al. (2018) Kepler Object of Interest Network I. First results combining ground and space-based observations of Kepler systems with transit timing variations. Astronomy & Astrophysics 615:1–16. https://doi.org/10.1051/0004-6361/201732483
Fleck B (1995) The soho mission. In: Benz A.O., Krüger Eds A. (eds). Coronal Magnetic Energy Releases. Lecture Notes in Physics, Springer, Berlin, Heidelberg. 444:233–244
Foreman-Mackey, et al. (2015) A systematic search for transiting planets in the K2 data. Astrophys J Lett 806:215. https://doi.org/10.1088/0004-637x/806/2/215
Freudenthal J, et al. (2018) Kepler Object of Interest Network. II. Photodynamical modelling of Kepler-9 over 8 years of transit observations. Astronomy & Astrophysics 618:A41. https://doi.org/10.1051/0004-6361/201833436
Gardner JP, et al. (2006) The James Webb Space Telescope. Space Science Reviews 123:485–606. https://doi.org/10.1007/s11214-006-8315-7
Grziwa S, Pätzold M. (2016) Wavelet-based filter methods to detect small transiting planets in stellar light curves. arXiv:1607.08417
Grziwa S, Pätzold M., Carone L (2012) The needle in the haystack: Searching for transiting extrasolar planets in CoRoT stellar light curves. Mon Not R Astron Soc 420:1045–1052. https://doi.org/10.1111/j.1365-2966.2011.19970.x
Hartman JD, et al. (2015) HATS-6b: A Warm Saturn Transiting an Early M Dwarf Star, and a Set of Empirical Relations for Characterizing K and M Dwarf Planet Hosts. The Astronomical Journal 149:166. https://doi.org/10.1088/0004-6256/149/5/166
He X, Niyogi P (2004) Locality preserving projections, Eds. Advances in Neural Information Processing Systems 16 pp. info pages 153–160 publisher MIT Press S. Thrun, L. K. Saul, B. Schölkopf (eds)
Henry GW, et al. (2000) A transiting ”51 peg-like” planet. Astrophys J Lett 529:L41–L44. https://doi.org/10.1086/312458
Howell SB, et al. (2014) The K2 Mission: Characterization and early results. Publ Astron Soc Pac 126:398–408. https://doi.org/10.1086/676406
Huang NE, Wu Z (2008) A review on Hilbert-Huang transform: Method and its applications to geophysical studies. Reviews of Geophysics 46:1–23. https://doi.org/10.1029/2007RG000228
Japkowicz N, Shah M (2011) Evaluating learning algorithms: A classification perspective
Jenkins J, et al. (2015) Discovery and validation of Kepler-452b: A 1.6-Re super earth exoplanet in the habitable zone of a G2 star. The Astronomical Journal 150:1–19. https://doi.org/10.1088/0004-6256/150/2/56
Jenkins JM (2002) The impact of solar-like variability on the detectability of transiting terrestrial planets. Astrophys J Lett 575:493–505. https://doi.org/10.1086/341136
Jenkins JM, et al. (2010) Overview of the Kepler science processing pipeline. Astrophys J Lett 713:L87–L91. https://doi.org/10.1088/2041-8205/713/2/l87
Khan MS, Stewart Jenkins J, Yoma N (2017) Discovering new worlds: a review of signal processing methods for detecting exoplanets from astronomical radial velocity data. IEEE Signal Processing Magazine 34:104–115. https://doi.org/10.1109/MSP.2016.2617293
Kingma D, Ba J (2014) Adam: A method for stochastic optimization, International Conference on Learning Representations
Koch DG, et al. (2010) Kepler Mission design, realized photometric performance, and early science. Astrophys J Lett Letters 713:L79–L86. https://doi.org/10.1088/2041-8205/713/2/L79. arXiv:1001.0268
Kovacs G (2017) Synergies between exoplanet surveys and variable star research. EPJ Web of Conferences 152:01005. https://doi.org/10.1051/epjconf/201715201005
Kovacs G, Bakos G, W Noyes R (2005) A trend filtering algorithm for wide field variability surveys. Mon Not R Astron Soc 356:557–567. https://doi.org/10.1111/j.1365-2966.2004.08479.x
Kovács G., Zucker S, Mazeh T (2002) A box-fitting algorithm in the search for periodic transits. Astronomy and Astrophysics 391:369–377. https://doi.org/10.1051/0004-6361:20020802
Kreidberg L (2015) batman: BAsic transit model cAlculatioN in python. Publ Astron Soc Pac 127:1161–1165. https://doi.org/10.1086/683602
Latham DW, et al. (1989) The unseen companion of HD114762 - A probable brown dwarf. Nature 339:38–40. https://doi.org/10.1038/339038a0
Lenzen R, et al. (1998) CONICA: The high-resolution near-infrared camera for the ESO VLT. In: Proc.SPIE pp. info pages 3354–3354 – 9 3354, DOI https://doi.org/10.1117/12.317287, (to appear in print)
Males JR, et al. (2014) Direct imaging of exoplanets in the habitable zone with adaptive optics. In: Adaptive Optics Systems IV pp. info pages 1–13 9148 of info series Society of Photo-Optical Instrumentation Engineers SPIE Conference Series, DOI https://doi.org/10.1117/12.2057135, (to appear in print)
Mandel K, Agol E (2002) Analytic light curves for planetary transit searches. Astrophys J Lett 580:L171–L175. https://doi.org/10.1086/345520
Masciadri E, Raga A (2004) Exoplanet recognition using a wavelet analysis technique. Astrophys J Lett 611:137–140. https://doi.org/10.1086/423984
Mathur S, et al. (2017) Revised stellar properties of Kepler Targets for the Q1-17 DR 25 transit detection run. Astrophys J Lett Supplement Series 229:30. https://doi.org/10.3847/1538-4365/229/2/30
Mayor M, Queloz D (1995) A Jupiter-mass companion to a solar-type star. info journal Nature 378:355–359. https://doi.org/10.1038/378355a0
McCauliff SD, et al. (2015) Automatic classification of Kepler planetary transit candidates. Astrophys J Lett 806:6. https://doi.org/10.1088/0004-637x/806/1/6
Morton TD, et al. (2016) False Positive Probabilities for all Kepler Objects of Interest: 1284 Newly Validated Planets and 428 Likely False Positives. Astrophys J Lett 822:86. https://doi.org/10.3847/0004-637X/822/2/86
Moutou C, Pont F (2006) Detection and characterization of extrasolar planets: the transit method. Ecole de Goutelas 28:55–79
Nason GP, Silverman BW (1995) The stationary wavelet transform and some statistical applications. In: Antoniadis A., Oppenheim G. (eds) Wavelets and Statistics. Lecture Notes in Statistics, Springer, New York, NY. 103:281–299
Nun I, et al. (2014) Supervised Detection of Anomalous Light Curves in Massive Astronomical Catalogs. Astrophys J Lett 793:23. https://doi.org/10.1088/0004-637X/793/1/23
P Hatzes A (2014) The role of space telescopes in the characterization of transiting exoplanets. journal Nature 513:353–7. https://doi.org/10.1038/nature13783
Parviainen H (2015) pytransit: fast and easy exoplanet transit modelling in python. Mon Not R Astron Soc 450:3233–3238. https://doi.org/10.1093/mnras/stv894
Pasquale BA, et al. (2017) Optical Design of the WFIRST Phase-A Wide Field Instrument. In: Optical Design and Fabrication 2017 Freeform, IODC, OFT ITh1B.2 Optical Society of America, DOI https://doi.org/10.1364/IODC.2017.ITh1B.2, (to appear in print)
Pearson KA, Palafox L, Griffith CA (2018) Searching for exoplanets using artificial intelligence. Mon Not R Astron Soc 474:478–491. https://doi.org/10.1093/mnras/stx2761
Petigura EA, Marcy GW, Howard AW (2013) A plateau in the planet population below twice the size of earth. Astrophys J Lett 770:69. https://doi.org/10.1088/0004-637x/770/1/69
Pollacco D, et al. (2006) The wasp project and the super wasp cameras. Publ Astron Soc Pac 118:1407–1418. https://doi.org/10.1086/508556
Rauer H, et al. (2014) The PLATO 2.0 mission. Experimental Astronomy 38:249–330. https://doi.org/10.1007/s10686-014-9383-4
Ricker GR, et al. (2015) Transiting Exoplanet Survey Satellite TESS. Journal of Astronomical Telescopes, Instruments, and Systems 1:014003. https://doi.org/10.1117/1.JATIS.1.1.014003
Rodriguez JE, et al. (2018) A Compact Multi-planet System with a Significantly Misaligned Ultra Short Period Planet. The Astronomical Journal 156:245. https://doi.org/10.3847/1538-3881/aae530
Rousset G, et al. (2000) Status of the VLT Nasmyth adaptive optics system NAOS. Proc.SPIE 4007:4007–10. https://doi.org/10.1117/12.390304
Sanders G (2013) The Thirty Meter Telescope TMT: An International Observatory. Journal of Astrophysics and Astronomy 34:81–86. https://doi.org/10.1007/s12036-013-9169-5
Schanche N, et al. (2019) Machine-learning approaches to exoplanet transit detection and candidate validation in wide-field ground-based surveys. Mon Not R Astron Soc 483:5534–5547. https://doi.org/10.1093/mnras/sty3146
Schwamb ME, et al. (2013) Planet hunters: A transiting circumbinary planet in a quadruple star system. Astrophys J Lett 768:127. https://doi.org/10.1088/0004-637x/768/2/127
Seager S, Bains W (2015) The search for signs of life on exoplanets at the interface of chemistry and planetary science. Science Advances 1:e1500047–e1500047. https://doi.org/10.1126/sciadv.1500047
Seager S, Mallén-Ornelas G (2003) A unique solution of planet and star parameters from an extrasolar planet transit light curve. Astrophys J Lett 585:1038–1055. https://doi.org/10.1086/346105
Shallue CJ, Vanderburg A (2018) Identifying Exoplanets with Deep Learning: A Five-planet Resonant Chain around Kepler-80 and an Eighth Planet around Kepler-90. The Astronomical Journal 155:94. https://doi.org/10.3847/1538-3881/aa9e09
Smith JC, et al. (2012) Kepler Presearch Data Conditioning II - a bayesian approach to systematic error correction. Publ Astron Soc Pac 124:1000–1014. https://doi.org/10.1086/667697
Stumpe MC, et al. (2014) Multiscale systematic error correction via wavelet-based bandsplitting in Kepler Data. Publ Astron Soc Pac 126:100–114. https://doi.org/10.1086/674989
Tamuz O, Mazeh T, Zucker S (2005) Correcting systematic effects in a large set of photometric light curves. Mon Not R Astron Soc 356:1466–1470. https://doi.org/10.1111/j.1365-2966.2004.08585.x
Thompson SE, et al. (2015) A machine learning technique to identify transit shaped signals. Astrophys J Lett 812:46. https://doi.org/10.1088/0004-637x/812/1/46
Tingley B (2003) Improvements to existing transit detection algorithms and their comparison. Astronomy and Astrophysics 408:L5–L7. https://doi.org/10.1051/0004-6361:20031138
Treu T, Marshall PJ, Clowe D (2012) Resource Letter GL-1: Gravitational Lensing. American Journal of Physics 80:753–763. https://doi.org/10.1119/1.4726204. arXiv:1206.0791
Vanderburg A, Johnson JA (2014) A Technique for Extracting Highly Precise Photometry for the Two-Wheeled Kepler Mission. Publ Astron Soc Pac 126:948. https://doi.org/10.1086/678764
Veitch D (2005) Wavelet Neural Networks and their application in the study of dynamical systems Master’s thesis University of York
Way MJ, et al. (2012) Advances in Machine Learning and Data Mining for Astronomy 1st ed. info publisher Chapman & Hall/CRC
Werner MW, et al. (2004) The Spitzer Space Telescope Mission. Astrophys J Lett Supplement Series 154:1–9. https://doi.org/10.1086/422992
Wheatley PJ, et al. (2018) The Next Generation Transit Survey NGTS. Mon Not R Astron Soc 475:4476–4493. https://doi.org/10.1093/mnras/stx2836
Wolszczan A, Frail D (1992) A planetary system around the millisecond pulsar PSR1257 + 12. Nature 355:145–147. https://doi.org/10.1038/355145a0
Wootten A, Thompson AR (2009) The atacama large millimeter/submillimeter array. In: Proceedings of the IEEE, vol 97, pp 1463–1471, DOI https://doi.org/10.1109/JPROC.2009.2020572
Yaqoob T (2011) Exoplanets and Alien Solar Systems New Earth Labs
Yu L, et al. (2019) Identifying Exoplanets with Deep Learning III: Automated Triage and Vetting of TESS Candidates. arXiv:1904.02726
Zapatero Osorio MR, et al. (2000) Discovery of young, isolated planetary mass objects in the σ orionis star cluster. Science 290:103–107. https://doi.org/10.1126/science.290.5489.103
Zeiler A, et al. (2010) Empirical Mode Decomposition - an introduction. In: Proceedings of the International Joint Conference on Neural Networks 1–8, DOI https://doi.org/10.1109/IJCNN.2010.5596829, (to appear in print)
Zingales T, et al. (2018) The ARIEL mission reference sample. Experimental Astronomy 46:67–100. https://doi.org/10.1007/s10686-018-9572-7
Zucker S, Giryes R (2018) Shallow Transits-Deep Learning. I Feasibility Study of Deep Learning to Detect Periodic Transits of Exoplanets. The Astronomical Journal 155:147. https://doi.org/10.3847/1538-3881/aaae05
Acknowledgments
The authors would like to thank the Mexican National Council for Science and Technology (CONACyT) and the Universidad de las Americas Puebla (UDLAP) for their support through the doctoral scholarship program. Also, the authors would like to thank Kyle A. Pearson for his valuable feedback regarding the light curve preprocessing step. This paper includes data collected by the Kepler mission and obtained from the MAST data archive at the Space Telescope Science Institute (STScI). Funding for the Kepler mission is provided by the NASA Science Mission Directorate. STScI is operated by the Association of Universities for Research in Astronomy, Inc., under NASA contract NAS 5–26555.
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by:H. Babaie
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Jara-Maldonado, M., Alarcon-Aquino, V., Rosas-Romero, R. et al. Transiting Exoplanet Discovery Using Machine Learning Techniques: A Survey. Earth Sci Inform 13, 573–600 (2020). https://doi.org/10.1007/s12145-020-00464-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12145-020-00464-7