A convolutional neural network (CNN) based ensemble model for exoplanet detection

Abstract

Exoplanet detection is an extremely active research topic in astronomy. Researchers in the past have attempted to detect exoplanets using conventional methods like Radial Velocity, Transit Method, Gravitational Microlensing, Direct Imaging, Polarimetry, Astrometry, etc. While the approaches undertaken for all these studies vary, many of the research works conducted are based on the change in flux (light intensity). Based on the same characteristic, we explore yet another method of detecting exoplanets in space, using Artificial Intelligence. We rely on several machine learning algorithms like Decision Trees, Support Vector Machines, Logistic Regression, Random Forest Classifier, Multilayer Perceptron (MLP), Convolutional Neural Networks (CNN), as baseline algorithms and introduce an Ensemble-CNN model to draw out comparisons between the different machine learning models. The performance of the models has been evaluated using parameters like Accuracy, Precision, Sensitivity, and Specificity. Our results denote that the proposed Ensemble-CNN model performs relatively better for detecting exoplanets with an accuracy of 99.62%. The research will be useful in the fields of Astronomy as well as Artificial Intelligence and would be of substantial importance to physicists, cosmologists, scientists, researchers, academicians, industry experts, and machine learning experts who work in areas related to (or closely related to) exoplanet detection.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

References

  1. Amin RA, Khan AT, Raisa ZT, Chisty N, SamihaKhan S, Khaja MS, Rahman RM (2018) Detection of exoplanet systems in Kepler light curves using adaptive Neuro-fuzzy system. In 2018 international conference on intelligent systems (IS) (pp. 66-72). IEEE

  2. Ansdell M, Ioannou Y, Osborn HP, Sasdelli M, Smith JC, Caldwell D et al (2018) Scientific domain knowledge improves exoplanet transit classification with deep learning. Astrophys J Lett 869(1):L7

    Article  Google Scholar 

  3. Barnes R, Raymond SN, Greenberg R, Jackson B, Kaib NA (2010) CoRoT-7b: super-earth or super-Io? Astrophys J Lett 709(2):L95–L98

    Article  Google Scholar 

  4. Ben-Hur A, Horn D, Siegelmann HT, Vapnik V (2001) Support vector clustering. J Mach Learn Res 2(Dec):125–137

    Google Scholar 

  5. Chakriswaran P, Vincent DR, Srinivasan K, Sharma V, Chang CY, Reina DG (2019) Emotion AI-driven sentiment analysis: a survey, future research directions, and open issues. Appl Sci 9(24):5462

    Article  Google Scholar 

  6. Chang CY, Srinivasan K, Chen SJ, Chang MS, Sharma V (2018) An efficient SVM based lymph node classification approach using intelligent communication ant Colony optimization. J Med Imaging Health Informats 8(5):1077–1086

    Article  Google Scholar 

  7. Chintarungruangchai P, Jiang G (2019) Detecting exoplanet transits through machine-learning techniques with convolutional neural networks. Publ Astron Soc Pac 131(1000):064502

  8. Cornachione MA et al (2019) A full implementation of Spectro-perfectionism for precise radial velocity exoplanet detection: a test case with the MINERVA reduction pipeline. Publ Astron Soc Pac 131(1006):124503

    Article  Google Scholar 

  9. Dansana D, Kumar R, Adhikari JD, Mohapatra M, Sharma R, Priyadarshini I, Le DN (2020) Global forecasting confirmed and fatal cases of COVID-19 outbreak using autoregressive integrated moving average model. Frontiers in public health, 8

  10. Dataset. Kaggle, Kepler Labelled Time Series Data. https://www.kaggle.com/keplersmachines/kepler-labelled-time-series-data

  11. Dattilo A, Vanderburg A, Shallue CJ, Mayo AW, Berlind P, Bieryla A et al (2019) Identifying Exoplanets with Deep Learning. II. Two New Super-Earths Uncovered by a Neural Network in K2 Data. Astronom J 157(5):169

    Article  Google Scholar 

  12. Doyle LR (2019) The discovery of “Tatooine”: Kepler-16b. New Astron Rev 84:101515

    Article  Google Scholar 

  13. Elavarasan D, Vincent DR, Sharma V, Zomaya AY, Srinivasan K (2018) Forecasting yield by integrating agrarian factors and machine learning models: a survey. Comput Electron Agric 155:257–282

    Article  Google Scholar 

  14. Flasseur O, Denis L, Thiébaut E, Langlois M (2018) An unsupervised patch-based approach for exoplanet detection by direct imaging. In 2018 25th IEEE international conference on image processing (ICIP) (pp. 2735-2739). IEEE

  15. Ho TK (1995). Random decision forests. In proceedings of 3rd international conference on document analysis and recognition (Vol. 1, pp. 278-282). IEEE

  16. Jara-Maldonado M, Alarcon-Aquino V, Rosas-Romero R, Starostenko O, Ramirez-Cortes JM (2020) Transiting exoplanet discovery using machine learning techniques: a survey. Earth Sci Inform 13:573–600. https://doi.org/10.1007/s12145-020-00464-7

    Article  Google Scholar 

  17. Jha S, Kumar R, Chiclana F, Puri V, Priyadarshini I (2019a) Neutrosophic approach for enhancing quality of signals. Multimed Tools Appl:1–32

  18. Jha S, Kumar R, Priyadarshini I, Smarandache F, Long HV (2019b) Neutrosophic image segmentation with dice coefficients. Measurement 134:762–772

    Article  Google Scholar 

  19. Jha S, Kumar R, Abdel-Basset M, Priyadarshini I, Sharma R, Long HV (2019c) Deep learning approach for software maintainability metrics prediction. Ieee Access 7:61840–61855

    Article  Google Scholar 

  20. Kane SR, Dalba PA, Li Z, Horch EP, Hirsch LA, Horner J, Wittenmyer RA, Howell SB, Everett ME, Butler RP, Tinney CG, Carter BD, Wright DJ, Jones HRA, Bailey J, O’Toole SJ (2019) Detection of planetary and stellar companions to neighboring stars via a combination of radial velocity and direct imaging techniques. Astron J 157(6):252

    Article  Google Scholar 

  21. Khan MS, Stewart Jenkins J, Yoma N (2017) Discover- ing new worlds: a review of signal processing methods for detecting exoplanets from astronomical radial veloc- ity data. IEEE Signal Process Mag 34:104–115. https://doi.org/10.1109/MSP.2016.2617293

    Article  Google Scholar 

  22. Kingsford C, Salzberg SL (2008) What are decision trees? Nat Biotechnol 26(9):1011–1013

    Article  Google Scholar 

  23. Lacour S et al (2019) First direct detection of an exoplanet by optical interferometry-astrometry and K-band spectroscopy of HR 8799 e. Astronomy Astrophys 623:L11

    Article  Google Scholar 

  24. Lu Y (2019) Artificial intelligence: a survey on evolution, models, applications and future trends. J Manag Analyt 6(1):1–29

    Google Scholar 

  25. Mathur, S., Sizon, S., & Goel, N. (2020) Identifying exoplanets using deep learning and predicting their likelihood of habitability. In advances in machine learning and computational intelligence (pp. 369-379). Springer, Singapore

  26. Melchior P, Spergel D, Lanz A (2018) In the crosshair: Astrometric exoplanet detection with WFIRST's diffraction spikes. Astron J 155(2):102

    Article  Google Scholar 

  27. Menard S (2002) Applied logistic regression analysis (Vol. 106). Sage

  28. Mislis D, Pyrzas S, Alsubai KA (2018) TSARDI: a machine learning data rejection algorithm for transiting exoplanet light curves. Mon Not R Astron Soc 481(2):1624–1630

    Article  Google Scholar 

  29. Mullally F, Coughlin JL, Thompson SE, Christiansen J, Burke C, Clarke BD, Haas MR (2016) Identifying false alarms in the Kepler planet candidate catalog. Publ Astron Soc Pac 128(965):074502

    Article  Google Scholar 

  30. Neubauer D, Vrtala A, Leitner JJ, Firneis MG, Hitzenberger R (2012) The life supporting zone of Kepler-22b and the Kepler planetary candidates: KOI268. 01, KOI701. 03, KOI854. 01 and KOI1026. 01. Planet Space Sci 73(1):397–406

    Article  Google Scholar 

  31. Patro SGK, Mishra BK, Panda SK, Kumar R, Long HV, Taniar D, Priyadarshini I (2020) A hybrid action-related K-nearest neighbour (HAR-KNN) approach for recommendation systems. IEEE Access 8:90978–90991

    Article  Google Scholar 

  32. Pearson KA, Palafox L, Griffith CA (2018) Searching for exoplanets using artificial intelligence. Mon Not R Astron Soc 474(1):478–491

    Article  Google Scholar 

  33. Pritam N, Khari M, Kumar R, Jha S, Priyadarshini I, Abdel-Basset M, Long HV (2019) Assessment of code smell for predicting class change proneness using machine learning. IEEE Access 7:37414–37425

    Article  Google Scholar 

  34. Priyadarshini I (2018). Features and architecture of the modern cyber range: a qualitative analysis and survey (Doctoral dissertation, University of Delaware)

  35. Priyadarshini I, Cotton C (2019, October) Internet memes: a novel approach to distinguish humans and bots for authentication. In proceedings of the future technologies conference (pp. 204-222). Springer, Cham

    Google Scholar 

  36. Priyadarshini I, Cotton C (2020) Intelligence in cyberspace: the road to cyber singularity. J Exp Theoretic Artificial Intell 1–35

  37. Priyadarshini I, Wang H, Cotton C (2019, October) Some Cyberpsychology techniques to distinguish humans and bots for authentication. In proceedings of the future technologies conference (pp. 306-323). Springer, Cham

    Google Scholar 

  38. Priyadarshini I, Mohanty P, Kumar R, Son LH, Chau HTM, Nhu VH, Ngo P, Tien Bui D (2020) Analysis of outbreak and global impacts of the COVID-19. In healthcare (Vol. 8, no. 2, p. 148). Multidisciplinary digital publishing institute

  39. Puri V, Jha S, Kumar R, Priyadarshini I, Abdel-Basset M, Elhoseny M, Long HV (2019) A hybrid artificial intelligence and internet of things model for generation of renewable resource of energy. IEEE Access 7:111181–111191

    Article  Google Scholar 

  40. Quek SG, Selvachandran G, Munir M, Mahmood T, Ullah K, Son LH et al (2019) Multi-attribute multi-perception decision-making based on generalized T-spherical fuzzy weighted aggregation operators on neutrosophic sets. Mathematics 7(9):780

    Article  Google Scholar 

  41. Quintana E (2014). Kepler 186f–the first earth-sized planet orbiting in habitable zone of another star

  42. Ren D, Ranganathan M, Christian DJ (2019) A host-star calibration based Polarimeter for earth-like exoplanet imaging. Publ Astron Soc Pac 131(1005):115004

    Article  Google Scholar 

  43. Schanche N, Cameron AC, Hébrard G, Nielsen L, Triaud AHMJ, Almenara JM, Alsubai KA, Anderson DR, Armstrong DJ, Barros SCC, Bouchy F, Boumis P, Brown DJA, Faedi F, Hay K, Hebb L, Kiefer F, Mancini L, Maxted PFL, Palle E, Pollacco DL, Queloz D, Smalley B, Udry S, West R, Wheatley PJ (2019) Machine-learning approaches to exoplanet transit detection and candidate validation in wide-field ground-based surveys. Mon Not R Astron Soc 483(4):5534–5547

    Article  Google Scholar 

  44. Simard PY, Steinkraus D, Platt JC (2003) Best practices for convolutional neural networks applied to visual document analysis. In Icdar (Vol. 3, no. 2003)

  45. Singh G, Gawane S, Prasad A, Wagaskar K (2020) Modeling CNN for best parameter investigation to predict viable exoplanets. In advanced computing technologies and applications (pp. 591–607). Springer, Singapore

    Google Scholar 

  46. Srinivasan K, Sharma V, Jayakody DNK, Vincent DR (2018, December) D-ConvNet: deep learning model for enhancement of brain MR images. In basic & Clinical Pharmacology & Toxicology (Vol. 124, pp. 3-4). 111 RIVER ST, HOBOKEN 07030-5774. WILEY, NJ

  47. Sturrock GC; Manry B; Rafiqi, Sohail (2019) Machine Learning Pipeline for Exoplanet Classification," SMU Data Science Review: Vol. 2 : No. 1 , Article 9

  48. Tang J, Deng C, Huang GB (2015) Extreme learning machine for multilayer perceptron. IEEE Trans Neural Networks Learn Syst 27(4):809–821

    Article  Google Scholar 

  49. Treu T, Marshall PJ, Clowe D (2012) Resource letter GL-1: gravitational lensing. Amer J Phys 80:753–763. https://doi.org/10.1119/1.4726204 arXiv:1206.0791

    Article  Google Scholar 

  50. Tuan TA, Long HV, Kumar R, Priyadarshini I, Son NTK (2019) Performance evaluation of botnet DDoS attack detection using machine learning. Evol Intel:1–12

  51. Wang G, Hao J, Ma J, Jiang H (2011) A comparative assessment of ensemble learning for credit scoring. Expert Syst Appl 38(1):223–230

    Article  Google Scholar 

  52. Yu L, Vanderburg A, Huang C, Shallue CJ, Crossfield IJ, Gaudi BS et al (2019) Identifying Exoplanets with Deep Learning. III. Automated Triage and Vetting of TESS Candidates. Astronom J 158(1):25

    Article  Google Scholar 

  53. Zaleski SM, Valio A, Marsden SC, Carter BD (2019) Differential rotation of Kepler-71 via transit photometry mapping of faculae and starspots. Mon Not R Astron Soc 484(1):618–630

    Article  Google Scholar 

  54. Zapatero Osorio MR et al (2000) Discovery of young, isolated planetary mass objects in the σ orionis star cluster. Science

  55. Zingales T, Waldmann IP (2018) Exogan: retrieving exoplanetary atmospheres using deep convolutional generative adversarial networks. Astron J 156(6):268

    Article  Google Scholar 

  56. Zucker S, Giryes R (2018) Shallow transits—deep learning. I. Feasibility study of deep learning to detect periodic transits of exoplanets. Astronom J 155(4):147

Download references

Funding

This research received no external funding.

Author information

Affiliations

Authors

Contributions

Conception and Design of Work: Ishaani Priyadarshini and Vikram Puri, Data Collection: Ishaani Priyadarshini, Data Analysis and Interpretation: Ishaani Priyadarshini and Vikram Puri, Drafting the Article: Ishaani Priyadarshini, Critical Revision of the Article: Vikram Puri, Final Approval of the Version to be submitted: Vikram Puri.

Corresponding author

Correspondence to Vikram Puri.

Ethics declarations

We declare that this manuscript is original, has not been published before, and is not currently being considered for publication elsewhere.

Ethics approval

NA

Consent to participate

NA

Conflict of interest

The authors declare no conflict of interest.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Priyadarshini, I., Puri, V. A convolutional neural network (CNN) based ensemble model for exoplanet detection. Earth Sci Inform (2021). https://doi.org/10.1007/s12145-021-00579-5

Download citation

Keywords

  • Exoplanet detection
  • Flux (light intensity)
  • Artificial intelligence
  • Machine learning
  • Convolutional neural networks (CNN)
  • Ensemble