Skip to main content

Deep-Learning Study of the 21-cm Differential Brightness Temperature During the Epoch of Reionization

Abstract

We propose a deep learning analysis technique with a convolutional neural network (CNN) to predict the evolutionary track of the Epoch of Reionization (EoR) from the 21-cm differential brightness temperature tomography images. We use 21cmFAST, a fast semi-numerical cosmological 21-cm signal simulator, to produce mock 21-cm maps between z = 6–13. We then apply two observational effects, such as instrumental noise and limit of (spatial and depth) resolution somewhat suitable for realistic choices of the Square Kilometre Array (SKA), into the 21-cm maps. We design our deep learning model with CNN to predict the sliced-averaged neutral hydrogen fraction from the given 21-cm map. The estimated neutral fraction from our CNN model has great agreement with the true value even after coarsely smoothing with broad beam size and frequency bandwidth and heavily covered by noise with narrow beam size and frequency bandwidth. Our results show that the deep learning analyzing method has the potential to reconstruct the EoR history efficiently from the 21-cm tomography surveys in future.

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

References

  1. J. Miralda-Escude, Science 300, 1904 (2003); astroph/0307396.

    ADS  Article  Google Scholar 

  2. S. R. Furlanetto and S. P. Oh, Mon. Not. R. Astron. Soc. 363, 1031 (2005); astro-ph/0505065.

    ADS  Article  Google Scholar 

  3. X. Fan et al., Astron. J. 132, 117 (2006), astroph/0512082.

    ADS  Article  Google Scholar 

  4. O. Zahn et al., Astrophys. J. 756, 65 (2012); 1111.6386.

    ADS  Article  Google Scholar 

  5. Planck Collaboration et al., Astron. Astrophys. 596, A108 (2016); 1605.03507.

    Article  Google Scholar 

  6. M. J. Mortonson and W. Hu, Astrophys. J. 672, 737 (2008); 0705.1132.

    ADS  Article  Google Scholar 

  7. K. Ahn et al., Astrophys. J. Lett. 756, L16 (2012); 1206.5007.

    ADS  Article  Google Scholar 

  8. C. H. Heinrich, V. Miranda and W. Hu, Phys. Rev. D 95, 023513 (2017); 1609.04788.

    ADS  Article  Google Scholar 

  9. S. J. Tingay et al., Publ. Astron. Soc. Aust. 30, e007 (2013); 1206.6945.

    ADS  Article  Google Scholar 

  10. G. Paciga et al., Mon. Not. R. Astron. Soc. 413, 1174 (2011); 1006.1351.

    ADS  Article  Google Scholar 

  11. M. P. van Haarlem et al., Astron. Astrophys. 556, A2 (2013); 1305.3550.

    Article  Google Scholar 

  12. A. R. Parsons et al., Astron. J. 139, 1468 (2010); 0904.2334.

    ADS  Article  Google Scholar 

  13. D. R. DeBoer et al., Publ. Astron. Soc. Pac. 129, 045001 (2017); 1606.07473.

    ADS  Article  Google Scholar 

  14. P. E. Dewdney, P. J. Hall, R. T. Schilizzi and T. J. L. W. Lazio, IEEE Proc. 97, 1482 (2009).

    ADS  Article  Google Scholar 

  15. L. Koopmans et al., in Advancing Astrophysics with the Square Kilometre Array (AASKA14), SISSA Medialab (2015), p. 1; 1505.07568.

  16. S. R. Furlanetto, S. P. Oh and F. H. Briggs, Phys. Rep. 433, 181 (2006); astro-ph/0608032.

    ADS  Article  Google Scholar 

  17. M. F. Morales and J. S. B. Wyithe, Annu. Rev. Astron. Astrophys. 48, 127 (2010); 0910.3010.

    ADS  Article  Google Scholar 

  18. S. Zaroubi, The Epoch of Reionization (2013), vol. 396 of Astrophysics and Space Science Library, Springer-Verlag Berlin Heidelberg, p. 45.

  19. T. Di Matteo, R. Perna, T. Abel and M. J. Rees, Astrophys. J. 564, 576 (2002); astro-ph/0109241.

    ADS  Article  Google Scholar 

  20. M. Zaldarriaga, S. R. Furlanetto and L. Hernquist, Astrophys. J. 608, 622 (2004); astro-ph/0311514.

    ADS  Article  Google Scholar 

  21. F. H. Briggs and J. Kocz, Radio Sci. 40, RS5S02 (2005).

    Article  Google Scholar 

  22. X. Wang, M. Tegmark, M. G. Santos and L. Knox, Astrophys. J. 650, 529 (2006); astro-ph/0501081.

    ADS  Article  Google Scholar 

  23. C. Schaefer, M. Geiger, T. Kuntzer and J. P. Kneib, Astron. Astrophys. 611, A2 (2018); 1705.07132.

    ADS  Article  Google Scholar 

  24. N. Gillet et al., Mon. Not. R. Astron. Soc. 484, 282 (2019); 1805.02699.

    ADS  Google Scholar 

  25. J. Seiler, A. Hutter, M. Sinha and D. Croton, Mon. Not. R. Astron. Soc. 487, 5739 (2019); 1902.01611.

    ADS  Article  Google Scholar 

  26. J. Chardin et al., Mon. Not. R. Astron. Soc. 490, 1055 (2019); 1905.06958.

    ADS  Article  Google Scholar 

  27. F. List and G. F. Lewis, Mon. Not. R. Astron. Soc. 493, 5913 (2020); 2002.07940.

    ADS  Article  Google Scholar 

  28. H. J. Hortua, L. Malago and R. Volpi, arXiv e-prints arXiv:2005.07694 (2020); 2005.07694.

  29. P. La Plante and M. Ntampaka, Astrophys. J. 880, 110 (2019); 1810.08211.

    ADS  Article  Google Scholar 

  30. H. Shimabukuro and B. Semelin, Mon. Not. R. Astron. Soc. 468, 3869 (2017); 1701.07026.

    ADS  Article  Google Scholar 

  31. S. Hassan, A. Liu, S. Kohn and P. La Plante, in The 34th Annual New Mexico Symposium, edited by A. D. Kapinska, National Radio Astronomy Observatory, 9 Nov, 2018; p. 7.

  32. A. Mesinger, S. Furlanetto and R. Cen, Mon. Not. R. Astron. Soc. 411, 955 (2011); 1003.3878.

    ADS  Article  Google Scholar 

  33. Planck Collaboration et al., arXiv e-prints arXiv:1807.06209 (2018); 1807.06209.

  34. J. R. Bond, S. Cole, G. Efstathiou and N. Kaiser, Astrophys. J. 379, 440 (1991).

    ADS  Article  Google Scholar 

  35. S. R. Furlanetto, M. Zaldarriaga and L. Hernquist, Astrophys. J. 613, 1 (2004); astro-ph/0403697.

    ADS  Article  Google Scholar 

  36. Y. B. Zel’Dovich, Astron. Astrophys. 500, 13 (1970).

    ADS  Google Scholar 

  37. J. Park, A. Mesinger, B. Greig and N. Gillet, Mon. Not. R. Astron. Soc. 484, 933 (2019); 1809.08995.

    ADS  Article  Google Scholar 

  38. G. Mellema, I. T. Iliev, U.-L. Pen and P. R. Shapiro, Mon. Not. R. Astron. Soc. 372, 679 (2006); astro-ph/0603518.

    ADS  Article  Google Scholar 

  39. S. E. Hong et al., J. Korean Astronom. Soc. 47, 49 (2014); 1008.3914.

    ADS  Article  Google Scholar 

  40. Y. Wang et al., Astrophys. J. 814, 6 (2015); 1510.01404.

    ADS  Article  Google Scholar 

  41. I. T. Iliev, E. Scannapieco, H. Martel and P. R. Shapiro, Mon. Not. R. Astron. Soc. 341, 81 (2003); astro-ph/0209216.

    ADS  Article  Google Scholar 

  42. J. Asorey et al., arXiv e-prints arXiv:2001.00833 (2020); 2001.00833.

  43. R. H. R. Hahnloser et al., Nature 405, 947 (2000).

    ADS  Article  Google Scholar 

  44. X. Glorot, A. Bordes and Y. Bengio, in Proceedings of the fourteenth international conference on artificial intelligence and statistics (Fort Lauderdale, FL, USA, April 11–13, 2011), pp. 315–323.

  45. K. He, X. Zhang, S. Ren and J. Sun, arXiv e-prints arXiv:1502.01852 (2015); 1502.01852.

  46. S. Ioffe and C. Szegedy, arXiv e-prints arXiv:1502.03167 (2015); 1502.03167.

  47. D. P. Kingma and J. Ba, arXiv e-prints arXiv:1412.6980 (2014); 1412.6980.

  48. F. Chollet et al., Keras, https://keras.io (2015).

  49. M. Abadi et al., TensorFlow: Large-scale machine learning on heterogeneous systems (2015), software available from tensorflow.org, URL https://www.tensorflow.org/.

  50. A. Liu and A. R. Parsons, Mon. Not. R. Astron. Soc. 457, 1864 (2016); 1510.08815.

    ADS  Article  Google Scholar 

Download references

Acknowledgments

The authors thank Kyungjin Ahn, Hyunbae Park, Dongsu Bak, Sangnam Park, David Parkinson, Jacobo Asorey, and an anonymous reviewer for helpful discussion and comments. The authors were supported by the Basic Science Research Program through the National Research Foundation of Korea funded by the Ministry of Education (2018R1A6A1A06024977). Computational data were transferred through a high-speed network provided by the Korea Research Environment Open NET-work (KREONET).

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Sungwook E. Hong.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Kwon, Y., Hong, S.E. & Park, I. Deep-Learning Study of the 21-cm Differential Brightness Temperature During the Epoch of Reionization. J. Korean Phys. Soc. 77, 49–59 (2020). https://doi.org/10.3938/jkps.77.49

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.3938/jkps.77.49

Keywords

  • Epoch of reionization
  • Deep learning