Plasma and Fusion Research

Volume 14, 1202117 (2019)

Rapid Communications

Tomographic Reconstruction of Imaging Diagnostics with a Generative Adversarial Network
Naoki KENMOCHI, Masaki NISHIURA1), Kaori NAKAMURA and Zensho YOSHIDA
The University of Tokyo, Kashiwa 277-8561, Japan
1)
National Institute for Fusion Science, Toki 509-5292, Japan
(Received 8 May 2019 / Accepted 20 May 2019 / Published 30 July 2019)

Abstract

We have developed a tomographic reconstruction method using a conditional Generative Adversarial Network to obtain local-intensity profiles from imaging-diagnostic data. To train the network we prepared pairs of local-emissivity and line-integrated images that simulate the experimental system. After validating the accuracy of the trained network, we used it to reconstruct a local image from a measured line-integrated image. We applied this procedure to the He II-emission imaging diagnostic for RT-1 magnetospheric plasmas, including the effects of stray light within the measured image to remove reflections from the chamber walls in the reconstruction. The local intensity profiles we obtain clearly elucidate the effect of ion-cyclotron-resonance heating. This method is a powerful tool for systems where it is difficult to solve the inversion problem due to the involved contributions of nonlocal optical effects or measurement restrictions.

Keywords

deep learning, generative adversarial network, imaging diagnostic, tomographic reconstruction, laboratory magnetosphere

DOI: 10.1585/pfr.14.1202117

Full Text

PDF format (846Kbytes) PDF Download

References

  • [1] D.R. Ferreira et al., Fusion Sci. Technol. 74, 47 (2018).
  • [2] I. Goodfellow et al., in Proc. NIPS, 2672 (2014).
  • [3] P. Isola et al., arXiv:1611.07004 (2016).
  • [4] K. Nakamura et al., Rev. Sci. Instrum. 89, 10D133 (2018).
  • [5] Z. Yoshida et al., Phys. Rev. Lett. 104, 235004 (2010).
  • [6] M. Nishiura et al., Nucl. Fusion 59, 096005 (2019).
  • [7] S. Ioffe and C. Szegedy, In ICML (2015).
  • [8] A. Radford et al., In ICLR (2016).
  • [9] Z. WANG et al., IEEE Trans. Image Process. 13, 4, 600 (2004).
  • [10] Q. Huynh-Thu and M. Ghanbari, Electron. Lett. 44, 13, 800 (2008).
  • [11] J.R. Fienup, Appl. Opt. 36, 32, 8352 (1997).
  • [12] M. Nishiura et al., Nucl. Fusion 57, 086038 (2017).