Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Neural networks for image-based wavefront sensing for astronomy

Andersen, Torben LU ; Owner-Petersen, Mette LU and Enmark, Anita LU (2019) In Optics Letters 44(18). p.4618-4621
Abstract
We study the possibility of using convolutional neural networks for wavefront sensing from a guide star image in astronomical telescopes. We generated a large number of artificial atmospheric wavefront screens and determined associated best-fit Zernike polynomials. We also generated in-focus and out-of-focus point-spread functions. We trained the well-known “Inception” network using the artificial data sets and found that although the accuracy does not permit diffraction-limited correction, the potential improvement in the residual phase error is promising for a telescope in the 2–4 m class.
Please use this url to cite or link to this publication:
author
; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
Optics Letters
volume
44
issue
18
pages
4 pages
publisher
Optical Society of America
external identifiers
  • scopus:85072106843
  • pmid:31517947
ISSN
0146-9592
DOI
10.1364/OL.44.004618
language
English
LU publication?
yes
additional info
Has been designated as "Editor's Pick" that serve to highlight articles with excellent scientific quality and that are representative of the work taking place in a specific field.
id
da9ed7a8-4f39-4226-ae5d-27f4fb247997
date added to LUP
2019-09-28 22:31:47
date last changed
2022-12-23 17:38:06
@article{da9ed7a8-4f39-4226-ae5d-27f4fb247997,
  abstract     = {{We study the possibility of using convolutional neural networks for wavefront sensing from a guide star image in astronomical telescopes. We generated a large number of artificial atmospheric wavefront screens and determined associated best-fit Zernike polynomials. We also generated in-focus and out-of-focus point-spread functions. We trained the well-known “Inception” network using the artificial data sets and found that although the accuracy does not permit diffraction-limited correction, the potential improvement in the residual phase error is promising for a telescope in the 2–4 m class.}},
  author       = {{Andersen, Torben and Owner-Petersen, Mette and Enmark, Anita}},
  issn         = {{0146-9592}},
  language     = {{eng}},
  month        = {{09}},
  number       = {{18}},
  pages        = {{4618--4621}},
  publisher    = {{Optical Society of America}},
  series       = {{Optics Letters}},
  title        = {{Neural networks for image-based wavefront sensing for astronomy}},
  url          = {{http://dx.doi.org/10.1364/OL.44.004618}},
  doi          = {{10.1364/OL.44.004618}},
  volume       = {{44}},
  year         = {{2019}},
}