Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Solar image denoising with convolutional neural networks
Stockholm University, Faculty of Science, Department of Astronomy.
Stockholm University, Faculty of Science, Department of Astronomy.
Stockholm University, Faculty of Science, Department of Astronomy.
Number of Authors: 32019 (English)In: Astronomy and Astrophysics, ISSN 0004-6361, E-ISSN 1432-0746, Vol. 629, article id A99Article in journal (Refereed) Published
Abstract [en]

The topology and dynamics of the solar chromosphere are greatly affected by the presence of magnetic fields. The magnetic field can be inferred by analyzing polarimetric observations of spectral lines. Polarimetric signals induced by chromospheric magnetic fields are, however, particularly weak, and in most cases very close to the detection limit of current instrumentation. Because of this, there are only few observational studies that have successfully reconstructed the three components of the magnetic field vector in the chromosphere. Traditionally, the signal-to-noise ratio of observations has been improved by performing time-averages or spatial averages, but in both cases, some information is lost. More advanced techniques, like principal-component analysis, have also been employed to take advantage of the sparsity of the observations in the spectral direction. In the present study, we use the spatial coherence of the observations to reduce the noise using deep-learning techniques. We designed a neural network that is capable of recovering weak signals under a complex noise corruption (including instrumental artifacts and non-linear post-processing). The training of the network is carried out without a priori knowledge of the clean signals, or an explicit statistical characterization of the noise or other corruption. We only use the same observations as our generative model. The performance of this method is demonstrated on both synthetic experiments and real data. We show examples of the improvement in typical signals obtained in current telescopes such as the Swedish 1 m Solar Telescope. The presented method can recover weak signals equally well no matter what spectral line or spectral sampling is used. It is especially suitable for cases when the wavelength sampling is scarce.

Place, publisher, year, edition, pages
2019. Vol. 629, article id A99
Keywords [en]
Sun: magnetic fields, techniques: image processing, methods: data analysis, polarization
National Category
Astronomy, Astrophysics and Cosmology
Identifiers
URN: urn:nbn:se:su:diva-174853DOI: 10.1051/0004-6361/201936069ISI: 000485214900003OAI: oai:DiVA.org:su-174853DiVA, id: diva2:1361110
Available from: 2019-10-15 Created: 2019-10-15 Last updated: 2019-10-15Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full text

Search in DiVA

By author/editor
Diaz Baso, Carlos Joséde la Cruz Rodriguez, JaimeDanilovic, Sanja
By organisation
Department of Astronomy
In the same journal
Astronomy and Astrophysics
Astronomy, Astrophysics and Cosmology

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 3 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf