Issue |
A&A
Volume 664, August 2022
|
|
---|---|---|
Article Number | A134 | |
Number of page(s) | 21 | |
Section | Astronomical instrumentation | |
DOI | https://doi.org/10.1051/0004-6361/202142113 | |
Published online | 19 August 2022 |
Deep learning-based imaging in radio interferometry
1
Astroparticle Physics, TU Dortmund University,
Otto-Hahn-Straβe 4a,
44227
Dortmund, Germany
e-mail: kevin3.schmidt@tu-dortmund.de; felix.geyer@tu-dortmund.de
2
Hamburger Sternwarte, University of Hamburg,
Gojenbergsweg 112,
21029
Hamburg, Germany
3
INAF – Istituto di Radioastronomia,
via P. Gobetti 101,
40129
Bologna, Italy
Received:
30
August
2021
Accepted:
22
March
2022
Context. The sparse layouts of radio interferometers result in an incomplete sampling of the sky in Fourier space which leads to artifacts in the reconstructed images. Cleaning these systematic effects is essential for the scientific use of radiointerferometric images.
Aims. Established reconstruction methods are often time-consuming, require expert knowledge, and suffer from a lack of reproducibility. We have developed a prototype deep learning-based method that generates reproducible images in an expedient fashion.
Methods. To this end, we take advantage of the efficiency of convolutional neural networks to reconstruct image data from incomplete information in Fourier space. The neural network architecture is inspired by super-resolution models that utilize residual blocks. Using simulated data of radio galaxies that are composed of Gaussian components, we trained deep learning models whose reconstruction capability is quantified using various measures.
Results. The reconstruction performance is evaluated on clean and noisy input data by comparing the resulting predictions with the true source images. We find that source angles and sizes are well reproduced, while the recovered fluxes show substantial scatter, albeit not worse than existing methods without fine-tuning. Finally, we propose more advanced approaches using deep learning that include uncertainty estimates and a concept to analyze larger images.
Key words: galaxies: active / radio continuum: galaxies / methods: data analysis / techniques: image processing / techniques: interferometric
© ESO 2022
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.