Flow-based neural networks for scalable high resolution imaging of VLBI observations
Abstract
Bayesian sampling methods in very-long-baseline interferometry enable reliable imaging of astronomical sources with a record high angular resolution. However, even after the transition from classical MCMC methods to flow-based neural networks, they remain computationally expensive as the number of recovered features grows. We used WaveletFlow neural network architecture to increase the number of pixels in the recovered image distribution, addressing the scaling issues of previous models. We applied the algorithm to both model data and archive RadioAstron project observations of M87 and ALMA telescope observations of HL Tau. While yielding comparable fidelity of the individual images, the algorithm provides more statistical information compared to CLEAN, which may be crucial for future research on compact astronomical objects such as active galactic nuclei.
Related
- Denoising Interferometric Observations Using Visibility-Informed Neural Networks
- Cracking open the 'dragon egg'. ALMA 1.3mm observations of a compact, young high-mass core candidate at 30mas resolution
- Spatially variant neural blind deconvolution to reconstruct ground-based solar observations
- Wave excitation by a collapsing granule: insights from IFU observations and high-resolution RMHD simulations
- High-resolution CO ( J = 1–0) and ( J = 3–2) Observations of Molecular Counterparts to the Double Helix Nebula in the Galactic Center
BibTeX
@misc{kats2026flowbased,
title = {{Flow-based neural networks for scalable high resolution imaging of VLBI observations}},
author = {Lev Kats and Alexey Goldin and Andrey S. Andrianov},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.38978},
eprint = {2610.38978},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.38978},
}
RIS
TY - UNPB
TI - Flow-based neural networks for scalable high resolution imaging of VLBI observations
AU - Lev Kats
AU - Alexey Goldin
AU - Andrey S. Andrianov
PY - 2026
DA - 2026/10/28
PB - arXiv
DO - 10.48550/arxiv.2610.38978
UR - https://arxiv.org/abs/2610.38978
AB - Bayesian sampling methods in very-long-baseline interferometry enable reliable imaging of astronomical sources with a record high angular resolution. However, even after the transition from classical MCMC methods to flow-based neural networks, they remain computationally expensive as the number of recovered features grows. We used WaveletFlow neural network architecture to increase the number of pixels in the recovered image distribution, addressing the scaling issues of previous models. We applied the algorithm to both model data and archive RadioAstron project observations of M87 and ALMA telescope observations of HL Tau. While yielding comparable fidelity of the individual images, the algorithm provides more statistical information compared to CLEAN, which may be crucial for future research on compact astronomical objects such as active galactic nuclei.
ER -