2021
DOI: 10.48550/arxiv.2111.03249
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Deep Radio Interferometric Imaging with POLISH: DSA-2000 and weak lensing

Liam Connor,
Katherine L. Bouman,
Vikram Ravi
et al.

Abstract: Radio interferometry allows astronomers to probe small spatial scales that are often inaccessible with single-dish instruments. However, recovering the radio sky from an interferometer is an ill-posed deconvolution problem that astronomers have worked on for half a century. More challenging still is achieving resolution below the array's diffraction limit, known as super-resolution imaging. To this end, we have developed a new learning-based approach for radio interferometric imaging, leveraging recent advance… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2022
2022
2022
2022

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(1 citation statement)
references
References 35 publications
0
1
0
Order By: Relevance
“…The reconstructions are however affected by patching artefacts. Most recently, Connor et al (2021) developed a DNN dubbed POLISH, show promising results on simulations for a simple super-resolution task, also demonstrating an ability to perform endto-end reconstruction on point-like sources from Very Large Array (VLA) observations. In summary, beyond the generalizability and interpretability issues, these approaches have neither been thoroughly validated for high resolution high dynamic range imaging of complex structure involving diffuse and faint emission, nor compared with both CLEAN and state-of-the-art optimization approaches.…”
Section: Deep Learning and First Ri Imaging Applicationsmentioning
confidence: 99%
“…The reconstructions are however affected by patching artefacts. Most recently, Connor et al (2021) developed a DNN dubbed POLISH, show promising results on simulations for a simple super-resolution task, also demonstrating an ability to perform endto-end reconstruction on point-like sources from Very Large Array (VLA) observations. In summary, beyond the generalizability and interpretability issues, these approaches have neither been thoroughly validated for high resolution high dynamic range imaging of complex structure involving diffuse and faint emission, nor compared with both CLEAN and state-of-the-art optimization approaches.…”
Section: Deep Learning and First Ri Imaging Applicationsmentioning
confidence: 99%