REVIEW 5 cited by
A Generative Modeling Approach to Reconstructing 21-cm Tomographic Data
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Analyses of the cosmic 21-cm signal are hampered by astrophysical foregrounds that are far stronger than the signal itself. These foregrounds, typically confined to a wedge-shaped region in Fourier space, often necessitate the removal of a vast majority of modes, thereby degrading the quality of the data anisotropically. To address this challenge, we introduce a novel deep generative model based on stochastic interpolants to reconstruct the 21-cm data lost to wedge filtering. Our method leverages the non-Gaussian nature of the 21-cm signal to effectively map wedge-filtered 3D lightcones to samples from the conditional distribution of wedge-recovered lightcones. We demonstrate how our method is able to restore spatial information effectively, considering both varying cosmological initial conditions and astrophysics. Furthermore, we discuss a number of future avenues where this approach could be applied in analyses of the 21-cm signal, potentially offering new opportunities to improve our understanding of the Universe during the epochs of cosmic dawn and reionization.
Forward citations
Cited by 5 Pith papers
-
Seeing Wiggles without Seeing Wiggles: BAO Recovery in 21 cm Intensity Mapping with Deep Learning
A 3D U-Net trained only on BAO-free 21 cm simulations recovers BAO wiggles from small-scale modes outside the foreground wedge, indicating physical mode coupling.
-
Fast Sampling of Cosmological Initial Conditions with Gaussian Neural Posterior Estimation
Cosmological initial conditions can be sampled from a learned Gaussian posterior with a Fourier-diagonal covariance, giving thousands of reconstructions in seconds on a GPU.
-
An Alcock-Paczynski Test on Reionization Bubbles for Cosmology
Stacks of reionization HII bubbles act as standard spheres, allowing a forecast ~2% measurement of D_A H at z=7.5 with SKA-like 21-cm data.
-
Reproducibility of machine learning analyses of 21 cm reionization maps
Convolutional networks trained on 21 cm reionization images often memorize simulation boxes rather than physics, yielding high same-box test scores but poor performance on unseen simulations.
-
Deep learning with hybrid frequency differencing and principal component analysis for 21-cm foreground and beam mitigation
A two-channel UNet combining frequency differencing and PCA preprocessing recovers the 21-cm HI power spectrum at large scales under realistic beam effects, improving cross-correlation by 5-8% over single-channel baselines.
Discussion (0). Continue with ORCID to comment.