Pith. sign in

REVIEW 2 cited by

The stability of deep learning for 21cm foreground removal across various sky models and frequency-dependent systematics

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

arxiv 2311.00493 v1 pith:CEEKYJY5 submitted 2023-11-01 astro-ph.CO

classification astro-ph.CO
keywords dataacrossforegroundmodelmodelsremovalsystematicsnetwork
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Deep learning (DL) has recently been proposed as a novel approach for 21cm foreground removal. Before applying DL to real observations, it is essential to assess its consistency with established methods, its performance across various simulation models and its robustness against instrumental systematics. This study develops a commonly used U-Net and evaluates its performance for post-reionisation foreground removal across three distinct sky simulation models based on pure Gaussian realisations, the Lagrangian perturbation theory, and the Planck sky model. Stable outcomes across the models are achieved provided that training and testing data align with the same model. On average, the residual foreground in the U-Net reconstructed data is $\sim$10% of the signal across angular scales at the considered redshift range. Comparable results are found with traditional approaches. However, blindly using a network trained on one model for data from another model yields inaccurate reconstructions, emphasising the need for consistent training data. The study then introduces frequency-dependent Gaussian beams and gain drifts to the test data. The network struggles to denoise data affected by "unexpected" systematics without prior information. However, after re-training consistently with systematics-contaminated data, the network effectively restores its reconstruction accuracy. This highlights the importance of incorporating prior systematics knowledge during training for successful denoising. Our work provides critical guidelines for using DL for 21cm foreground removal, tailored to specific data attributes. Notably, it is the first time that DL has been applied to the Planck sky model being most realistic foregrounds at present.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Foreground Subtraction with a Tensor-Based Oriented Singular Value Decomposition Method for HI Experiments

    astro-ph.IM 2026-08 conditional novelty 5.0 of 10

    A tensor-oriented singular value decomposition can subtract radio foregrounds from 21 cm intensity mapping data while preserving more cosmological signal than standard PCA.

  2. Machine Learning and the SKA for Cosmic Dawn and the Epoch of Reionization

    astro-ph.IM 2026-07 accept novelty 2.5 of 10

    A multi-author overview of machine-learning algorithms proposed for instrument modelling, data analysis, simulation and inference in SKA Cosmic Dawn and Epoch of Reionization science.

Pith tools