Inpainting via Generative Adversarial Networks for CMB data analysis

Abstract

In this work, we propose a new method to inpaint the CMB signal in regions masked out following a point source extraction process. We adopt a modified Generative Adversarial Network (GAN) and compare different combinations of internal (hyper-)parameters and training strategies. We study the performance using a suitable ${\mathcal{C}}_r$ variable in order to estimate the performance regarding the CMB power spectrum recovery. We consider a test set where one point source is masked out in each sky patch with a 1.83 $\times$ 1.83 squared degree extension, which, in our gridding, corresponds to 64 $\times$ 64 pixels. The GAN is optimized for estimating performance on Planck 2018 total intensity simulations. The training makes the GAN effective in reconstructing a masking corresponding to about 1500 pixels with $1\%$ error down to angular scales corresponding to about 5 arcminutes.

arXiv comment19 pages, 21 figures. Prepared for submission to JCAP. All codes will be published after acceptance

References in corpus (7)

• Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation: Results with Advanced LIGO Data
• Multi-Detector Multi-Component spectral matching and applications for CMB data analysis
• Painting with baryons: augmenting N-body simulations with gas using deep generative models
• DeepSource: Point Source Detection using Deep Learning
• Using inpainting to construct accurate cut-sky CMB estimators
• Cosmic String Detection with Tree-Based Machine Learning
• Predicting CMB dust foreground using galactic 21 cm data

Cited by in corpus (4)

• Full-sky Cosmic Microwave Background Foreground Cleaning Using Machine Learning
• Deep learning approach for identification of HII regions during reionization in 21-cm observations
• Encoding large scale cosmological structure with Generative Adversarial Networks
• Decoding Dark Matter Substructure without Supervision