Inpainting CMB maps using Partial Convolutional Neural Networks

Abstract

We present a novel application of partial convolutional neural networks (PCNN) that can inpaint masked images of the cosmic microwave background. The network can reconstruct both the maps and the power spectra to a few percent for circular and irregularly shaped masks covering up to ~10% of the image area. By performing a Kolmogorov-Smirnov test we show that the reconstructed maps and power spectra are indistinguishable from the input maps and power spectra at the 99.9% level. Moreover, we show that PCNNs can inpaint maps with regular and irregular masks to the same accuracy. This should be particularly beneficial to inpaint irregular masks for the CMB that come from astrophysical sources such as galactic foregrounds. The proof of concept application shown in this paper shows that PCNNs can be an important tool in data analysis pipelines in cosmology.

17 pages, 6 figures, 1 table

References in corpus (10)

• HEALPix -- a Framework for High Resolution Discretization, and Fast Analysis of Data Distributed on the Sphere
• Efficient Computation of CMB anisotropies in closed FRW models
• MASTER of the CMB Anisotropy Power Spectrum: A Fast Method for Statistical Analysis of Large and Complex CMB Data Sets
• Planck 2018 results. IV. Diffuse component separation
• Error analysis of quadratic power spectrum estimates for CMB polarization: sampling covariance
• Full-sky Cosmic Microwave Background Foreground Cleaning Using Machine Learning
• Filling in CMB map missing data using constrained Gaussian realizations
• Using inpainting to construct accurate cut-sky CMB estimators
• Inpainting Galactic Foreground Intensity and Polarization maps using Convolutional Neural Network
• Fast Wiener filtering of CMB maps with Neural Networks

Cited by in corpus (9)

• Machine Learning for Observational Cosmology
• MillimeterDL: Deep Learning Simulations of the Microwave Sky
• Cosmological Particle Production and Pairwise Hotspots on the CMB
• An Unbiased Estimator of the Full-sky CMB Angular Power Spectrum at Large Scales using Neural Networks
• Inpainting hydrodynamical maps with deep learning
• Deep learning approach for identification of HII regions during reionization in 21-cm observations -- III. image recovery
• Self-supervised component separation for the extragalactic submillimeter sky
• Cosmic Kite: Auto-encoding the Cosmic Microwave Background
• Removing the mask -- reconstructing a scalar field on the sphere from a masked field