Cosmic Microwave Background Recovery: A Graph-Based Bayesian Convolutional Network Approach

Abstract

The cosmic microwave background (CMB) is a significant source of knowledge about the origin and evolution of our universe. However, observations of the CMB are contaminated by foreground emissions, obscuring the CMB signal and reducing its efficacy in constraining cosmological parameters. We employ deep learning as a data-driven approach to CMB cleaning from multi-frequency full-sky maps. In particular, we develop a graph-based Bayesian convolutional neural network based on the U-Net architecture that predicts cleaned CMB with pixel-wise uncertainty estimates. We demonstrate the potential of this technique on realistic simulated data based on the Planck mission. We show that our model ac- accurately recovers the cleaned CMB sky map and resulting angular power spectrum while identifying regions of uncertainty. Finally, we discuss the current challenges and the path forward for deploying our model for CMB recovery on real observations.

Datacube segmentation via deep spectral clustering

“…[11,12]. and references therein), as highlighted in recent works [13,14], which have extracted subtle cosmological signals from complex datasets more effectively than traditional methods. Moreover, the application of deep learning in transient astrophysical phenomena, such as fast radio bursts and supernovae, has enabled rapid data processing and analysis, crucial for timely scientific observations (e.g.…”