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

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 contami- nated by foreground emissions, obscuring the CMB signal and reducing its efficacy in constraining cosmological param- eters. We employ deep learning as a data-driven approach to CMB cleaning from multi-frequency full-sky maps. In partic- ular, 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- curately recovers the cleaned CMB sky map and resulting angular power spectrum while identifying regions of uncer- tainty. Finally, we discuss the current challenges and the path forward for deploying our model for CMB recovery on real observations.