An Integrated Pipeline for Cosmic Microwave Background Component Separation Study using Machine Learning

In this study, we present a novel pipeline that integrates the simulation of cosmic microwave background (CMB) signals with machine learning- based methods for separating foreground contaminants. We will compare our approach with established physics-based techniques, such as those applied in the Planck experiment but looking to future for Simon Observatory and CMB-S4 experiments. Our aim is to enhance current methodologies using machine learning to improve both the accuracy and efficiency of CMB signal separation in temperature and polarization domains. By achieving a more precise and efficient separation of CMB signals, particularly in polarization, we hope to deepen our understanding of the early universe's evolution.