Speaker
Description
One of the most effective observational instruments for understanding the universe's formation, composition, and evolution is the Cosmic Microwave Background (CMB). However, increasing data volumes, complex noise structures, and the need for high-precision cosmological inference present growing challenges for conventional CMB processing methods. The goal of this project is to develop an AI-driven framework that enhances the processing, reconstruction, and interpretation of CMB temperature and polarization data. The work will focus on improving noise suppression, foreground removal, feature extraction, and cosmological parameter estimation using machine learning and deep learning techniques. The proposed approach aims to combine data-driven methodologies with physics-informed models to produce an analysis that is faster, more accurate, and more reliable than traditional methods. Ultimately, this work seeks to contribute to next-generation CMB research and deepen our understanding of the early Universe by evaluating performance gains and demonstrating the potential of AI to advance cosmology through the application of the developed tools to existing datasets such as Planck, WMAP, ACT, or simulated CMB maps.
| Stream | Science or Engineering |
|---|