Adrita Khan

Greetings, everyone. I am Adrita Khan. I am a graduate of the University of Science, Malaysia (USM) with a major in Physics and a minor in Astronomy. My research interests lie in theoretical and observational cosmology, including large-scale structure, dark matter, dark energy, high-energy astroparticle physics, and machine learning applications in astrophysics.

My research focuses on modified gravity theories through cross-correlation analyses of the Cosmic Microwave Background (CMB) and galaxy data. I develop machine learning and deep learning methods for radio astronomy, including automated classification of bent radio AGN and semi-supervised learning approaches. I am currently working on gamma-ray burst redshift estimation and on developing the Explainable Polynomial Chebyshev Network (EPCN), a neural architecture that incorporates interpretable interaction features into Chebyshev-based frameworks.

My research goal is to advance precision cosmology at the intersection of theory and observation, particularly using data from next-generation surveys such as the Vera C. Rubin Observatory's LSST, the Euclid mission, and DESI. I use computational approaches including machine learning, Bayesian inference, and cosmological emulation to extract constraints on the universe's origin, evolution, and matter–energy composition. I am committed to fostering diversity, equity, and inclusion within the academic community.