Speaker
Description
Galaxies are the primary tracers of the large-scale structure of the Universe and are traditionally used through summary statistics such as correlation functions and power spectra to constrain cosmological models. However, galaxies themselves are complex systems whose spatial distribution, internal properties, and environments may encode additional cosmological information beyond these traditional summaries. In this talk, I explore how modern machine learning techniques can help uncover this information directly from galaxy populations. I will present recent work using graph neural networks (GNNs) to infer cosmological parameters from galaxy catalogs, studies investigating the cosmological information content of individual galaxies, and ongoing efforts to extract reliable galaxy properties such as redshift from imaging and photometric data. Together, these approaches suggest new ways to connect galaxies and cosmology, potentially expanding the information accessible in the era of precision large-scale structure surveys.