Explore the intersection of deep learning and cosmological simulations in this 24-minute conference talk by Elena Giusarma from Michigan Tech. Discover how machine learning techniques are revolutionizing our ability to simulate the universe, offering new insights into galaxy formation and evolution. Delve into the application of astrostatistics and data science tools in analyzing vast datasets from Integral Field Unit surveys, galaxy morphology studies, and multi-wavelength observations. Learn about the potential of machine learning-powered outlier detection algorithms in identifying anomalous galaxies and pushing the boundaries of our current understanding. Gain insights into how these advanced computational methods are bridging the gap between observational data and theoretical models, including cosmological hydrodynamical simulations and dark matter-only simulations. Understand the broader context of this research within the field of galaxy formation physics and its implications for future astronomical surveys like Rubin, DESI, Roman, Euclid, and the SKA. Read more