Deep learning insights on galaxy formation and evolution

John Wu


The growth of galaxies is regulated by the amount of cold gas available to form stars. In order to constrain galaxy evolution models, it is critical to measure the interstellar gas mass and the abundance of heavy elements (metallicity) in the gas phase for large samples of galaxies. However, these properties are observationally difficult to measure, and galaxies' cold gas reservoirs are mostly invisible at optical wavelengths. One way to circumvent these challenges is to rely on the morphologies of galaxies, which are linked to their star formation and chemical enrichment histories. Deep learning offers a method for estimating the gas content and metallicity of galaxies purely from imaging data. Computer vision techniques also enable novel ways to analyze galaxy properties. I will discuss xSAGA, an ambitious deep learning campaign to identify new dwarf and satellite galaxies in the local Universe from Legacy Survey imaging, which will provide an unprecedented view of cosmic low-mass structure and galaxy formation in action. Interpretable and accurate deep learning tools will enable us to multiply the scientific returns of wide-field imaging surveys in the coming decade.

Date: Jeudi, le 22 avril 2021
Heure: 11:30
Lieu: Université de Montréal