Astronomy Re-envisioned: Investigating the Physics of Galaxy Evolution with Machine Learning
John Wu, Space Telescope Science Institute
Friday, March 1 at 12:45
Astronomical imaging of galaxies reveals how they formed and evolved. While spectroscopy is necessary for measuring galaxies' physical properties, such as their cold gas content or metallicity, it is now possible to reliably predict these properties direct from three-color optical image cutouts by using convolutional neural networks (CNNs). Even the entire optical spectrum can be determined purely from galaxy images. We have also found that highly optimized CNNs can robustly identify nearby dwarf galaxies from large-area imaging surveys, resulting in a dramatic increase in the total number of satellite galaxy systems we can study at low redshifts. Finally, we present a novel theoretical approach for modeling galaxies, dark matter halos, and their cosmic surroundings using graph neural networks. These applications are prime examples of how deep learning can facilitate new discoveries in galaxy evolution and near-field cosmology.