Abstract
Astronomy is on the cusp of a data revolution, with facilities like the Vera Rubin Observatory (formerly LSST) and the Nancy Grace Roman Space Telescope (formerly WFIRST) posed to provide high-quality, multi band images over thousands of square degrees on the sky. With tens of billions of astronomical objects in these images, astronomers need to devise new methods to identify and classify stars and galaxies at scale. To address these challenges in astronomical data analysis, Prof Robertson and colleagues have developed Morpheus, a new model for generating pixel-level morphological classifications of astronomical sources. Morpheus leverages advances in deep learning to perform source detection, source segmentation, and morphological classification pixel-by-pixel via a semantic segmentation algorithm adopted from the field of computer vision. He will review the model and its performance, and shows applications to real astronomical data including the largest Hubble Space Telescope surveys taken to date.
Biography
Brant Robertson is a Professor in the Department of Astronomy and Astrophysics at the University of California, Santa Cruz. His research interests include theoretical topics related to galaxy formation, dark matter, hydrodynamics, machine learning, and numerical simulation methodologies. He was previously the John and Maureen Hendricks Visiting Professor at the Institute for Advanced Study, Princeton, NJ in 2019, and an Assistant Professor at the University of Arizona from 2011-2015. He held a Hubble Fellowship at the California Institute of Technology from 2009-2011, and a Spitzer and Institute Fellowship at the Kavli Institute for Cosmological Physics and Enrico Fermi Institute at the University of Chicago from 2006-2009. He earned his Ph.D. in Astronomy from Harvard University in 2006, and received his B.S. in Physics and Astronomy at the University of Washington, Seattle in 2001.
