Using Machine Learning to Study the Relationship Between Galaxy Morphology and Evolution

We can track the physical evolution of massive galaxies over time by characterizingthe morphological signatures inherent to different mechanisms of galactic assembly. Structural studies rely on a small set of measurements to bin galaxies into disk,spheroid and irregular classifications. These classes are correlated with colors, SFhistory and stellar masses. Rare and subtle features that are lost in such a genericclassification scheme are important for characterizing the evolution of galaxy morphology. We can connect the Hubble sequence observed for local galaxies to theirhigh redshift progenitors to determine the full distribution of galaxy morphologiesas a function of time over the entire lifetime of the Universe. To fully capture thecomplex morphological transformation of galaxies we need more useful classifications. To accomplish such a feat in a computationally tractable way we will need to convertgalaxy images to low-dimensional representations of only a few parameters.