Bringing Manifold Learning and Dimensionality Reduction to SED Fitters
We show that unsupervised machine learning techniques are a valuable tool for both visualizing and computationally accelerating the estimation of galaxy physical properties from photometric data. As a proof of concept, we use self-organizing maps (SOMs) to visualize a spectral energy distribution (SED) model library in the observed photometry space. The resulting visual maps allow for a better understanding of how the observed data maps to physical properties and allows for better optimization of the model libraries for a given set of observational data. Next, the SOMs are used to estimate the physical parameters of 14,000 z ~ 1 galaxies in the COSMOS field and are found to be in agreement with those measured with SED fitting. However, the SOM method is able to estimate the full probability distribution functions for each galaxy up to ~10^6 times faster than direct model fitting. We conclude by discussing how this acceleration, as well as learning how the galaxy data manifold maps to physical parameter space and visualizing this mapping in lower dimensions, helps overcome other challenges in galaxy formation and evolution.
Additional Information© 2019 The American Astronomical Society. Received 2019 May 23; revised 2019 July 11; accepted 2019 July 22; published 2019 August 9. We wish to thank the referee for very helpful comments that improved the content and presentation of this paper. This work used SOMPY, a python package for SOMs (main contributors: Vahid Moosavi @sevamoo, Sebastian Packmann @sebastiandev, Iván Vallás @ivallesp). We are thankful to NVIDIA for the GPU granted as their academic grant program. Parts of this research were carried out at the Jet Propulsion Laboratory, California Institute of Technology, under a contract with the National Aeronautics and Space Administration.
Published - Hemmati_2019_ApJL_881_L14.pdf
Submitted - 1905.10379.pdf