Using convolutional neural networks to predict galaxy metallicity from three-colour images
| Autor: | John F. Wu, Steven Boada |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Physics
Mean squared error 010308 nuclear & particles physics media_common.quotation_subject Metallicity FOS: Physical sciences Astronomy and Astrophysics Astrophysics Astrophysics - Astrophysics of Galaxies 01 natural sciences Convolutional neural network Galaxy Spectral line Optical imaging Space and Planetary Science Sky Astrophysics of Galaxies (astro-ph.GA) 0103 physical sciences 010303 astronomy & astrophysics Image resolution media_common |
| Zdroj: | Monthly Notices of the Royal Astronomical Society. 484:4683-4694 |
| ISSN: | 1365-2966 0035-8711 |
| DOI: | 10.1093/mnras/stz333 |
| Popis: | We train a deep residual convolutional neural network (CNN) to predict the gas-phase metallicity ($Z$) of galaxies derived from spectroscopic information ($Z \equiv 12 + \log(\rm O/H)$) using only three-band $gri$ images from the Sloan Digital Sky Survey. When trained and tested on $128 \times 128$-pixel images, the root mean squared error (RMSE) of $Z_{\rm pred} - Z_{\rm true}$ is only 0.085 dex, vastly outperforming a trained random forest algorithm on the same data set (RMSE $=0.130$ dex). The amount of scatter in $Z_{\rm pred} - Z_{\rm true}$ decreases with increasing image resolution in an intuitive manner. We are able to use CNN-predicted $Z_{\rm pred}$ and independently measured stellar masses to recover a mass-metallicity relation with $0.10$ dex scatter. Because our predicted MZR shows no more scatter than the empirical MZR, the difference between $Z_{\rm pred}$ and $Z_{\rm true}$ can not be due to purely random error. This suggests that the CNN has learned a representation of the gas-phase metallicity, from the optical imaging, beyond what is accessible with oxygen spectral lines. 13 pages, 6 figures, accepted to MNRAS. Code is available at https://github.com/jwuphysics/galaxy-cnns |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|