Inferring physical properties of galaxies from their emission line spectra

TL;DR

This paper introduces GAME, a machine learning tool that accurately infers galaxy physical properties from emission line spectra, outperforming traditional diagnostics and applicable to various spectroscopic data.

Contribution

The paper presents GAME, a novel supervised machine learning code for estimating galaxy properties from emission lines, with improved accuracy and broader applicability.

Findings

GAME achieves high predictive accuracy for metallicity and column density.

GAME outperforms traditional emission line diagnostics in accuracy.

It is versatile for use with different spectroscopic data and simulations.

Abstract

We present a new approach based on Supervised Machine Learning (SML) algorithms to infer key physical properties of galaxies (density, metallicity, column density and ionization parameter) from their emission line spectra. We introduce a numerical code (called GAME, GAlaxy Machine learning for Emission lines) implementing this method and test it extensively. GAME delivers excellent predictive performances, especially for estimates of metallicity and column densities. We compare GAME with the most widely used diagnostics (e.g. R$_{23}$, [NII]$\lambda$6584 / H$\alpha$ indicators) showing that it provides much better accuracy and wider applicability range. GAME is particularly suitable for use in combination with Integral Field Unit (IFU) spectroscopy, both for rest-frame optical/UV nebular lines and far-infrared/sub-mm lines arising from Photo-Dissociation Regions. Finally, GAME can also be applied to the analysis of synthetic galaxy maps built from numerical simulations.