Predicting spectral features in galaxy spectra from broad-band photometry

TL;DR

This paper investigates how well broad-band photometry can predict galaxy spectral emission features and classify galaxy types, potentially improving future redshift surveys by reducing the need for spectral data.

Contribution

It demonstrates that galaxy emission lines and classifications can be effectively predicted from broad-band photometry using neural networks and regression techniques, aiding survey efficiency.

Findings

Recombination lines are well predicted by galaxy colours.

Some collisional lines can be predicted from colours, others cannot.

Photometry alone can classify AGN and star-forming galaxies reasonably well.

Abstract

We explore the prospects of predicting emission line features present in galaxy spectra given broad-band photometry alone. There is a general consent that colours, and spectral features, most notably the 4000 A break, can predict many properties of galaxies, including star formation rates and hence they could infer some of the line properties. We argue that these techniques have great prospects in helping us understand line emission in extragalactic objects and might speed up future galaxy redshift surveys if they are to target emission line objects only. We use two independent methods, Artifical Neural Neworks (based on the ANNz code) and Locally Weighted Regression (LWR), to retrieve correlations present in the colour N-dimensional space and to predict the equivalent widths present in the corresponding spectra. We also investigate how well it is possible to separate galaxies with and without lines from broad band photometry only. We find, unsurprisingly, that recombination lines can be well predicted by galaxy colours. However, among collisional lines some can and some cannot be predicted well from galaxy colours alone, without any further redshift information. We also use our techniques to estimate how much information contained in spectral diagnostic diagrams can be recovered from broad-band photometry alone. We find that it is possible to classify AGN and star formation objects relatively well using colours only. We suggest that this technique could be used to considerably improve redshift surveys such as the upcoming FMOS survey and the planned WFMOS survey.