The infra-red luminosities of ~332,000 SDSS galaxies predicted from artificial neural networks and the Herschel Stripe 82 survey

TL;DR

This study uses artificial neural networks trained on Herschel data to accurately predict infrared luminosities for over 330,000 SDSS galaxies, enabling better star formation rate estimates even in AGN-hosting galaxies.

Contribution

The paper introduces a neural network approach to estimate galaxy IR luminosities for large samples, overcoming limitations of shallow IR surveys and providing a comprehensive catalog.

Findings

Neural networks predict L_IR with ~0.23 dex scatter and no systematic bias.

The method performs well for both star-forming and AGN-hosting galaxies.

A public catalog of L_IR predictions for over 330,000 SDSS galaxies is provided.

Abstract

The total infra-red (IR) luminosity (L_IR) can be used as a robust measure of a galaxy's star formation rate (SFR), even in the presence of an active galactic nucleus (AGN), or when optical emission lines are weak. Unfortunately, existing all sky far-IR surveys, such as the Infra-red Astronomical Satellite (IRAS) and AKARI, are relatively shallow and are biased towards the highest SFR galaxies and lowest redshifts. More sensitive surveys with the Herschel Space Observatory are limited to much smaller areas. In order to construct a large sample of L_IR measurements for galaxies in the nearby universe, we employ artificial neural networks (ANNs), using 1136 galaxies in the Herschel Stripe 82 sample as the training set. The networks are validated using two independent datasets (IRAS and AKARI) and demonstrated to predict the L_IR with a scatter sigma ~ 0.23 dex, and with no systematic offset. Importantly, the ANN performs well for both star-forming galaxies and those with an AGN. A public catalog is presented with our L_IR predictions which can be used to determine SFRs for 331,926 galaxies in the Sloan Digital Sky Survey (SDSS), including ~ 129,000 SFRs for AGN-dominated galaxies for which SDSS SFRs have large uncertainties.