Reconstructing the mid-infrared spectra of galaxies using ultraviolet to submillimeter photometry and Deep Generative Networks

TL;DR

This paper demonstrates that deep generative networks can accurately reconstruct mid-infrared galaxy spectra from limited ultraviolet to submillimeter photometry, enabling insights into galaxy physics with fewer observations.

Contribution

The study introduces a novel application of deep generative networks to reconstruct galaxy mid-infrared spectra from multi-wavelength photometry, expanding analysis capabilities in extragalactic surveys.

Findings

Deep Generative Networks can reconstruct spectra with ~70% accuracy.

The method effectively uses simulated radiative transfer models.

Reconstruction quality varies but is generally high.

Abstract

The mid-infrared spectra of galaxies are rich in features such as the Polycyclic Aromatic Hydrocarbon (PAH) and silicate dust features which give valuable information about the physics of galaxies and their evolution. For example they can provide information about the relative contribution of star formation and accretion from a supermassive black hole to the power output of galaxies. However, the mid-infrared spectra are currently available for a very small fraction of galaxies that have been detected in deep multi-wavelength surveys of the sky. In this paper we explore whether Deep Generative Network methods can be used to reconstruct mid-infrared spectra in the 5-35{\mu}m range using the limited multi-wavelength photometry in ~20 bands from the ultraviolet to the submillimeter which is typically available in extragalactic surveys. For this purpose we use simulated spectra computed with a combination of radiative transfer models for starbursts, active galactic nucleus (AGN) tori and host galaxies. We find that our method using Deep Generative Networks, namely Generative Adversarial Networks and Generative Latent Optimization models, can efficiently produce high quality reconstructions of mid-infrared spectra in ~70% of the cases.