Super-resolving Herschel imaging: a proof of concept using Deep Neural Networks

TL;DR

This paper introduces a deep neural network autoencoder with a novel loss function to enhance the resolution of Herschel sub-millimetre images, enabling more detailed galaxy observations by effectively reproducing higher-resolution data.

Contribution

It presents a new autoencoder-based method with a custom loss function for super-resolution in sub-millimetre astronomy, demonstrated on Herschel and JCMT data.

Findings

High-fidelity reproduction of JCMT images from Herschel data

Improved point source flux and position accuracy

Enhanced completeness and purity in super-resolved images

Abstract

Wide-field sub-millimetre surveys have driven many major advances in galaxy evolution in the past decade, but without extensive follow-up observations the coarse angular resolution of these surveys limits the science exploitation. This has driven the development of various analytical deconvolution methods. In the last half a decade Generative Adversarial Networks have been used to attempt deconvolutions on optical data. Here we present an autoencoder with a novel loss function to overcome this problem in the sub-millimeter wavelength range. This approach is successfully demonstrated on Herschel SPIRE 500$\mu$m COSMOS data, with the super-resolving target being the JCMT SCUBA-2 450$\mu$m observations of the same field. We reproduce the JCMT SCUBA-2 images with high fidelity using this autoencoder. This is quantified through the point source fluxes and positions, the completeness and the purity.