Super-resolving Herschel SPIRE images using Convolutional Neural Networks
AstroML
Lynge
Lauritsen
Date Submitted
2021-04-30 00:00:00
The Open University
L. Lauritsen (The Open University), H. Dickinson (The Open University), S. Serjeant (The Open University), J. Bromley (The Open University), Chen-Fatt Lim (National Taiwan University, Academia Sinica Institute of Astronomy and Astrophysics), Zhen-Kai Gao (Academia Sinica Institute of Astronomy and Astrophysics, National Central University), Wei-Hao Wang (Academia Sinica Institute of Astronomy and Astrophysics)
Wide-field sub-millimetre surveys have driven many major advances in galaxy evolution in the past decade, but without extensive follow-ups the coarse angular resolution of these surveys limits the science exploitation. This has driven many deconvolution efforts. Generative Adversarial Networks have already been used to attempt deconvolutions on optical data. In this talk I will present an autoencoder with a novel loss function to overcome this problem at submm wavelengths. This approach is successfully demonstrated on Herschel SPIRE COSMOS data, with the super-resolving target being the JCMT SCUBA-2 observations of the same field. We reproduce the JCMT SCUBA-2 images with surprisingly high fidelity, and quantify the point source flux constraints using this autoencoder.
All attendees are expected to show respect and courtesy to other attendees and staff, and to adhere to the NAM Code of Conduct.