Abstract
ABSTRACT We present ‘Pix2Prof’, a deep learning model that can eliminate any manual steps taken when measuring galaxy profiles. We argue that a galaxy profile of any sort is conceptually similar to a natural language image caption. This idea allows us to leverage image captioning methods from the field of natural language processing, and so we design Pix2Prof as a float sequence ‘captioning’ model suitable for galaxy profile inference. We demonstrate the technique by approximating a galaxy surface brightness (SB) profile fitting method that contains several manual steps. Pix2Prof processes ∼1 image per second on an Intel Xeon E5-2650 v3 CPU, improving on the speed of the manual interactive method by more than two orders of magnitude. Crucially, Pix2Prof requires no manual interaction, and since galaxy profile estimation is an embarrassingly parallel problem, we can further increase the throughput by running many Pix2Prof instances simultaneously. In perspective, Pix2Prof would take under an hour to infer profiles for 105 galaxies on a single NVIDIA DGX-2 system. A single human expert would take approximately 2 yr to complete the same task. Automated methodology such as this will accelerate the analysis of the next generation of large area sky surveys expected to yield hundreds of millions of targets. In such instances, all manual approaches – even those involving a large number of experts – will be impractical.
Highlights
Large astrophysical surveys such as the Sloan Digital Sky Survey (SDSS; York et al 2000), the Panoramic Survey Telescope and Rapid Response System (Pan-STARRS; Chambers et al 2016), the Hyper Suprime Cam (HSC; Aihara et al 2017) Subaru Strategic Program Survey, or the upcoming Vera C
While Pix2Prof can rapidly and accurately produce profiles of arbitrary length, there are some limitations to this technique
Any profile produced will be biased to the training set
Summary
Large astrophysical surveys such as the Sloan Digital Sky Survey (SDSS; York et al 2000), the Panoramic Survey Telescope and Rapid Response System (Pan-STARRS; Chambers et al 2016), the Hyper Suprime Cam (HSC; Aihara et al 2017) Subaru Strategic Program Survey, or the upcoming Vera C. A precursor to LSST, HSC’s 990 megapixel camera has already produced over 1 PB of imaging data (Aihara et al 2019). These surveys will be dwarfed by the upcoming LSST project. We are concerned with the automated direct analysis of galaxy imagery towards estimating galaxy properties such as size, luminosity, colour, and stellar mass To calculate these properties, one typically applies a photometric analysis that involves extracting and characterizing the spatial distribution of a galaxy’s light, described by a surface brightness (SB) profile. Machine learning is ideally suited for this task, and we apply it in this paper towards the specific problem of extracting SB profiles from multiband imaging data. The remainder of the paper is organized as follows: Section 2 introduces our approach; our results and validation are presented in Section 3; Section 4 addresses our global findings, and concludes with suggestions for broader application of the algorithm
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
