PSFGAN: a generative adversarial network system for separating quasar point sources and host galaxy light

TL;DR

This paper introduces PSFGAN, a GAN-based system that effectively separates quasar point sources from host galaxy light, outperforming traditional parametric methods in accuracy, robustness, and computational efficiency.

Contribution

The paper presents a novel GAN-based approach for quasar and galaxy light separation, demonstrating improved accuracy and robustness over parametric methods like GALFIT.

Findings

PSFGAN recovers magnitudes with 49% less systematic error.

It is more tolerant to PSF inaccuracies than parametric methods.

Evaluation is 40 times faster than GALFIT.

Abstract

The study of unobscured active galactic nuclei (AGN) and quasars depends on the reliable decomposition of the light from the AGN point source and the extended host galaxy light. The problem is typically approached using parametric fitting routines using separate models for the host galaxy and the point spread function (PSF). We present a new approach using a Generative Adversarial Network (GAN) trained on galaxy images. We test the method using Sloan Digital Sky Survey (SDSS) r-band images with artificial AGN point sources added which are then removed using the GAN and with parametric methods using GALFIT. When the AGN point source PS is more than twice as bright as the host galaxy, we find that our method, PSFGAN, can recover PS and host galaxy magnitudes with smaller systematic error and a lower average scatter ($49\%$). PSFGAN is more tolerant to poor knowledge of the PSF than parametric methods. Our tests show that PSFGAN is robust against a broadening in the PSF width of $\pm 50\%$ if it is trained on multiple PSF's. We demonstrate that while a matched training set does improve performance, we can still subtract point sources using a PSFGAN trained on non-astronomical images. While initial training is computationally expensive, evaluating PSFGAN on data is more than $40$ times faster than GALFIT fitting two components. Finally, PSFGAN it is more robust and easy to use than parametric methods as it requires no input parameters.