Gaussian Process Classification for Galaxy Blend Identification in LSST

TL;DR

This paper compares a standard peak-finding method with a novel Gaussian process classifier for identifying galaxy blends in LSST images, demonstrating the Gaussian process model's competitive accuracy and reliable probability estimates.

Contribution

It introduces a Gaussian process classification model for galaxy blend detection in LSST images, showing it performs comparably to existing methods and provides reliable probability outputs.

Findings

Gaussian process classifier is competitive with peak-finding and CNN methods.

The Gaussian process model naturally provides reliable classification probabilities.

Standard peak-finding method's reliability is limited in blend classification.

Abstract

A significant fraction of observed galaxies in the Rubin Observatory Legacy Survey of Space and Time (LSST) will overlap at least one other galaxy along the same line of sight, in a so-called "blend." The current standard method of assessing blend likelihood in LSST images relies on counting up the number of intensity peaks in the smoothed image of a blend candidate, but the reliability of this procedure has not yet been comprehensively studied. Here we construct a realistic distribution of blended and unblended galaxies through high-fidelity simulations of LSST-like images, and from this we examine the blend classification accuracy of the standard peak-finding method. Furthermore, we develop a novel Gaussian process blend classifier model, and show that this classifier is competitive with both the peak-finding method as well as with a convolutional neural network model. Finally, whereas the peak-finding method does not naturally assign probabilities to its classification estimates, the Gaussian process model does, and we show that the Gaussian process classification probabilities are generally reliable.