An Unsupervised Hunt for Gravitational Lenses

TL;DR

This paper presents an advanced semi-supervised learning approach combining simulation, data augmentation, and GANs to improve the automated detection of rare gravitational lenses in astronomical surveys, achieving high precision and recall.

Contribution

It introduces a novel method that integrates simulation, augmentation, and GANs to enhance gravitational lens detection with minimal labeled data.

Findings

Performance improved by an order of magnitude

High precision and recall achieved in lens classification

Method effective with limited positive samples

Abstract

Strong gravitational lenses allow us to peer into the farthest reaches of space by bending the light from a background object around a massive object in the foreground. Unfortunately, these lenses are extremely rare, and manually finding them in astronomy surveys is difficult and time-consuming. We are thus tasked with finding them in an automated fashion with few if any, known lenses to form positive samples. To assist us with training, we can simulate realistic lenses within our survey images to form positive samples. Naively training a ResNet model with these simulated lenses results in a poor precision for the desired high recall, because the simulations contain artifacts that are learned by the model. In this work, we develop a lens detection method that combines simulation, data augmentation, semi-supervised learning, and GANs to improve this performance by an order of magnitude. We perform ablation studies and examine how performance scales with the number of non-lenses and simulated lenses. These findings allow researchers to go into a survey mostly ``blind" and still classify strong gravitational lenses with high precision and recall.