The Strong Gravitational Lens Finding Challenge

TL;DR

This paper presents an open challenge to develop automated methods for identifying gravitational lenses in large imaging surveys, demonstrating that machine learning techniques can outperform human inspection in accuracy and speed.

Contribution

It introduces a large-scale lens finding challenge and evaluates various automated methods, including CNNs and SVMs, for their effectiveness in detecting lenses in massive datasets.

Findings

Several methods identified over half the lenses with minimal false positives.

Automated methods are fast enough for upcoming large-scale surveys.

Machine learning approaches outperform human visual inspection.

Abstract

Large scale imaging surveys will increase the number of galaxy-scale strong lensing candidates by maybe three orders of magnitudes beyond the number known today. Finding these rare objects will require picking them out of at least tens of millions of images and deriving scientific results from them will require quantifying the efficiency and bias of any search method. To achieve these objectives automated methods must be developed. Because gravitational lenses are rare objects reducing false positives will be particularly important. We present a description and results of an open gravitational lens finding challenge. Participants were asked to classify 100,000 candidate objects as to whether they were gravitational lenses or not with the goal of developing better automated methods for finding lenses in large data sets. A variety of methods were used including visual inspection, arc and ring finders, support vector machines (SVM) and convolutional neural networks (CNN). We find that many of the methods will be easily fast enough to analyse the anticipated data flow. In test data, several methods are able to identify upwards of half the lenses after applying some thresholds on the lens characteristics such as lensed image brightness, size or contrast with the lens galaxy without making a single false-positive identification. This is significantly better than direct inspection by humans was able to do. (abridged)