Identification of Galaxy-Galaxy Strong Lens Candidates in the DECam Local Volume Exploration Survey Using Machine Learning

TL;DR

This paper uses a convolutional neural network to identify galaxy-galaxy strong lens candidates in the DECam Local Volume Exploration Survey, discovering 581 candidates with many previously unreported, demonstrating the effectiveness of machine learning in astronomical surveys.

Contribution

The study introduces a CNN-based method for detecting strong lens candidates in large astronomical datasets, resulting in a new catalog with many novel candidates and potential quadruply lensed quasars.

Findings

Identified 581 strong lens candidates, 562 are new.

Discovered 8 potential quadruply lensed quasars.

Demonstrated the effectiveness of CNNs in large-scale lens searches.

Abstract

We perform a search for galaxy-galaxy strong lens systems using a convolutional neural network (CNN) applied to imaging data from the first public data release of the DECam Local Volume Exploration Survey (DELVE), which contains $\sim 520$ million astronomical sources covering $\sim 4,000$ $\mathrm{deg}^2$ of the southern sky to a $5\sigma$ point-source depth of $g=24.3$, $r=23.9$, $i=23.3$, and $z=22.8$ mag. Following the methodology of similar searches using DECam data, we apply color and magnitude cuts to select a catalog of $\sim 11$ million extended astronomical sources. After scoring with our CNN, the highest scoring 50,000 images were visually inspected and assigned a score on a scale from 0 (definitely not a lens) to 3 (very probable lens). We present a list of 581 strong lens candidates, 562 of which are previously unreported. We categorize our candidates using their human-assigned scores, resulting in 55 Grade A candidates, 149 Grade B candidates, and 377 Grade C candidates. We additionally highlight eight potential quadruply lensed quasars from this sample. Due to the location of our search footprint in the northern Galactic cap ($b > 10$ deg) and southern celestial hemisphere (${\rm Dec.}<0$ deg), our candidate list has little overlap with other existing ground-based searches. Where our search footprint does overlap with other searches, we find a significant number of high-quality candidates which were previously unidentified, indicating a degree of orthogonality in our methodology. We report properties of our candidates including apparent magnitude and Einstein radius estimated from the image separation.