Using deep Residual Networks to search for galaxy-Ly{\alpha} emitter lens candidates based on spectroscopic-selection

TL;DR

This paper introduces a deep Residual Network approach to identify galaxy-Lyα emitter lens candidates from spectroscopic data, achieving high accuracy and discovering new potential lenses in SDSS data.

Contribution

The study applies a 28-layer ResNet to spectroscopic data for lens candidate detection, with a large synthetic training set, demonstrating high accuracy and discovering new candidates.

Findings

Test accuracy of 99.54% on synthetic data

92.5% recovery rate of known candidates

536 new lens candidates identified

Abstract

More than one hundred galaxy-scale strong gravitational lens systems have been found by searching for the emission lines coming from galaxies with redshifts higher than the lens galaxies. Based on this spectroscopic-selection method, we introduce the deep Residual Networks (ResNet, a kind of deep Convolutional Neural Networks) to search for the galaxy-Ly$\alpha$ emitter (LAE) lens candidates by recognizing the Ly$\alpha$ emission lines coming from high redshift galaxies ($2 < z < 3$) in the spectra of early-type galaxies (ETGs) at middle redshift ($z\sim 0.5$). The spectra of the ETGs come from the Data Release 12 (DR12) of the Baryon Oscillation Spectroscopic Survey (BOSS) of the Sloan Digital Sky Survey \uppercase\expandafter{\romannumeral3} (SDSS-\uppercase\expandafter{\romannumeral3}). In this paper, we first build a 28 layers ResNet model, and then artificially synthesize 150,000 training spectra, including 140,000 spectra without Ly$\alpha$ lines and 10,000 ones with Ly$\alpha$ lines, to train the networks. After 20 training epochs, we obtain a near-perfect test accuracy at 0.9954. The corresponding loss is 0.0028 and the completeness is 93.6\%. We finally apply our ResNet model to our predictive data with 174 known lens candidates. We obtain 1232 hits including 161 of the 174 known candidates (92.5\% discovery rate). Apart from the hits found in other works, our ResNet model also find 536 new hits. We then perform several subsequent selections on these 536 hits and present 5 most believable lens candidates.