Deep Learning for Strong Lensing Search: Tests of the Convolutional Neural Networks and New Candidates from KiDS DR3

TL;DR

This paper applies convolutional neural networks to identify strong gravitational lensing systems in the KiDS survey, testing robustness and discovering new candidates with different training sets and PSF variations.

Contribution

It introduces a CNN-based method for strong lensing detection using both simulated and real data, and evaluates its robustness against PSF and training set size variations.

Findings

Identified 48 high-probability lens candidates, including 27 new ones.

Network performance remains stable across PSF variations from 0.4 to 2 times median PSF.

Training set size from 0.1 to 0.8 million has little impact on detection stability.

Abstract

Convolutional Neutral Networks have been successfully applied in searching for strong lensing systems, leading to discoveries of new candidates from large surveys. On the other hand, systematic investigations about their robustness are still lacking. In this paper, we first construct a neutral network, and apply it to $r$-band images of Luminous Red Galaxies (LRGs) of the Kilo Degree Survey (KiDS) Data Release 3 to search for strong lensing systems. We build two sets of training samples, one fully from simulations, and the other one using the LRG stamps from KiDS observations as the foreground lens images. With the former training sample, we find 48 high probability candidates after human-inspection, and among them, 27 are newly identified. Using the latter training set, about 67\% of the aforementioned 48 candidates are also found, and there are 11 more new strong lensing candidates identified. We then carry out tests on the robustness of the network performance with respect to the variation of PSF. With the testing samples constructed using PSF in the range of 0.4 to 2 times of the median PSF of the training sample, we find that our network performs rather stable, and the degradation is small. We also investigate how the volume of the training set can affect our network performance by varying it from 0.1 millions to 0.8 millions. The output results are rather stable showing that within the considered range, our network performance is not very sensitive to the volume size.