Using Convolutional Neural Networks to Search for Strongly Lensed Quasars in KiDS DR5

Abstract Gravitationally strongly lensed quasars (SL-QSO) offer invaluable insights into cosmological and astrophysical phenomena. With the data from ongoing and next-generation surveys, thousands of SL-QSO systems can be discovered expectedly, leading to unprecedented opportunities. However, the challenge lies in identifying SL-QSO from enormous data sets with high recall and purity in an automated and efficient manner. Hence, we developed a program based on a convolutional neural network (CNN) for finding SL-QSO from large-scale surveys and applied it to the Kilo-degree Survey Data Release 5. Our approach involves three key stages: first, we preselected 10 million bright objects (with r -band MAG_AUTO < 22), excluding stars from the data set; second, we established realistic training and test sets to train and fine-tune the CNN, resulting in the identification of 4195 machine candidates, and the false-positive rate of ∼1/2000 and recall of 0.8125 evaluated by using the real test set containing 16 confirmed lensed quasars; third, human inspections were performed for further selections, and then, 272 SL-QSO candidates were eventually found in total, including 16 high-score, 118 median-score, and 138 lower-score candidates, separately. Removing the systems already confirmed or identified in other papers, we end up with 229 SL-QSO candidates, including 7 high-score, 95 median-score, and 127 lower-score candidates, and the corresponding catalog is publicly available online ( https://github.com/EigenHermit/H24 ). We have also included an excellent quad candidate in the Appendix, discovered serendipitously during the fine-tuning process of the CNN.