YOLOX-LS: Strong Gravitational Lenses Detection in the DECaLS with Deep Learning
The identification of strong gravitational lenses is essential to facilitate many studies in astronomy. The search for strong gravitational lenses has become more challenging because of their scientific value and their rarity. In this paper, we construct a data set for strong gravitational lensing s...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2025-01-01
|
| Series: | The Astrophysical Journal |
| Subjects: | |
| Online Access: | https://doi.org/10.3847/1538-4357/ad97ba |
| _version_ | 1826895415127048192 |
|---|---|
| author | Yangyang Liu Liangping Tu Jianxi Li Jiawei Miao Gengqi Lin Chenying Zhao |
| author_facet | Yangyang Liu Liangping Tu Jianxi Li Jiawei Miao Gengqi Lin Chenying Zhao |
| author_sort | Yangyang Liu |
| collection | DOAJ |
| description | The identification of strong gravitational lenses is essential to facilitate many studies in astronomy. The search for strong gravitational lenses has become more challenging because of their scientific value and their rarity. In this paper, we construct a data set for strong gravitational lensing searches that consist of known lenses and lens candidates from the Dark Energy Spectroscopic Instrument Legacy Imaging Surveys (the DESI Legacy Imaging Surveys) and the Dark Energy Survey (DES) and non-lenses from the Legacy Surveys Data Release 9 (DR9). We apply the YOLOX algorithm as the basic framework and improve it by selecting the optimal optimizer, activation function, attention mechanism, and loss function. The improved YOLOX-LS algorithm achieves 97.87%, 97.51%, 0.97, 96.8%, and 53.1% in the evaluation metrics of precision, recall, F1 score, mean average precision (mAP)@0.5, and mAP@0.5:0.95, respectively. Compared with the YOLOX model, it improves by 0.63%, 0.26%, and 0.6% in the three metrics of precision, recall, and mAP@0.5, respectively. This paper presents the results of the trained YOLOX-LS algorithm applied to 4.75 million cutout images. These images are centered on the central source with mag _z ≤ 20 in the Dark Energy Camera Legacy Survey footprint from DESI DR9. Finally, we find 1697 lenses, including 303 known lenses or candidates, and 1394 new candidates, among which there are 102 high-quality candidates. This further verifies that the YOLOX-LS algorithm proposed in this paper can be effectively applied to the search for strong gravitational lenses. All visual results are displayed online at https://github.com/Young-mmm/YOLOX-LS . |
| first_indexed | 2025-02-17T05:35:26Z |
| format | Article |
| id | doaj.art-0f730fb93ae04c84bcc2cd98ea52c704 |
| institution | Directory Open Access Journal |
| issn | 1538-4357 |
| language | English |
| last_indexed | 2025-02-17T05:35:26Z |
| publishDate | 2025-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | The Astrophysical Journal |
| spelling | doaj.art-0f730fb93ae04c84bcc2cd98ea52c7042025-01-08T07:04:25ZengIOP PublishingThe Astrophysical Journal1538-43572025-01-01978215110.3847/1538-4357/ad97baYOLOX-LS: Strong Gravitational Lenses Detection in the DECaLS with Deep LearningYangyang Liu0https://orcid.org/0009-0004-4462-5464Liangping Tu1https://orcid.org/0000-0002-2439-0766Jianxi Li2https://orcid.org/0000-0001-7034-9062Jiawei Miao3https://orcid.org/0000-0002-8135-6222Gengqi Lin4https://orcid.org/0009-0007-8362-217XChenying Zhao5https://orcid.org/0009-0003-6178-5745School of Electronic and Information Engineering, University of Science and Technology Liaoning , Anshan, 114044, People’s Republic of China ; tuliangping@ustl.edu.cnSchool of Electronic and Information Engineering, University of Science and Technology Liaoning , Anshan, 114044, People’s Republic of China ; tuliangping@ustl.edu.cn; School of Mathematics and Statistics, Minnan Normal University , Zhangzhou, 363000, People’s Republic of ChinaSchool of Mathematics and Statistics, Minnan Normal University , Zhangzhou, 363000, People’s Republic of ChinaSchool of Electronic and Information Engineering, University of Science and Technology Liaoning , Anshan, 114044, People’s Republic of China ; tuliangping@ustl.edu.cnSchool of Electronic and Information Engineering, University of Science and Technology Liaoning , Anshan, 114044, People’s Republic of China ; tuliangping@ustl.edu.cnSchool of Electronic and Information Engineering, University of Science and Technology Liaoning , Anshan, 114044, People’s Republic of China ; tuliangping@ustl.edu.cnThe identification of strong gravitational lenses is essential to facilitate many studies in astronomy. The search for strong gravitational lenses has become more challenging because of their scientific value and their rarity. In this paper, we construct a data set for strong gravitational lensing searches that consist of known lenses and lens candidates from the Dark Energy Spectroscopic Instrument Legacy Imaging Surveys (the DESI Legacy Imaging Surveys) and the Dark Energy Survey (DES) and non-lenses from the Legacy Surveys Data Release 9 (DR9). We apply the YOLOX algorithm as the basic framework and improve it by selecting the optimal optimizer, activation function, attention mechanism, and loss function. The improved YOLOX-LS algorithm achieves 97.87%, 97.51%, 0.97, 96.8%, and 53.1% in the evaluation metrics of precision, recall, F1 score, mean average precision (mAP)@0.5, and mAP@0.5:0.95, respectively. Compared with the YOLOX model, it improves by 0.63%, 0.26%, and 0.6% in the three metrics of precision, recall, and mAP@0.5, respectively. This paper presents the results of the trained YOLOX-LS algorithm applied to 4.75 million cutout images. These images are centered on the central source with mag _z ≤ 20 in the Dark Energy Camera Legacy Survey footprint from DESI DR9. Finally, we find 1697 lenses, including 303 known lenses or candidates, and 1394 new candidates, among which there are 102 high-quality candidates. This further verifies that the YOLOX-LS algorithm proposed in this paper can be effectively applied to the search for strong gravitational lenses. All visual results are displayed online at https://github.com/Young-mmm/YOLOX-LS .https://doi.org/10.3847/1538-4357/ad97baStrong gravitational lensingConvolutional neural networks |
| spellingShingle | Yangyang Liu Liangping Tu Jianxi Li Jiawei Miao Gengqi Lin Chenying Zhao YOLOX-LS: Strong Gravitational Lenses Detection in the DECaLS with Deep Learning The Astrophysical Journal Strong gravitational lensing Convolutional neural networks |
| title | YOLOX-LS: Strong Gravitational Lenses Detection in the DECaLS with Deep Learning |
| title_full | YOLOX-LS: Strong Gravitational Lenses Detection in the DECaLS with Deep Learning |
| title_fullStr | YOLOX-LS: Strong Gravitational Lenses Detection in the DECaLS with Deep Learning |
| title_full_unstemmed | YOLOX-LS: Strong Gravitational Lenses Detection in the DECaLS with Deep Learning |
| title_short | YOLOX-LS: Strong Gravitational Lenses Detection in the DECaLS with Deep Learning |
| title_sort | yolox ls strong gravitational lenses detection in the decals with deep learning |
| topic | Strong gravitational lensing Convolutional neural networks |
| url | https://doi.org/10.3847/1538-4357/ad97ba |
| work_keys_str_mv | AT yangyangliu yoloxlsstronggravitationallensesdetectioninthedecalswithdeeplearning AT liangpingtu yoloxlsstronggravitationallensesdetectioninthedecalswithdeeplearning AT jianxili yoloxlsstronggravitationallensesdetectioninthedecalswithdeeplearning AT jiaweimiao yoloxlsstronggravitationallensesdetectioninthedecalswithdeeplearning AT gengqilin yoloxlsstronggravitationallensesdetectioninthedecalswithdeeplearning AT chenyingzhao yoloxlsstronggravitationallensesdetectioninthedecalswithdeeplearning |