Astronomical Image Superresolution Reconstruction with Deep Learning for Better Identification of Interacting Galaxies
Galaxy–galaxy mergers are crucial in galaxy evolution, but the tidal features around galaxies are often faint, making it difficult to identify interacting or merging galaxies. High-resolution images of galaxies can identify fine structures within galaxies, which are essential for identifying and dis...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2025-01-01
|
| Series: | The Astrophysical Journal Supplement Series |
| Subjects: | |
| Online Access: | https://doi.org/10.3847/1538-4365/adca34 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849468092526100480 |
|---|---|
| author | Jiawei Miao Liangping Tu Hao Liu Jian Zhao |
| author_facet | Jiawei Miao Liangping Tu Hao Liu Jian Zhao |
| author_sort | Jiawei Miao |
| collection | DOAJ |
| description | Galaxy–galaxy mergers are crucial in galaxy evolution, but the tidal features around galaxies are often faint, making it difficult to identify interacting or merging galaxies. High-resolution images of galaxies can identify fine structures within galaxies, which are essential for identifying and distinguishing different substructures within merging systems. However, due to observational and instrumental limitations, galaxy data is often collected at low resolution. To further improve visual quality and enhance the details of galaxy structures, we propose a dual-branch network structure combining convolutional neural networks (CNNs) and Transformer (DBCTNet), which leverages the local characteristics of CNNs to complement the global features of Transformer. We select four representative models for comparative experiments: Real-ESRGAN, SwinIR, Hybrid Attention Transformer, and EDAT. In the experiment, we adopt a two-stage training strategy. The results from the first stage show that DBCTNet improves the peak signal-to-noise ratio by 0.13, 0.19, 0.12, and 0.11, respectively, and achieves the highest structural similarity index value of 0.5578. In the second stage, we use DBCTNet, trained in the first stage as the generator, to train the galaxy image superresolution reconstruction model based on generative adversarial networks, DBCTGAN, which aims to enhance the visual quality of the reconstructed images. In addition, we use superresolution methods as a preprocessing step in the task of interacting galaxy classification. Experimental results show that using DBCTGAN for preprocessing improves classification performance compared to other models, which further verifies its effectiveness in enhancing the quality of low-resolution images. |
| format | Article |
| id | doaj-art-3389c4d7eff24953bc403e77ac51ed67 |
| institution | Kabale University |
| issn | 0067-0049 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | The Astrophysical Journal Supplement Series |
| spelling | doaj-art-3389c4d7eff24953bc403e77ac51ed672025-08-20T03:25:57ZengIOP PublishingThe Astrophysical Journal Supplement Series0067-00492025-01-0127823510.3847/1538-4365/adca34Astronomical Image Superresolution Reconstruction with Deep Learning for Better Identification of Interacting GalaxiesJiawei Miao0https://orcid.org/0000-0002-8135-6222Liangping Tu1https://orcid.org/0000-0002-2439-0766Hao Liu2https://orcid.org/0000-0002-8205-9211Jian Zhao3https://orcid.org/0000-0002-8330-7205School of Electronic and Information Engineering, University of Science and Technology Liaoning , Anshan, 114044, People’s Republic of China ; jwmiao@ustl.edu.cn, tuliangping@ustl.edu.cnSchool of Electronic and Information Engineering, University of Science and Technology Liaoning , Anshan, 114044, People’s Republic of China ; jwmiao@ustl.edu.cn, tuliangping@ustl.edu.cn; School of Mathematics and Statistics, Minnan Normal University , Zhangzhou, 363000, People’s Republic of ChinaSchool of Science, University of Science and Technology Liaoning , Anshan, 114044, People’s Republic of China ; haoliu@ustl.edu.cn, zhao@ustl.edu.cnSchool of Science, University of Science and Technology Liaoning , Anshan, 114044, People’s Republic of China ; haoliu@ustl.edu.cn, zhao@ustl.edu.cnGalaxy–galaxy mergers are crucial in galaxy evolution, but the tidal features around galaxies are often faint, making it difficult to identify interacting or merging galaxies. High-resolution images of galaxies can identify fine structures within galaxies, which are essential for identifying and distinguishing different substructures within merging systems. However, due to observational and instrumental limitations, galaxy data is often collected at low resolution. To further improve visual quality and enhance the details of galaxy structures, we propose a dual-branch network structure combining convolutional neural networks (CNNs) and Transformer (DBCTNet), which leverages the local characteristics of CNNs to complement the global features of Transformer. We select four representative models for comparative experiments: Real-ESRGAN, SwinIR, Hybrid Attention Transformer, and EDAT. In the experiment, we adopt a two-stage training strategy. The results from the first stage show that DBCTNet improves the peak signal-to-noise ratio by 0.13, 0.19, 0.12, and 0.11, respectively, and achieves the highest structural similarity index value of 0.5578. In the second stage, we use DBCTNet, trained in the first stage as the generator, to train the galaxy image superresolution reconstruction model based on generative adversarial networks, DBCTGAN, which aims to enhance the visual quality of the reconstructed images. In addition, we use superresolution methods as a preprocessing step in the task of interacting galaxy classification. Experimental results show that using DBCTGAN for preprocessing improves classification performance compared to other models, which further verifies its effectiveness in enhancing the quality of low-resolution images.https://doi.org/10.3847/1538-4365/adca34GalaxiesGalaxy mergersInteracting galaxiesConvolutional neural networksGalaxy classification systemsGround-based astronomy |
| spellingShingle | Jiawei Miao Liangping Tu Hao Liu Jian Zhao Astronomical Image Superresolution Reconstruction with Deep Learning for Better Identification of Interacting Galaxies The Astrophysical Journal Supplement Series Galaxies Galaxy mergers Interacting galaxies Convolutional neural networks Galaxy classification systems Ground-based astronomy |
| title | Astronomical Image Superresolution Reconstruction with Deep Learning for Better Identification of Interacting Galaxies |
| title_full | Astronomical Image Superresolution Reconstruction with Deep Learning for Better Identification of Interacting Galaxies |
| title_fullStr | Astronomical Image Superresolution Reconstruction with Deep Learning for Better Identification of Interacting Galaxies |
| title_full_unstemmed | Astronomical Image Superresolution Reconstruction with Deep Learning for Better Identification of Interacting Galaxies |
| title_short | Astronomical Image Superresolution Reconstruction with Deep Learning for Better Identification of Interacting Galaxies |
| title_sort | astronomical image superresolution reconstruction with deep learning for better identification of interacting galaxies |
| topic | Galaxies Galaxy mergers Interacting galaxies Convolutional neural networks Galaxy classification systems Ground-based astronomy |
| url | https://doi.org/10.3847/1538-4365/adca34 |
| work_keys_str_mv | AT jiaweimiao astronomicalimagesuperresolutionreconstructionwithdeeplearningforbetteridentificationofinteractinggalaxies AT liangpingtu astronomicalimagesuperresolutionreconstructionwithdeeplearningforbetteridentificationofinteractinggalaxies AT haoliu astronomicalimagesuperresolutionreconstructionwithdeeplearningforbetteridentificationofinteractinggalaxies AT jianzhao astronomicalimagesuperresolutionreconstructionwithdeeplearningforbetteridentificationofinteractinggalaxies |