Application of Deep-learning Methods for Distinguishing Gamma-Ray Bursts from Fermi/GBM Time-tagged Event Data
To investigate gamma-ray bursts (GRBs) in depth, it is crucial to develop an effective method for identifying GRBs accurately. Current criteria, e.g., onboard blind search, ground blind search, and target search, are limited by manually set thresholds and perhaps miss GRBs, especially for subthresho...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2024-01-01
|
| Series: | The Astrophysical Journal Supplement Series |
| Subjects: | |
| Online Access: | https://doi.org/10.3847/1538-4365/ad2de5 |
| _version_ | 1827276527010578432 |
|---|---|
| author | Peng Zhang Bing Li Renzhou Gui Shaolin Xiong Ze-Cheng Zou Xianggao Wang Xiaobo Li Ce Cai Yi Zhao Yanqiu Zhang Wangchen Xue Chao Zheng Hongyu Zhao |
| author_facet | Peng Zhang Bing Li Renzhou Gui Shaolin Xiong Ze-Cheng Zou Xianggao Wang Xiaobo Li Ce Cai Yi Zhao Yanqiu Zhang Wangchen Xue Chao Zheng Hongyu Zhao |
| author_sort | Peng Zhang |
| collection | DOAJ |
| description | To investigate gamma-ray bursts (GRBs) in depth, it is crucial to develop an effective method for identifying GRBs accurately. Current criteria, e.g., onboard blind search, ground blind search, and target search, are limited by manually set thresholds and perhaps miss GRBs, especially for subthreshold events. We proposed a novel approach that utilizes convolutional neural networks (CNNs) to distinguish GRBs and non-GRBs directly. We structured three CNN models, plain -CNN, ResNet, and ResNet-CBAM, and endeavored to exercise fusing strategy models. Count maps of NaI detectors on board Fermi/Gamma-ray Burst Monitor were employed, as the input samples of data sets and models were implemented to evaluate their performance on different timescale data. The ResNet-CBAM model trained on the 64 ms data set achieves high accuracy overall, which includes residual and attention mechanism modules. The visualization methods of Grad-CAM and t-SNE explicitly displayed that the optimal model focuses on the key features of GRBs precisely. The model was applied to analyze 1 yr data, accurately identifying approximately 98% of GRBs listed in the Fermi burst catalog, eight out of nine subthreshold GRBs, and five GRBs triggered by other satellites, which demonstrated that the deep-learning methods could effectively distinguish GRBs from observational data. Besides, thousands of unknown candidates were retrieved and compared with the bursts of SGR J1935+2154, for instance, which exemplified the potential scientific value of these candidates indeed. Detailed studies on integrating our model into real-time analysis pipelines thus may improve their accuracy of inspection and provide valuable guidance for rapid follow-up observations of multiband telescopes. |
| first_indexed | 2024-04-24T06:55:46Z |
| format | Article |
| id | doaj.art-b9119e6d4dcd4876b998b659d92b676b |
| institution | Directory Open Access Journal |
| issn | 0067-0049 |
| language | English |
| last_indexed | 2024-04-24T06:55:46Z |
| publishDate | 2024-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | The Astrophysical Journal Supplement Series |
| spelling | doaj.art-b9119e6d4dcd4876b998b659d92b676b2024-04-22T12:39:25ZengIOP PublishingThe Astrophysical Journal Supplement Series0067-00492024-01-012721410.3847/1538-4365/ad2de5Application of Deep-learning Methods for Distinguishing Gamma-Ray Bursts from Fermi/GBM Time-tagged Event DataPeng Zhang0https://orcid.org/0000-0002-8097-3616Bing Li1https://orcid.org/0000-0002-0238-834XRenzhou Gui2Shaolin Xiong3https://orcid.org/0000-0002-4771-7653Ze-Cheng Zou4https://orcid.org/0000-0002-6189-8307Xianggao Wang5https://orcid.org/0000-0001-8411-8011Xiaobo Li6https://orcid.org/0000-0003-4585-589XCe Cai7https://orcid.org/0000-0002-6540-2372Yi Zhao8https://orcid.org/0000-0002-4636-0293Yanqiu Zhang9https://orcid.org/0000-0001-5348-7033Wangchen Xue10Chao Zheng11Hongyu Zhao12College of Electronic and Information Engineering, Tongji University , Shanghai 201804, People's Republic of China ; rzgui@tongji.edu.cn; Key Laboratory of Particle Astrophysics, Chinese Academy of Sciences , Beijing 100049, People's Republic of China ; libing@ihep.ac.cnKey Laboratory of Particle Astrophysics, Chinese Academy of Sciences , Beijing 100049, People's Republic of China ; libing@ihep.ac.cn; School of Astronomy and Space Science, Nanjing University , Nanjing 210023, People's Republic of China; Guangxi Key Laboratory for Relativistic Astrophysics , Nanning 530004, People's Republic of ChinaCollege of Electronic and Information Engineering, Tongji University , Shanghai 201804, People's Republic of China ; rzgui@tongji.edu.cnKey Laboratory of Particle Astrophysics, Chinese Academy of Sciences , Beijing 100049, People's Republic of China ; libing@ihep.ac.cnSchool of Astronomy and Space Science, Nanjing University , Nanjing 210023, People's Republic of ChinaGuangxi Key Laboratory for Relativistic Astrophysics , Nanning 530004, People's Republic of ChinaKey Laboratory of Particle Astrophysics, Chinese Academy of Sciences , Beijing 100049, People's Republic of China ; libing@ihep.ac.cnCollege of Physics and Hebei Key Laboratory of Photophysics Research and Application, Hebei Normal University , Shijiazhuang, Hebei 050024, People's Republic of ChinaSchool of Computer and Information, Dezhou University , Dezhou 253023, People's Republic of ChinaKey Laboratory of Particle Astrophysics, Chinese Academy of Sciences , Beijing 100049, People's Republic of China ; libing@ihep.ac.cnKey Laboratory of Particle Astrophysics, Chinese Academy of Sciences , Beijing 100049, People's Republic of China ; libing@ihep.ac.cnKey Laboratory of Particle Astrophysics, Chinese Academy of Sciences , Beijing 100049, People's Republic of China ; libing@ihep.ac.cnSchool of Computing and Artificial Intelligence, Southwest Jiaotong University , Chengdu 611756, People's Republic of ChinaTo investigate gamma-ray bursts (GRBs) in depth, it is crucial to develop an effective method for identifying GRBs accurately. Current criteria, e.g., onboard blind search, ground blind search, and target search, are limited by manually set thresholds and perhaps miss GRBs, especially for subthreshold events. We proposed a novel approach that utilizes convolutional neural networks (CNNs) to distinguish GRBs and non-GRBs directly. We structured three CNN models, plain -CNN, ResNet, and ResNet-CBAM, and endeavored to exercise fusing strategy models. Count maps of NaI detectors on board Fermi/Gamma-ray Burst Monitor were employed, as the input samples of data sets and models were implemented to evaluate their performance on different timescale data. The ResNet-CBAM model trained on the 64 ms data set achieves high accuracy overall, which includes residual and attention mechanism modules. The visualization methods of Grad-CAM and t-SNE explicitly displayed that the optimal model focuses on the key features of GRBs precisely. The model was applied to analyze 1 yr data, accurately identifying approximately 98% of GRBs listed in the Fermi burst catalog, eight out of nine subthreshold GRBs, and five GRBs triggered by other satellites, which demonstrated that the deep-learning methods could effectively distinguish GRBs from observational data. Besides, thousands of unknown candidates were retrieved and compared with the bursts of SGR J1935+2154, for instance, which exemplified the potential scientific value of these candidates indeed. Detailed studies on integrating our model into real-time analysis pipelines thus may improve their accuracy of inspection and provide valuable guidance for rapid follow-up observations of multiband telescopes.https://doi.org/10.3847/1538-4365/ad2de5Gamma-ray burstsConvolutional neural networksAstronomy data analysisHigh energy astrophysicsGamma-ray astronomyDimensionality reduction |
| spellingShingle | Peng Zhang Bing Li Renzhou Gui Shaolin Xiong Ze-Cheng Zou Xianggao Wang Xiaobo Li Ce Cai Yi Zhao Yanqiu Zhang Wangchen Xue Chao Zheng Hongyu Zhao Application of Deep-learning Methods for Distinguishing Gamma-Ray Bursts from Fermi/GBM Time-tagged Event Data The Astrophysical Journal Supplement Series Gamma-ray bursts Convolutional neural networks Astronomy data analysis High energy astrophysics Gamma-ray astronomy Dimensionality reduction |
| title | Application of Deep-learning Methods for Distinguishing Gamma-Ray Bursts from Fermi/GBM Time-tagged Event Data |
| title_full | Application of Deep-learning Methods for Distinguishing Gamma-Ray Bursts from Fermi/GBM Time-tagged Event Data |
| title_fullStr | Application of Deep-learning Methods for Distinguishing Gamma-Ray Bursts from Fermi/GBM Time-tagged Event Data |
| title_full_unstemmed | Application of Deep-learning Methods for Distinguishing Gamma-Ray Bursts from Fermi/GBM Time-tagged Event Data |
| title_short | Application of Deep-learning Methods for Distinguishing Gamma-Ray Bursts from Fermi/GBM Time-tagged Event Data |
| title_sort | application of deep learning methods for distinguishing gamma ray bursts from fermi gbm time tagged event data |
| topic | Gamma-ray bursts Convolutional neural networks Astronomy data analysis High energy astrophysics Gamma-ray astronomy Dimensionality reduction |
| url | https://doi.org/10.3847/1538-4365/ad2de5 |
| work_keys_str_mv | AT pengzhang applicationofdeeplearningmethodsfordistinguishinggammarayburstsfromfermigbmtimetaggedeventdata AT bingli applicationofdeeplearningmethodsfordistinguishinggammarayburstsfromfermigbmtimetaggedeventdata AT renzhougui applicationofdeeplearningmethodsfordistinguishinggammarayburstsfromfermigbmtimetaggedeventdata AT shaolinxiong applicationofdeeplearningmethodsfordistinguishinggammarayburstsfromfermigbmtimetaggedeventdata AT zechengzou applicationofdeeplearningmethodsfordistinguishinggammarayburstsfromfermigbmtimetaggedeventdata AT xianggaowang applicationofdeeplearningmethodsfordistinguishinggammarayburstsfromfermigbmtimetaggedeventdata AT xiaoboli applicationofdeeplearningmethodsfordistinguishinggammarayburstsfromfermigbmtimetaggedeventdata AT cecai applicationofdeeplearningmethodsfordistinguishinggammarayburstsfromfermigbmtimetaggedeventdata AT yizhao applicationofdeeplearningmethodsfordistinguishinggammarayburstsfromfermigbmtimetaggedeventdata AT yanqiuzhang applicationofdeeplearningmethodsfordistinguishinggammarayburstsfromfermigbmtimetaggedeventdata AT wangchenxue applicationofdeeplearningmethodsfordistinguishinggammarayburstsfromfermigbmtimetaggedeventdata AT chaozheng applicationofdeeplearningmethodsfordistinguishinggammarayburstsfromfermigbmtimetaggedeventdata AT hongyuzhao applicationofdeeplearningmethodsfordistinguishinggammarayburstsfromfermigbmtimetaggedeventdata |