Classification and Physical Characteristic Analysis of Fermi-GBM Gamma-Ray Bursts Based on Deep Learning
The classification of gamma-ray bursts (GRBs) has long been an unresolved problem. Early long- and short-burst classification based on duration is not convincing owing to the significant overlap in duration plot, which leads to different views on the classification results. We propose a new classifi...
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/ada0b0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832575850293231616 |
|---|---|
| author | Jia-Ming Chen Ke-Rui Zhu Zhao-Yang Peng Li Zhang |
| author_facet | Jia-Ming Chen Ke-Rui Zhu Zhao-Yang Peng Li Zhang |
| author_sort | Jia-Ming Chen |
| collection | DOAJ |
| description | The classification of gamma-ray bursts (GRBs) has long been an unresolved problem. Early long- and short-burst classification based on duration is not convincing owing to the significant overlap in duration plot, which leads to different views on the classification results. We propose a new classification method based on convolutional neural networks and adopt a sample including 3774 GRBs observed by Fermi-GBM to address the T _90 overlap problem. By using count maps that incorporate both temporal and spectral features as inputs, we successfully classify 593 overlapping events into two distinct categories, thereby refuting the existence of an intermediate GRB class. Additionally, we apply the optimal model to extract features from the count maps and visualize the extracted GRB features using the t-SNE algorithm, discovering two distinct clusters corresponding to S-type and L-type GRBs. To further investigate the physical properties of these two types of bursts, we conduct a time-integrated spectral analysis and discover significant differences in their spectral characteristics. The analysis also shows that most GRBs associated with kilonovae belong to the S type, while those associated with supernovae are predominantly L type, with few exceptions. Additionally, the duration characteristics of short bursts with extended emission suggest that they may manifest as either L-type or S-type GRBs. Compared to traditional classification methods (Amati and energy–hardness–duration methods), the new approach demonstrates significant advantages in classification accuracy and robustness without relying on redshift observations. The deep learning classification strategy proposed in this paper provides a more reliable tool for future GRB research. |
| format | Article |
| id | doaj-art-4165aa77b2f14a19984183abfaa9552f |
| 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-4165aa77b2f14a19984183abfaa9552f2025-01-31T16:54:16ZengIOP PublishingThe Astrophysical Journal Supplement Series0067-00492025-01-0127626210.3847/1538-4365/ada0b0Classification and Physical Characteristic Analysis of Fermi-GBM Gamma-Ray Bursts Based on Deep LearningJia-Ming Chen0https://orcid.org/0000-0001-5681-6939Ke-Rui Zhu1https://orcid.org/0000-0002-3132-1507Zhao-Yang Peng2https://orcid.org/0000-0003-3846-0988Li Zhang3https://orcid.org/0000-0002-7824-4289Department of Astronomy, School of Physics and Astronomy, Key Laboratory of Astroparticle Physics of Yunnan Province, Yunnan University , Kunming 650091, People’s Republic of ChinaDepartment of Astronomy, School of Physics and Astronomy, Key Laboratory of Astroparticle Physics of Yunnan Province, Yunnan University , Kunming 650091, People’s Republic of ChinaCollege of Physics and Electronics, Yunnan Normal University , Kunming 650500, People’s Republic of ChinaDepartment of Astronomy, School of Physics and Astronomy, Key Laboratory of Astroparticle Physics of Yunnan Province, Yunnan University , Kunming 650091, People’s Republic of ChinaThe classification of gamma-ray bursts (GRBs) has long been an unresolved problem. Early long- and short-burst classification based on duration is not convincing owing to the significant overlap in duration plot, which leads to different views on the classification results. We propose a new classification method based on convolutional neural networks and adopt a sample including 3774 GRBs observed by Fermi-GBM to address the T _90 overlap problem. By using count maps that incorporate both temporal and spectral features as inputs, we successfully classify 593 overlapping events into two distinct categories, thereby refuting the existence of an intermediate GRB class. Additionally, we apply the optimal model to extract features from the count maps and visualize the extracted GRB features using the t-SNE algorithm, discovering two distinct clusters corresponding to S-type and L-type GRBs. To further investigate the physical properties of these two types of bursts, we conduct a time-integrated spectral analysis and discover significant differences in their spectral characteristics. The analysis also shows that most GRBs associated with kilonovae belong to the S type, while those associated with supernovae are predominantly L type, with few exceptions. Additionally, the duration characteristics of short bursts with extended emission suggest that they may manifest as either L-type or S-type GRBs. Compared to traditional classification methods (Amati and energy–hardness–duration methods), the new approach demonstrates significant advantages in classification accuracy and robustness without relying on redshift observations. The deep learning classification strategy proposed in this paper provides a more reliable tool for future GRB research.https://doi.org/10.3847/1538-4365/ada0b0Gamma-ray burstsAstronomy data analysisConvolutional neural networks |
| spellingShingle | Jia-Ming Chen Ke-Rui Zhu Zhao-Yang Peng Li Zhang Classification and Physical Characteristic Analysis of Fermi-GBM Gamma-Ray Bursts Based on Deep Learning The Astrophysical Journal Supplement Series Gamma-ray bursts Astronomy data analysis Convolutional neural networks |
| title | Classification and Physical Characteristic Analysis of Fermi-GBM Gamma-Ray Bursts Based on Deep Learning |
| title_full | Classification and Physical Characteristic Analysis of Fermi-GBM Gamma-Ray Bursts Based on Deep Learning |
| title_fullStr | Classification and Physical Characteristic Analysis of Fermi-GBM Gamma-Ray Bursts Based on Deep Learning |
| title_full_unstemmed | Classification and Physical Characteristic Analysis of Fermi-GBM Gamma-Ray Bursts Based on Deep Learning |
| title_short | Classification and Physical Characteristic Analysis of Fermi-GBM Gamma-Ray Bursts Based on Deep Learning |
| title_sort | classification and physical characteristic analysis of fermi gbm gamma ray bursts based on deep learning |
| topic | Gamma-ray bursts Astronomy data analysis Convolutional neural networks |
| url | https://doi.org/10.3847/1538-4365/ada0b0 |
| work_keys_str_mv | AT jiamingchen classificationandphysicalcharacteristicanalysisoffermigbmgammarayburstsbasedondeeplearning AT keruizhu classificationandphysicalcharacteristicanalysisoffermigbmgammarayburstsbasedondeeplearning AT zhaoyangpeng classificationandphysicalcharacteristicanalysisoffermigbmgammarayburstsbasedondeeplearning AT lizhang classificationandphysicalcharacteristicanalysisoffermigbmgammarayburstsbasedondeeplearning |