Application of Machine Learning to Background Rejection in Very-high-energy Gamma-Ray Observation
Identifying gamma rays and rejecting the background of cosmic-ray hadrons are crucial for very-high-energy gamma-ray observations and relevant scientific research. Based on the simulated data from the square kilometer array (KM2A) of LHAASO, eight high-level features were extracted for the gamma/had...
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/ad9581 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841553624824545280 |
|---|---|
| author | Jie Li Hongkui Lv Yang Liu Jiajun Huang Yu Wang Wenbin Lin |
| author_facet | Jie Li Hongkui Lv Yang Liu Jiajun Huang Yu Wang Wenbin Lin |
| author_sort | Jie Li |
| collection | DOAJ |
| description | Identifying gamma rays and rejecting the background of cosmic-ray hadrons are crucial for very-high-energy gamma-ray observations and relevant scientific research. Based on the simulated data from the square kilometer array (KM2A) of LHAASO, eight high-level features were extracted for the gamma/hadron classification. Machine learning (ML) models, including logistic regression, support vector machines, decision trees, random forests, XGBoost, CatBoost, and deep neural networks (DNN) were constructed and trained using data sets of four energy bands ranging from 10 ^12 to 10 ^16 eV, and finally fused using the stacking ensemble algorithm. To comprehensively assess the classification ability of each model, the accuracy, F1 score, precision, recall, and area under the curve value of the receiver operating characteristic curve were used. The results show that the ML methods have a significant improvement on particle classification in LHAASO-KM2A, particularly in the low-energy range. Among these methods, XGBoost, CatBoost, and DNN demonstrate stronger classification capabilities than decision trees and random forests, while the fusion model exhibits the best discriminatory ability. The ML methods provide a useful and alternative method for gamma/hadron identification. The codes used in this paper are available at Zenodo at doi: http://dx.doi.org/10.5281/zenodo.13623261 . |
| format | Article |
| id | doaj-art-75a0d63c738f4a65bb52c1b5c7c76378 |
| 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-75a0d63c738f4a65bb52c1b5c7c763782025-01-09T06:48:40ZengIOP PublishingThe Astrophysical Journal Supplement Series0067-00492025-01-0127612410.3847/1538-4365/ad9581Application of Machine Learning to Background Rejection in Very-high-energy Gamma-Ray ObservationJie Li0Hongkui Lv1https://orcid.org/0000-0002-7779-3630Yang Liu2Jiajun Huang3Yu Wang4https://orcid.org/0000-0001-7959-3387Wenbin Lin5https://orcid.org/0000-0002-4282-066XSchool of Mathematics and Physics, University of South China , Hengyang 421001, People’s Republic of China ; lwb@usc.edu.cnKey Laboratory of Particle Astrophysics, Institute of High Energy Physics , Chinese Academy of Sciences, Beijing 100049, People’s Republic of China ; lvhk@ihep.ac.cn; TIANFU Cosmic Ray Research Center , Chengdu, Sichuan, People’s Republic of ChinaSchool of Computer Science, University of South China , Hengyang 421001, People’s Republic of ChinaKey Laboratory of Particle Astrophysics, Institute of High Energy Physics , Chinese Academy of Sciences, Beijing 100049, People’s Republic of China ; lvhk@ihep.ac.cn; University of Chinese Academy of Sciences , Beijing 10049, People’s Republic of ChinaICRA-Dip. di Fisica, University of Rome , P.le Aldo Moro, 5, Rome 00185, Italy ; yu.wang@icranet.org; INAF-Osservatorio Astronomico d’Abruzzo , Via M. Maggini snc, Teramo I-64100, Italy; International Center for Relativistic Astrophysics Network (ICRANet) , Pescara I-65122, ItalySchool of Mathematics and Physics, University of South China , Hengyang 421001, People’s Republic of China ; lwb@usc.edu.cn; School of Computer Science, University of South China , Hengyang 421001, People’s Republic of China; International Center for Relativistic Astrophysics Network (ICRANet) , Pescara I-65122, Italy; School of Physical Science and Technology, Southwest Jiaotong University , Chengdu 610031, People’s Republic of ChinaIdentifying gamma rays and rejecting the background of cosmic-ray hadrons are crucial for very-high-energy gamma-ray observations and relevant scientific research. Based on the simulated data from the square kilometer array (KM2A) of LHAASO, eight high-level features were extracted for the gamma/hadron classification. Machine learning (ML) models, including logistic regression, support vector machines, decision trees, random forests, XGBoost, CatBoost, and deep neural networks (DNN) were constructed and trained using data sets of four energy bands ranging from 10 ^12 to 10 ^16 eV, and finally fused using the stacking ensemble algorithm. To comprehensively assess the classification ability of each model, the accuracy, F1 score, precision, recall, and area under the curve value of the receiver operating characteristic curve were used. The results show that the ML methods have a significant improvement on particle classification in LHAASO-KM2A, particularly in the low-energy range. Among these methods, XGBoost, CatBoost, and DNN demonstrate stronger classification capabilities than decision trees and random forests, while the fusion model exhibits the best discriminatory ability. The ML methods provide a useful and alternative method for gamma/hadron identification. The codes used in this paper are available at Zenodo at doi: http://dx.doi.org/10.5281/zenodo.13623261 .https://doi.org/10.3847/1538-4365/ad9581High-energy cosmic radiationCosmic raysClassificationAstronomy data analysisInterdisciplinary astronomyAstronomy software |
| spellingShingle | Jie Li Hongkui Lv Yang Liu Jiajun Huang Yu Wang Wenbin Lin Application of Machine Learning to Background Rejection in Very-high-energy Gamma-Ray Observation The Astrophysical Journal Supplement Series High-energy cosmic radiation Cosmic rays Classification Astronomy data analysis Interdisciplinary astronomy Astronomy software |
| title | Application of Machine Learning to Background Rejection in Very-high-energy Gamma-Ray Observation |
| title_full | Application of Machine Learning to Background Rejection in Very-high-energy Gamma-Ray Observation |
| title_fullStr | Application of Machine Learning to Background Rejection in Very-high-energy Gamma-Ray Observation |
| title_full_unstemmed | Application of Machine Learning to Background Rejection in Very-high-energy Gamma-Ray Observation |
| title_short | Application of Machine Learning to Background Rejection in Very-high-energy Gamma-Ray Observation |
| title_sort | application of machine learning to background rejection in very high energy gamma ray observation |
| topic | High-energy cosmic radiation Cosmic rays Classification Astronomy data analysis Interdisciplinary astronomy Astronomy software |
| url | https://doi.org/10.3847/1538-4365/ad9581 |
| work_keys_str_mv | AT jieli applicationofmachinelearningtobackgroundrejectioninveryhighenergygammarayobservation AT hongkuilv applicationofmachinelearningtobackgroundrejectioninveryhighenergygammarayobservation AT yangliu applicationofmachinelearningtobackgroundrejectioninveryhighenergygammarayobservation AT jiajunhuang applicationofmachinelearningtobackgroundrejectioninveryhighenergygammarayobservation AT yuwang applicationofmachinelearningtobackgroundrejectioninveryhighenergygammarayobservation AT wenbinlin applicationofmachinelearningtobackgroundrejectioninveryhighenergygammarayobservation |