Application of AI technology in pulsar candidate identification

Wanqiong Wang; Jie Wang; Xinchen Ye; Yazhou Zhang; Jia Li; Xu Du; Wenna Cai; Han Wu; Ting Zhang; Yuyue Jiao

doi:10.61977/ati2024050

Astronomical Techniques and Instruments > 2025 > 2(1): 27-43. > DOI: 10.61977/ati2024050 CSTR: 32083.14.ati2024050

Wang, W. Q., Wang, J., Ye, X. C., et al. 2025. Application of AI technology in pulsar candidate identification. Astronomical Techniques and Instruments, 2(1): 27−43. https://doi.org/10.61977/ati2024050.

Citation:

PDF (4808 KB)

Application of AI technology in pulsar candidate identification

Wanqiong Wang¹,
Jie Wang^{1, 2, 3, , ,},
Xinchen Ye^{1, 3,},
Yazhou Zhang^1,,
Jia Li¹,
Xu Du^{1, 2,},
Wenna Cai^{1, 2},
Han Wu^{1, 2},
Ting Zhang^{1, 2},
Yuyue Jiao^{1, 2,}

1.
Xinjiang Astronomical Observatory, Chinese Academy of Sciences, Urumqi 830011, China
2.
University of Chinese Academy of Sciences, Beijing 100049, China
3.
National Astronomical Data Center, Beijing 100101, China

More Information

Corresponding author:
Jie Wang, wangjie@xao.ac.cn
Received Date: September 09, 2024
Accepted Date: October 25, 2024
Available Online: November 17, 2024
Published Date: November 15, 2024
© 2025 Editorial Office of Astronomical Techniques and Instruments, Yunnan Observatories, Chinese Academy of Sciences.
This is an open access article under the CC BY 4.0 license (http:/creativecommons.org/licenses/by/4.0/)

Graphical Abstract

Abstract

Abstract

As artificial intelligence (AI) technology has continued to develop, its efficient data processing and pattern recognition capabilities have significantly improved the precision and speed of decision-making processes, and it has been widely applied across various fields. In the field of astronomy, AI techniques have demonstrated unique advantages, particularly in the identification of pulsars and their candidates. AI is able to address the challenges of pulsar celestial body identification and classification because of its accuracy and efficiency. This paper systematically surveys commonly used AI models for pulsar candidate identification, analyzing and discussing the typical applications of machine learning, artificial neural networks, convolutional neural networks, and generative adversarial networks in candidate identification. Furthermore, it explores how the introduction of AI techniques not only enhances the efficiency and accuracy of pulsar identification but also provides new perspectives and tools for pulsar survey data processing, thus playing a significant role in advancing pulsar research and the field of astronomy.
- AI technology,
- Candidate identification,
- Machine learning,
- Neural networks

FullText(HTML)

ACKNOWLEDGEMENTS

This work is supported by the National Key R&D Program of China (2021YFC2203502 and 2022YFF0711502); the National Natural Science Foundation of China (NSFC) (12173077); the Tianshan Talent Project of Xinjiang Uygur Autonomous Region (2022TSYCCX0095 and 2023TSYCCX0112); the Scientific Instrument Developing Project of the Chinese Academy of Sciences (PTYQ2022YZZD01); China National Astronomical Data Center (NADC); the Operation, Maintenance and Upgrading Fund for Astronomical Telescopes and Facility Instruments, budgeted from the Ministry of Finance of China (MOF) and administrated by the Chinese Academy of Sciences (CAS); Natural Science Foundation of Xinjiang Uygur Autonomous Region (2022D01A360).

AUTHOR CONTRIBUTIONS

Wanqiong Wang conceived the idea, provided investigation support, wrote original draft and edited the manuscript. Jie Wang reviewed the manuscript, and performed the project administration and supervision roles. Xinchen Ye and Yazhou Zhang reviewed the manuscript and performed supervision. Jia Li, Xu Du, Wenna Cai, Han Wu, Ting Zhang, Yuyue Jiao provided investigation support. All authors read and approved the final manuscript.

DECLARATION OF INTERESTS

The authors declare no competing interests.

References (70)

References

[1]	Zhang, H. Y., Zhao, Z., An, T., et al. 2019. Pulsar candidate recognition with deep learning. Computers & Electrical Engineering, 73: 1−8. doi: 10.1016/j.compeleceng.2018.10.016
[2]	Haykin, S. 2008. Neural networks: A comprehensive foundation (3rd Edition). London: Pearson.
[3]	Lou, G. X., Shi, H. Z. 2020. Face image recognition based on convolutional neural network. China Communications, 17(2): 117−124. doi: 10.23919/JCC.2020.02.010
[4]	Zeng, Q. 2024. Research on image recognition method based on generated adversarial networks. Master thesis, Changsha University of Science and Technology. (in Chinese)
[5]	Lin, Y. R., Ma, S. P. 1989. An introduction to artificial intelligence. Beijing: Tsinghua University Press. (in Chinese)
[6]	Haindavi, P., Kumar, S., Ganesh, G., et al. 2024. Discovery of astronomical objects in galaxies by means of deep learning. MATEC Web of Conferences, 392: 01123. doi: 10.1051/matecconf/202439201123
[7]	Singh, K. K., Dhar, V. K., Meintjes, P. J. 2022. Artificial neural networks for cosmic gamma-ray propagation in the universe. New Astronomy, 91: 101701. doi: 10.1016/j.newast.2021.101701
[8]	García-Jara, G., Protopapas, P., Estévez, P. A. 2022. Improving astronomical time-series classification via data augmentation with generative adversarial networks. The Astrophysical Journal, 935(1): 23. doi: 10.3847/1538-4357/ac6f5a
[9]	Zhou, Z. H. 2016. Machine learning. Beijing: Tsinghua University Press.
[10]	Cunningham, P., Cord, M., Delany, S. J. 2008. Supervised learning. In Machine learning techniques for multimedia. Springer, 21−49.
[11]	Neter, J., Wassermann, W., Kutner, M. 1974. Applied linear statistical models: Regression, analysis of variance, and experimental designs. Boca Raton: CRC Press.
[12]	Kleinbaum, D. G., Klein, M. 2002. Logistic regression (A self-learning text). Berlin: Springer.
[13]	Cristianint, N., Shawe-Taylor, J. 2000. An introduction to support vector machines and other kernel-based learning methods. Cambridge: Cambridge University Press.
[14]	Hastie, T., Tibshirani, R., Friedman, J., 2008. The elements of statistical learning: data mining, inference, and prediction. Berlin: Springer.
[15]	Breiman, L. 2001. Random forests. Machine Learning, 45: 5−32. doi: 10.1023/A:1010933404324
[16]	Olaode, A., Naghdy, G., Todd, C. 2014. Unsupervised classification of images: a review. International Journal of Image Processing, 8(5): 325−342.
[17]	Jain, A. K. 2010. Data clustering: 50 years beyond K-means. Pattern Recognition Letters, 31(8): 651−666. doi: 10.1016/j.patrec.2009.09.011
[18]	Kaufman, L., Rousseeuw, P. J. 2005. Finding groups in data: An introduction to cluster analysis. New York: Wiley.
[19]	Hady, M. F. A., Schwenker, F. 2013. Semi-supervised learning. In Handbook on Neural Information Processing, Springer Nature Link, 215−239.
[20]	LeCun, Y., Bengio, Y., Hinton, G. 2015. Deep learning. Nature, 521: 436−444. doi: 10.1038/nature14539
[21]	Janiesch, C., Zschech, P., Heinrich, K. 2021. Machine learning and deep learning. Electronic Markets, 31(3): 685−695. doi: 10.1007/s12525-021-00475-2
[22]	Kanwisher, N., Khosla, M., Dobs, K. 2023. Using artificial neural networks to ask 'why' questions of minds and brains. Trends in Neurosciences, 46(3): 240−254. doi: 10.1016/j.tins.2022.12.008
[23]	Smith, M. J., Geach, J. E. 2023. Astronomia ex machina: a history, primer and outlook on neural networks in astronomy. Royal Society Open Science, 10(5): 221454. doi: 10.1098/rsos.221454
[24]	Wang, Z. H., Ye, Y., Liu, H. Y., et al. 2024. Spatio-temporal back-propagation algorithm for deep pulse neural network based on pulse sequence identity. Journal of Electronics & Information Technology, 46(6): 2596−2604. (in Chinese) doi: 10.11999/JEIT230705
[25]	Chen Yuncai. 2024. Research on natural language processing technology based on artificial neural network. Engineering and Technological Research, 9(8): 93−95. (in Chinese) doi: 10.19537/j.cnki.2096-2789.2024.08.030
[26]	Zhou, F. Y., Jin, L. P., Dong, J . 2017. Review of convolutional neural network. Chinese Journal of Computer Science, 40(6): 1229−1251. (in Chinese)
[27]	Chang, L., Demg. X. M., Zhou, M. Q., et al . 2016. Convolutional neural network in image understanding. Acta Automatica Sinica, 42(9): 1300−1312. (in Chinese) doi: 10.16383/j.aas.2016.c150800
[28]	Lecun, Y., Bottou, L. 1998. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11): 2278−2324. doi: 10.1109/5.726791
[29]	Wang, W., Zhang, H. M. 2024. High-similarity image recognition method based on a convolutional neural network. Journal of Heilongjiang University of Technology (Comprehensive edition), 24(3): 80−84. (in Chinese) doi: 10.16792/j.cnki.1672-6758.2024.03.002
[30]	Luo, F. G., Song, Q., Qin, Y. C., et al. 2024. Research on the application of convolutional neural network in image rrecognition. Computer and Information Technology, 32(3): 51−54. (in Chinese) doi: 10.19414/j.cnki.1005-1228.2024.03.032
[31]	Wang, J. Y., Yang, H. T., Li, G. Y., et al. 2021. Progress in the application of generating adversarial networks and their image processing. Computer Engineering and Application, 57(8): 10. (in Chinese) doi: 10.3778/j.issn.1002-8331.2011-0322
[32]	Zhang, H. L., Wang, J., Zhang, Y. Z., et al. 2024. Review of artificial intelligence applications inastronomical data processing. Astronomical Techniques and Instruments, 1(1): 1−15. doi: 10.61977/ati2024001
[33]	Zhang, C. J., Shang, Z. H., Chen, W. M., et al. 2020. A review of research on pulsar candidate recognition based on machine learning. Procedia Computer Science, 166: 534−538. doi: 10.1016/j.procs.2020.02.050
[34]	Nan, R. D. 2006. Five hundred meter aperture spherical radio telescope (FAST). Science China (Physics, Mechanics & Astronomy), 49(2): 129−148. doi: 10.1007/s11433-006-0129-9
[35]	Nan, R. D., Li, D. 2013. The five-hundred-meter aperture spherical radio telescope (FAST) project. In Proceedings of IOP Conference Series: Materials Science and Engineering.
[36]	Nan, R. D., Wang, Q. M., Zhu, L. C., et al. 2006. Pulsar observations with radio telescope FAST. Chinese Journal of Astronomy and Astrophysics, 6(Suppl 2): 304. doi: 10.1088/1009-9271/6/S2/57
[37]	Xu, Y., Li, D., Liu, Z. J., etc. 2017. Application of artificial intelligence in the screening of pulsar candidates. Progress in Astronomy, 35(3): 304−315. (in Chinese)
[38]	Wu, X. J. 2017. Parkes radio telescope with pulsar survey discovery — Memorial pulsar discovery 50 years. Science, 69(6): 43−49. (in Chinese)
[39]	Liu, X. F., Lao, B. Q., An, T., et al. 2021. Research on pulsar candidate identification method based on deep residual neural network. Acta Astronomica Sinica, 62(2): 98−111. (in Chinese) doi: 10.15940/j.cnki.0001-5245.2021.02.009
[40]	Sarkissian, J. 2010. The Parkes Pulsar Timing Array (PPTA).In Proceedings of the Conference dedicated to Viktor Ambartsumian's 100th anniversary, Evolution of Cosmic Objects Through Their Physical Activity.
[41]	Manchester, R. N. 2013. The international pulsar timing array. Classical and Quantum Gravity, 30: 55−61. doi: 10.1088/0264-9381/30/22/224010
[42]	Devine, T. R., Goseva-Popstojanova, K., McLaughlin, M. 2016. Detection of dispersed radio pulses: A machine learning approach to candidate identification and classification. Monthly Notices of the Royal Astronomical Society, 459(2): 1519−1532. doi: 10.1093/mnras/stw655
[43]	Punia, A., Sardana, A., Subashini, M. 2017. Evaluating advanced machine learning techniques for pulsar detection from HTRU survey. In Proceedings of International Conference on Intelligent Sustainable Systems.
[44]	Balakrishnan, V., Champion, D., Barr, E.,et al. 2021. Pulsar candidate identification using semi-supervised generative adversarial networks. Monthly Notices of the Royal Astronomical Society, 505(1): 1180−1194. doi: 10.1093/mnras/stab1308
[45]	Agarwal, D., Aggarwal, K., Burke-Spolaor, S., et al. 2020. A deep-learning based classifier for fast transient classification. Monthly Notices of the Royal Astronomical Society, 497(2): 1661−1674. doi: 10.1093/mnras/staa1856
[46]	Zhang, B., You, S. P., Xie, X. Y., et al. 2023. Application of single-pulse search candidate identification based on machine learning to FAST observation CRAFTS data. Progress in Astronomy, 41(3): 415−428. (in Chinese) doi: 10.3969/j.issn.1000-8349.2023.03.09
[47]	Liu, Y. 2022. Unsupervised clustering analysis study of large-scale pulsar candidate body signals. Master thesis, Guizhou Normal University.
[48]	Wang, H. F., Zhu, W. W., Guo, P., et al. 2019. Pulsar candidate selection using ensemble networks for FAST drift-scan survey. Science China Physics, Mechanics & Astronomy, 62: 959507. doi: 10.1007/s11433-018-9388-3
[49]	Liu, Y., Jin, J., Zhao, H. Y., et al. 2023. MFPIM: A deep learning model based on multimodal Fusion technology for pulsar identification. The Astrophysical Journal, 954(1): 86. doi: 10.3847/1538-4357/acd9c8
[50]	You, Z. Y., Pan, Y. R., Ma, Z., et al. 2024. Applying hybrid clustering in pulsar candidate sifting with multi-modality for FAST survey. Research in Astronomy and Astrophysics, 24(3): 035022. doi: 10.1088/1674-4527/ad0c28
[51]	Zeng, P., Yu, X. H., Liu, Z. J., et al. 2024. Application of the pre-trained model in the screening of pulsar candidates. Automation Application, 65(8): 227−231. (in Chinese) doi: 10.19769/j.zdhy.2024.08.072
[52]	Morello, V., Barr, E. D., Bailes, M., et al. 2014. SPINN: a straightforward machine learning solution to the pulsar candidate selection problem. Monthly Notices of the Royal Astronomical Society, 443(2): 1651−1662. doi: 10.1093/mnras/stu1188
[53]	Eatough, R. P., Molkenthin, N., Kramer, M., et al. 2010. Selection of radio pulsar candidates using artificial neural networks. Monthly Notices of the Royal Astronomical Society, 407(4): 2443−2450. doi: 10.1111/j.1365-2966.2010.17082.x
[54]	Bates, S. D., Bailes, M., Barsdell, B. R., et al. 2012. The high time resolution universe survey VI: An artificial neural network and timing of 75 pulsars. Monthly notices of the Royal Astronomical Society, 427(2): 1052−1065. doi: 10.1111/j.1365-2966.2012.22042.x
[55]	Zhu, W. W., Berndsen, A., Madsen, E. C., et al. 2014. Searching for pulsars using image pattern recognition. The Astrophysical Journal, 781: 117. doi: 10.1088/0004-637x/781/2/117
[56]	Wang, Y. C., Li, M. T., Pan, Z. C.,et al. 2019. Pulsar candidate classification with deep convolutional neural networks. Research in Astronomy and Astrophysics, 19: 133. doi: 10.1088/1674-4527/19/9/133
[57]	Yin, Q., Wang, Y., Zheng, X., et al. 2022. Pulsar candidate recognition using deep neural network model. Electronics, 11(14): 2216. doi: 10.3390/electronics11142216
[58]	Cabrera-Vives, G., Reyes, I., Förster, F., et al. 2017. Deep-HiTS: rotation invariant convolutional neural network for transient detection. The Astrophysical Journal, 836: 97. doi: 10.3847/1538-4357/836/1/97
[59]	Radford, A., Metz, L., Chintala, S. 2015. Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv: 1511.06434.
[60]	Douzas, G., Bacao, F. 2018. Effective data generation for imbalanced learning using conditional generative adversarial networks. Expert Systems with Application, 91: 464−471. doi: 10.1016/j.eswa.2017.09.030
[61]	Wang, Z. L. 2023. Pulsar candidate discrimination method based on semi-supervised learning. Master thesis, Southwest University of Science and Technology. (in Chinese)
[62]	Zhou, L. Y. 2024. Research of image classification based on generative adversarial nets and its application for pulsar candidate identification. Doctoral thesis, Guizhou Normal University. (in Chinese)
[63]	Tan, C. M., Lyon, R. J., Stappers, B. W., et al. 2018. Ensemble candidate classification for the LOTAAS pulsar survey. Monthly Notices of the Royal Astronomical Society, 474(4): 4571−4583. doi: 10.1093/mnras/stx3047
[64]	Lyon, R. J., Stappers, B. W., Cooper, S., et al. 2016. Fifty years of pulsar candidate selection: from simple filters to a new principled real-time classification approach. Monthly Notices of the Royal Astronomical Society, 459(1): 1104−1123. doi: 10.1093/mnras/stw656
[65]	Jiang, Y., Jin, J., Yu, Y. L., et al. 2019. Denoising method of pulsar photon signal based on recurrent neural network. In Proceedings of 2019 IEEE International Conference on Unmanned Systems, 661−665.
[66]	Zhu, K. R., Kang, S. J., Zheng, Y. G. 2021. Searching for AGN and pulsar candidates in 4FGL unassociated sources using machine learning. Research in Astronomy and Astrophysics, 21: 015. doi: 10.1088/1674-4527/21/1/15
[67]	Cai, N. N., Han, J. L., Jing, W. C., et al. 2023. Pulsar candidate classification using a computer vision method from a combination of convolution and attention. Research in Astronomy and Astrophysics, 23: 10. doi: 10.1088/1674-4527/accdc2
[68]	Guo, P., Duan, F. Q., Wang, P., et al. 2019. Pulsar candidate classification using generative adversary networks. Monthly Notices of the Royal Astronomical Society, 490(4): 5424−5439. doi: 10.1093/mnras/stz2975
[69]	Liu, T. 2020. Research on pulsar candidate selection method based on artificial intelligence. Master thesis, Hunan University. (in Chinese)
[70]	Yin, Q., Li, Y. F., Li, J. J., et al. 2022. Pulsar-candidate selection using a generative adversarial network and ResNeXt. The Astrophysical Journal Supplement Series, 264: 2. doi: 10.3847/1538-4365/ac9e54

Articles Related

[1]	Ting Zhang, Hailong Zhang, Yazhou Zhang, Xu Du, Wenna Cai, Han Wu, Yuyue Jiao, Wanqiong Wang, Jie Wang, Xinchen Ye, Jia Li. Application of machine learning in astronomical spectral data mining [J]. Astronomical Techniques and Instruments, 2025, 2(2): 73-87. DOI: 10.61977/ati2024057
[2]	Xiaoqian Zhang, Huang Wang, QiChang An, Hongchao Zhao. Optical Neural Networks: Principles, Challenges, and Future Prospects in Computing and Astrophotonics [J]. Astronomical Techniques and Instruments. DOI: 10.61977/ati2025031
[3]	Xiong Jianping, Liu Chao, Li Jiao, Li Chunqian, Zhao Yongheng. Light Curve Modeling of Semi-detached Binaries Based on Neural Network [J]. Astronomical Techniques and Instruments, 2023, 20(2): 123-134. DOI: 10.14005/j.cnki.issn1672-7673.20221116.001
[4]	Zhang Hailong, Zhang Yazhou, Wang Jie, Ye Xinchen, Wang Wanqiong, Li Jia, Zhang Meng, Du Xu. Application of RFI Mitigation Technology in Radio Astronomy [J]. Astronomical Research and Technology, 2022, 19(6): 613-625. DOI: 10.14005/j.cnki.issn1672-7673.20220415.002
[5]	Liu Yanling, Chen Maozheng, Yuan Jianping. A Review of Fast Radio Burst Search Methods Based on Machine Learning [J]. Astronomical Research and Technology, 2022, 19(5): 509-517. DOI: 10.14005/j.cnki.issn1672-7673.20210916.001
[6]	Jiang Jiatao, Xie Xiaoyao, Yu Xuhong. Research on Compression of Pulsar Candidate Diagnostic Images Based on WBS and Deep Neural Network [J]. Astronomical Research and Technology, 2022, 19(5): 470-478. DOI: 10.14005/j.cnki.issn1672-7673.20220323.001
[7]	Li Rongkai, Li Xirui, Cai Yong. Research on Fault Diagnosis of Hydrogen Maser Based on Machine Learning [J]. Astronomical Research and Technology, 2020, 17(3): 349-356.
[8]	Cui Shun, Xu Yunfei, Su Liying, Cui Chenzhou, Fan Dongwei, Han Jun, Wang Chuanzhong, Zhang Lei, Zhang Jie. Classification of All-sky Camera Data Based on Convolutional Neural Network [J]. Astronomical Research and Technology, 2019, 16(2): 225-235.
[9]	Fu Xiaona, Liao Chengwu, Bai Xianyong, Liang Bo, Feng Song, Yang Hongjuan, Yang Yunfei. A Detection Method for Sunspots Based on Convolutional Neural Network LeNet-5 [J]. Astronomical Research and Technology, 2018, 15(3): 340-346.
[10]	Lei Yu, Cai Hongbing, Zhao Danning. Effects of Training Patterns on Predictions of Variations of Length Of Day Using an Extreme Learning Machine Neural Network [J]. Astronomical Research and Technology, 2015, 12(3): 299-305.