CLASSIFICATION OF JETS IN ACTIVE GALACTIC NUCLEI USING MACHINE LEARNING
Section: HIGH ENERGY ASTROPHYSICS
Authors:
1.
Moscow Institute of Physics and Technology
2.
Astro Space Center of P. N. Lebedev Physical Institute of the Russian Academy of Sciences
Institute of Physics, Pontifical Catholic University of Valparaiso
Institute of Physics, Pontifical Catholic University of Valparaiso
Type:
Сonference article
Pages:
from 113
to 116
Published:
27.12.2024
Subject area:
UDC 52
UDC 53
UDC 520
UDC 521
UDC 523
UDC 524
UDC 52-1
UDC 52-6
CSCSTI 41.00
CSCSTI 29.35
CSCSTI 29.31
CSCSTI 29.33
CSCSTI 29.27
CSCSTI 29.05
Russian Classification of Professions by Education 03.06.01
Russian Classification of Professions by Education 03.05.01
Russian Classification of Professions by Education 03.04.03
Russian Library and Bibliographic Classification 2
Russian Library and Bibliographic Classification 223
Russian Trade and Bibliographic Classification 614
Russian Trade and Bibliographic Classification 6135
BISAC SCI004000 Astronomy
BISAC SCI005000 Physics / Astrophysics
UDC 53
UDC 520
UDC 521
UDC 523
UDC 524
UDC 52-1
UDC 52-6
CSCSTI 41.00
CSCSTI 29.35
CSCSTI 29.31
CSCSTI 29.33
CSCSTI 29.27
CSCSTI 29.05
Russian Classification of Professions by Education 03.06.01
Russian Classification of Professions by Education 03.05.01
Russian Classification of Professions by Education 03.04.03
Russian Library and Bibliographic Classification 2
Russian Library and Bibliographic Classification 223
Russian Trade and Bibliographic Classification 614
Russian Trade and Bibliographic Classification 6135
BISAC SCI004000 Astronomy
BISAC SCI005000 Physics / Astrophysics
Language:
English
Keywords:
galaxies: active; quasars: general; techniques: high angular resolution; methods: machine learning
Abstract (English):
This work explores the application of machine learning techniques to classifying jetted active galactic nuclei (AGN) based on Very-Long-Baseline Interferometry (VLBI) observations at frequencies 1-90 GHz. Building upon previous work by Fanaroff and Riley, who classified relativistic jets in radio galaxies on kiloparsec scales, we extend this classification to parsec scales, closer to the central supermassive black hole. This approach enables detailed study of jet spatial structures and can help enhancing accuracy in global positioning systems. We define four morphological classes: single Gaussian source, double Gaussian source, and sources with single or double-sided jets. Synthetic models of AGN jets were generated to create a training dataset for a convolutional neural network (CNN). The CNN was trained on these synthetic data and subsequently applied to classify 130 thousand AGN jet images from the Astrogeo database. The distribution of images into designated classes, predicted by CNN, qualitatively matches the expected outcome.
This work explores the application of machine learning techniques to classifying jetted active galactic nuclei (AGN) based on Very-Long-Baseline Interferometry (VLBI) observations at frequencies 1-90 GHz. Building upon previous work by Fanaroff and Riley, who classified relativistic jets in radio galaxies on kiloparsec scales, we extend this classification to parsec scales, closer to the central supermassive black hole. This approach enables detailed study of jet spatial structures and can help enhancing accuracy in global positioning systems. We define four morphological classes: single Gaussian source, double Gaussian source, and sources with single or double-sided jets. Synthetic models of AGN jets were generated to create a training dataset for a convolutional neural network (CNN). The CNN was trained on these synthetic data and subsequently applied to classify 130 thousand AGN jet images from the Astrogeo database. The distribution of images into designated classes, predicted by CNN, qualitatively matches the expected outcome.
Keywords:
galaxies: active; quasars: general; techniques: high angular resolution; methods: machine learning
galaxies: active; quasars: general; techniques: high angular resolution; methods: machine learning
1. Blandford R., Meier D., and Readhead A., 2019, Annu. Rev. Astron. Astrophys, 57, p. 467
2. Fanaroff B. and Riley J., 1974, MNRAS, 167, p. 31P
3. Forgy E., 1965, Biometrics, 21, p. 768
4. Lacy M., Baum S., Chandler C., et al., 2020, PASP, 132, id. 035001
5. LeCun Y., Boser B., Denker J., et al., 1989, Neural Comput., 1, p. 541
6. Lister M., Aller M., Aller H., et al., 2018, ApJ Supp. Serires, 234, p. 12
7. Lloyd S., 1982, IEEE Trans. Inf. Theory, 28, p. 129
8. Petrov L., 2016, The 13th EVN Symposium and Users Meeting Proceedings, arXiv:1610.04951
9. Petrov L. 2021, AJ, 161, p. 14
