Prediction of parameters and classification of molecular outflows using convolutional neural networks
DOI:
https://doi.org/10.26577/RCPh.2020.v75.i4.09Keywords:
radio astronomy, star formation, bipolar outflows, machine learning, convolutional neural networksAbstract
Machine learning is gaining popularity in modern astrophysics for its incredibly powerful ability to make predictions or make assumptions over large amounts of data. We describe the application of machine learning to regression of molecular outflow parameters (mass, momentum, kinetic energy, and dynamic time) and classification of bipolar outflow using convolutional neural networks. The size of our training sample is ~ 125 sources of molecular outflow for classification, that is, 80% of the total amount of data, where 67 sources are bipolar outflow and ~ 75 sources of bipolar outflow for regression. The results show that the use of CNN improves the image classification accuracy up to 97%. The regression model predicts molecular outflow parameters with an average absolute percentage error of 37.7% for the training data and with an average absolute error of 88.0 (mass), 1237.7 (momentum), 193.3 (kinetic energy), and 3.0 (dynamic time) for test data. The machine learning algorithm reduces data processing time for predictions and classification, and this methodology has a broad prospect for future studies of astrophysics problems.
References
2 Y. Bai, J. Liu, S. Wang, and F. Yang, The Astronomical Journal, 157, 9 (2018).
3 G. Martin, S. Kaviraj, A. Hocking, S.C. Read, and J.E. Geach, Monthly Notices of the Royal Astronomical Society, 491, 1408-1426 (2020).
4 Y. Bai, J.F. Liu, and S. Wang, Research in Astronomy and Astrophysics, 18, 118 (2018).
5 A. Ghosh, C.M. Urry, Z. Wang, K. Schawinski, D. Turp, and M.C. Powell, The Astrophysical Journal. 895, 112 (2020).
6 E.J. Kim, and R.J. Brunner, Monthly Notices of the Royal Astronomical Society, 464, 4463-4475 (2017).
7 S. Akras, M.L. Leal-Ferreira, L. Guzman-Ramirez, and G. Ramos-Larios, Monthly Notices of the Royal Astronomical Society, 483, 5077-5104 (2019).
8 K. Sharma, A. Kembhavi, A. Kembhavi, T. Sivarani, S. Abraham, and K. Vaghmare Monthly Notices of the Royal Astronomical Society, 491, 2280-2300 (2020).
9 V. Lukic, M. Brüggen, B. Mingo, J.H. Croston, G. Kasieczka, and P.N. Best, Monthly Notices of the Royal Astronomical Society, 487, 1729-1744 (2019).
10 X.P. Zhu, J.M. Dai, C.J. Bian, Y. Chen, S. Chen, and C. Hu, Astrophysics and Space Science, 364, 55 (2019).
11 W. Liu, M. Zhu, C. Dai, D.Y. He, J. Yao, H.F. Tian, B.Y. Wang, K. Wu, Y. Zhan, B.Q. Chen, A.L. Luo, R. Wang, Y. Cao, and X.C. Yu, Monthly Notices of the Royal Astronomical Society, 483, 4774-4783 (2019).
12 S. Fabbro, K.A. Venn, T. O'Briain, S. Bialek, C.L. Kielty, F. Jahandar, S. Monty, Monthly Notices of the Royal Astronomical Society, 475, 2978-2993 (2018).
13 C.N. Beaumont, J.P. Williams, and A.A. Goodman, The Astrophysical Journal, 741, 14 (2011).
14 C.N. Beaumont, A.A. Goodman, S. Kendrew, J.P. Williams, and R. Simpson, The Astrophysical Journal Supplement Series, 214, 3 (2014).
15 C.M. Van Oort, D. Xu, S.S. Offner, and R.A. Gutermuth, The Astrophysical Journal. 880, 83 (2019).
16 D. Xu, S.S. Offner, and R.A. Gutermuth, and C. Van Oort, The Astrophysical Journal. 890, 64 (2020).
17 D. Xu, S.S. Offner, and R.A. Gutermuth, and C. Van Oort, arXiv preprint arXiv:2010.12525, (2020).
18 S. Zhang, J. Yang, Y. Xu, X. Chen, Y. Su, Y. Sun, X. Zhou, Y. Li, and D. Lu, The Astrophysical Journal Supplement Series, 248, 15 (2020).
19 D. Xu, and S.S.R. Offner, The Astrophysical Journal, 851,149 (2017).
20 A. Krizhevsky, I. Sutskever, G.E. Hinton, Communications of the ACM, 60, 84-90 (2017).
21 R. Girshick, Proceedings of the IEEE international conference on computer vision (Santiago, 7-15 December, 2015), p.1440-1448.
22 S. Ren, K. He, R. Girshick, and J. Sun, IEEE transactions on pattern analysis and machine intelligence, 39, 1137 (2017).
23 J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, Proceedings of the IEEE conference on computer vision and pattern recognition (Las Vegas, 27-30 June, 2016), p.779-788.
24 L. Zhao, and S.Li, Electronics. 9, 537 (2020).
25 G. Yao, T. Lei, and J. Zhong, Pattern Recognition Letters, 118, 14-22 (2019).
26 Q. Li, J. Zhou, J. Esimbek, Y. He, W.A. Baan, D. Li, G. Wu, X. Tang, W. Ji, D. Zhexebay, The Astrophysical Journal. 867, 167 (2018).
