Classifying bent radio galaxies from a mixture of point-like/extended images with Machine Learning.

IEEE Radio and Antenna Days of the Indian Ocean

无线电电子学

Bastien, David^1 ; Oozeer, Nadeem^2,3,4 ; Somanah, Radhakrishna^1,5

Physics Department, University of Mauritius, Reduit, Mauritius^1

SKA South Africa, The Park, Park Road, Pinelands, Cape Town

7405, South Africa^2

African Institute for Mathematical Sciences, 6-8 Melrose Road, Muizenberg

7945, South Africa^3

Centre for Space Research, North-West University, Potchefstroom

2520, South Africa^4

Universite des Mascareignes, Avenue de la Concorde Rose Hill, Roche Brunes, Mauritius^5

关键词: Accuracy rate;    Extended sources;    Galaxy clusters;    Ml algorithms;    Radio galaxies;    Radio images;    Radio sources;    Random forest algorithm;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/198/1/012013/pdf
DOI  :  10.1088/1757-899X/198/1/012013

来源: IOP

【 摘 要 】

The hypothesis that bent radio sources are supposed to be found in rich, massive galaxy clusters and the avalibility of huge amount of data from radio surveys have fueled our motivation to use Machine Learning (ML) to identify bent radio sources and as such use them as tracers for galaxy clusters. The shapelet analysis allowed us to decompose radio images into 256 features that could be fed into the ML algorithm. Additionally, ideas from the field of neuro-psychology helped us to consider training the machine to identify bent galaxies at different orientations. From our analysis, we found that the Random Forest algorithm was the most effective with an accuracy rate of 92% for a classification of point and extended sources as well as an accuracy of 80% for bent and unbent classification.