A Machine Learning Based Morphological Classification of 14,251 Radio AGNs Selected From The Best-Heckman Sample

Zhixian Ma, Haiguang Xu, Jie Zhu, Dan Hu, Weitian Li, Chenxi Shan, Zhenghao Zhu, Liyi Gu, Jinjin Li, Chengze Liu, Xiangping Wu

Published 2018-12-18Version 1

We present a morphological classification of 14,251 radio active galactic nuclei (AGNs) into six types, i.e., typical Fanaroff-Riley Class I / II (FRI/II), FRI/II-like bent tailed (BT), X-shaped radio galaxy (XRG), and ring-like radio galaxy (RRG), by designing a convolutional neural network (CNN) based autoencoder (CAE), namely MCRGNet, and applying it to a labeled radio galaxy (LRG) sample containing 1,442 AGNs and an unlabled radio galaxy (unLRG) sample containing 14,251 unlabeled AGNs selected from the Best-Heckman sample. We train the MCRGNet and implement the classification task by a three-step strategy, i.e., pre-training, fine-tuning, and classification, which combines both unsupervised and supervised learnings. A four-layer dichotomous tree is designed to classify the radio AGNs, which leads to a significantly better performance than the direct six-type classification. On the LRG sample, our MCRGNet achieves a total precision of \$\sim 93\%\$ and an averaged sensitivity of \$\sim 87\%\$, which are better than those obtained in previous works. On the unLRG sample, whose labels have been human-inspected, the neural network achieves a total precision of \$\sim 84\%\$. Also, by using the Sloan Digital Sky Survey (SDSS) Data Release 7 (DR7) to calculate the $r$-band absolute magnitude (\$M_\mathrm{opt}\$), and using the flux densities to calculate the radio luminosity (\$L_\mathrm{radio}\$), we find that the distributions of the unLRG sources on the \$L_\mathrm{radio}\$-\$M_\mathrm{opt}\$ plane do not show an apparent redshift evolution, and could confirm with a sufficiently large sample that there could not exist an abrupt separation between FRIs and FRIIs as reported in some previous works.