Abstract: ClaRAN (Classifying Radio sources Automatically with Neural networks) classifies radio source morphology based upon the Faster Region-based Convolutional Neutral Network (Faster R-CNN). It is capable of associating discrete and extended components of radio sources in an automated fashion. ClaRAN demonstrates the feasibility of applying deep learning methods for cross-matching complex radio sources of multiple components with infrared maps. The promising results from ClaRAN have implications for the further development of efficient cross-wavelength source identification, matching, and morphology classifications for future radio surveys.
Credit: Wu, Chen; Wong, Oiwei Ivy; Rudnick, Lawrence; Shabala, Stanislav S.; Alger, Matthew J.; Banfield, Julie K.; Ong, Cheng Soon; White, Sarah V.; Garon, Avery F.; Norris, Ray P.; Andernach, Heinz; Tate, Jean; Lukic, Vesna; Tang, Hongming; Schawinski, Kevin; Diakogiannis, Foivos I.
Preferred citation method: https://ui.adsabs.harvard.edu/abs/2019MNRAS.482.1211W