SUPERVISED AUTOMATIC IDENTIFICATION OF EXTRAGALACTIC SOURCES IN THE WISExSUPERCOSMOS CATALOGUE

Анотація

We present new catalogue of ~8,500,000 extragalactic objects as a result of automatic classification of WISE and SuperCOSMOS (SCOS) cross-identification product.  The  main  goal  is  to  create  a  set  of  candidates  in extragalactic  objects  due  to  colour  (photometric)  features through machine learning techniques. Extragalactic sources were separated from stars in high-dimensional colour space using Support Vector Machine (SVM) classifier. Construction of catalogue of the extragalactic objects is based  on  the  four  important  procedures:  1.  Cross-identification of the WISExSCOS catalogues. 2. Training set creation (Gaia DR1 and 2MASX\XSC data). 3. Feature engineering  and  colour-space  constructing  for  further learning  and  classification.  4.  Fine-tuning  of  SVM  and separation and classification processes. In  result  we  got  high-accuracy  (~98%)  algorithm  for extragalactic  source  identification  in  built  colour  space. Product  of  algorithm  realization  is  presented  as photometric catalogue of the extragalactic objects and can be used for further astronomical investigations.