J/ApJS/230/20ivo://CDS.VizieR/J/ApJS/230/20doi:10.26093/cds/vizier.22300020CDSAniyan A.K.Thorat K.2017-09-04T08:43:37Z2017-08-17T14:51:41ZCDS support team

CDS, Observatoire de Strasbourg, 11 rue de l'Universite, F-67000 Strasbourg, France

cds-question@unistra.frradio-galaxiesWe present the application of a deep machine learning technique to classify radio images of extended sources on a morphological basis using convolutional neural networks (CNN). In this study, we have taken the case of the Fanaroff-Riley (FR) class of radio galaxies as well as radio galaxies with bent-tailed morphology. We have used archival data from the Very Large Array (VLA)-Faint Images of the Radio Sky at Twenty Centimeters survey and existing visually classified samples available in the literature to train a neural network for morphological classification of these categories of radio sources. Our training sample size for each of these categories is ~200 sources, which has been augmented by rotated versions of the same. Our study shows that CNNs can classify images of the FRI and FRII and bent-tailed radio galaxies with high accuracy (maximum precision at 95%) using well-defined samples and a "fusion classifier," which combines the results of binary classifications, while allowing for a mechanism to find sources with unusual morphologies. The individual precision is highest for bent-tailed radio galaxies at 95% and is 91% and 75% for the FRI and FRII classes, respectively, whereas the recall is highest for FRI and FRIIs at 91% each, while the bent-tailed class has a recall of 79%. These results show that our results are comparable to that of manual classification, while being much faster. Finally, we discuss the computational and data-related challenges associated with the morphological classification of radio galaxies with CNNs.2017ApJS..230...20Ahttps://cdsarc.cds.unistra.fr/viz-bin/cat/J/ApJS/230/20CatalogResearchIsServedByTAP VizieR generic serviceIsServedByConesearch servicerelated-toVIII/65 : 1.4GHz NRAO VLA Sky Survey (NVSS) (Condon+ 1998)VIII/92 : The FIRST Survey Catalog, Version 2014Dec17 (Helfand+ 2015)J/MNRAS/390/819 : Combined NVSS-FIRST Galaxies (CoNFIG) sample (Gendre+, 2008)J/MNRAS/404/1719 : CoNFIG sample II (Gendre+, 2010)J/ApJS/194/31 : Morphology for groups in the FIRST database (Proctor, 2011)J/MNRAS/421/1569 : Properties of 18286 SDSS radio galaxies (Best+, 2012)J/MNRAS/430/3086 : CoNFIG AGN sample (Gendre+, 2013)J/MNRAS/446/2985 : Double-lobed radio sources catalog (van Velzen+, 2015)https://cds.unistra.fr/vizier-org/licences_vizier.htmlhttps://vizier.cds.unistra.fr/viz-bin/VizieR-2?-source=J/ApJS/230/20https://vizier.iucaa.in/viz-bin/VizieR-2?-source=J/ApJS/230/20http://vizieridia.saao.ac.za/viz-bin/VizieR-2?-source=J/ApJS/230/20https://vizier.cds.unistra.fr/viz-bin/votable?-source=J/ApJS/230/20https://vizier.iucaa.in/viz-bin/votable?-source=J/ApJS/230/20http://vizieridia.saao.ac.za/viz-bin/votable?-source=J/ApJS/230/20GETtext/xml+votablehttps://tapvizier.cds.unistra.fr/TAPVizieR/tapCone search capability for table J/ApJS/230/20/table5 (Table of predictions for validation samples)https://vizier.cds.unistra.fr/viz-bin/conesearch/J/ApJS/230/20/table5?https://vizier.iucaa.in/viz-bin/conesearch/J/ApJS/230/20/table5?http://vizieridia.saao.ac.za/viz-bin/conesearch/J/ApJS/230/20/table5?GETtext/xml+votable180.050000true216.707666670.933305560.0055555555555555566/4119 4198 4324 4372 4376 4432 4451 4461 4475 4563 4572 4611 4646 4680 4731 4808 4901 5234 5260 5264 5278 5340 5355 5435 5517 5714 5801 5813 5825 5920 5948 5979 5993 6018 6023 6044 6071 6075 6088 6107 6168 6171 6209 6236 6396 6409 6528 6551 6571 6609 6612 6620 6622 6966 7225 7354 7376 7395 8218 8220 8304 8369 8373 8384 8393 8431 8432 8437 8450 8467 8484 8486 8508 8537 8549 8572 8608 8632 8641 8647 8705 8858 8897 8986 9016 9018 9030 9063 9073 9252 9268 9272 9370 9421 9490 9497 9761 9795 9817 9820 10137 10188 10262 10297 10320 10345 10387 10411 10492 10529 10761 10776 10797 10873 10910 10925 11137 11158 11349 11377 11462 11485 11591 17675 17751 18069 18078 18176 18537 18767 18800 25460 25860 25920 25923 25954 25956 25964 25977 26007 26033 26050 26057 26302 26364 26591 26832 26964 27083 27148 27151 27228 27345 27428 27448 27456 27478 27507 27672 27686 27692 27783 27830 27848 27934 27980 27987 28004 28040 28147 28249 28276 28430 28479 28584 28609 31283 31432 31540 31550 31674 32412 32413 32489 32497https://cdsarc.cds.unistra.fr/viz-bin/moc/J/ApJS/230/20?format=asciiRadiodefaultJ/ApJS/230/20/table5Table of predictions for validation samplesrecnoRecord number assigned by the VizieR team. Should Not be used for identification.meta.recordintNameSource Namemeta.id;meta.maincharRAJ2000Hour of Right Ascension (J2000)pos.eq.ra;meta.mainDEJ2000Degree of Declination (J2000)pos.eq.dec;meta.mainTrueTrue Class of Source (1)src.classcharPredPrediction by algorithm (1)src.classcharProbProbability Score of Prediction (1)stat.probabilitydoubleCoNFIGDisplay data from CoNFIG (Gendre & Wall 2008, J/MNRAS/390/819 and Gendre+, 2010, J/MNRAS/404/1719) within 0.5"meta.ref.urlintnullableB12Display data from Best+, 2012, J/MNRAS/421/1569, within 2"meta.ref.urlintnullableNVSSDisplay data from NVSS (VIII/65) within 5"meta.ref.urlintnullableFIRSTDisplay data from NVSS (VIII/92) and Proctor, 2011, J/ApJS/194/31, within 3"meta.ref.urlintnullable