J/A+A/648/A122ivo://CDS.VizieR/J/A+A/648/A122doi:10.26093/cds/vizier.36480122CDSVavilova I.B.Dobrycheva D.V.Vasylenko M.Yu.Elyiv A.A.Melnyk O.V.,Khramtsov V.2021-07-05T11:27:09Z2021-04-26T09:07:36ZCDS support team

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

cds-question@unistra.frgalaxiescatalogsgalaxy-classification-systemsvisible-astronomysloan-photometryMachine learning methods are effective tools in astronomical tasks for classifying objects by their individual features. One of the promising utilities is related to the morphological classification of galaxies at different redshifts. We use the photometry-based approach for the SDSS data (1) to exploit five supervised machine learning techniques and define the most effective among them for the automated galaxy morphological classification; (2) to test the influence of photometry data on morphology classification; (3) to discuss problem points of supervised machine learning and labeling bias; and (4) to apply the best fitting machine learning methods for revealing the unknown morphological types of galaxies from the SDSS DR9 at z<0.1. We used different galaxy classification techniques: human labeling, multi-photometry diagrams, naive Bayes, logistic regression, support-vector machine, random forest, k-nearest neighbors. We present the results of a binary automated morphological classification of galaxies conducted by human labeling, multi-photometry, and five supervised machine learning methods. We applied it to the sample of galaxies from the SDSS DR9 with redshifts of 0.02<z<0.1 and absolute stellar magnitudes of -24mag<Mr<-19.4mag. For the analysis we used absolute magnitudes Mu, Mg, Mr, Mi, Mz; color indices Mu-Mr, Mg-Mi, Mu-Mg, Mr-Mz; and the inverse concentration index to the center R50/R90. We determined the ability of each method to predict the morphological type, and verified various dependencies of the method's accuracy on redshifts, human labeling, morphological shape, and overlap of different morphological types for galaxies with the same color indices. We find that the morphology based on the supervised machine learning methods trained over photometric parameters demonstrates significantly less bias than the morphology based on citizen-science classifiers. The support-vector machine and random forest methods with Scikit-learn software machine learning library in Python provide the highest accuracy for the binary galaxy morphological classification. Specifically, the success rate is 96.4% for support-vector machine (96.1% early E and 96.9% late L types) and 95.5% for random forest (96.7% early E and 92.8% late L types). Applying the support-vector machine for the sample of 316 031 galaxies from the SDSS DR9 at z<0.1 with unknown morphological types, we found 139659 E and 176372 L types among them.2021A&A...648A.122Vhttps://cdsarc.cds.unistra.fr/viz-bin/cat/J/A+A/648/A122CatalogResearchIsServedByTAP VizieR generic serviceIsServedByConesearch servicerelated-tohttp://skyserver.sdss.org/dr9 : SDSS DR9 Home Pagehttps://cds.unistra.fr/vizier-org/licences_vizier.htmlhttps://vizier.cds.unistra.fr/viz-bin/VizieR-2?-source=J/A+A/648/A122https://vizier.iucaa.in/viz-bin/VizieR-2?-source=J/A+A/648/A122http://vizieridia.saao.ac.za/viz-bin/VizieR-2?-source=J/A+A/648/A122https://vizier.cds.unistra.fr/viz-bin/votable?-source=J/A+A/648/A122https://vizier.iucaa.in/viz-bin/votable?-source=J/A+A/648/A122http://vizieridia.saao.ac.za/viz-bin/votable?-source=J/A+A/648/A122GETtext/xml+votablehttps://tapvizier.cds.unistra.fr/TAPVizieR/tapCone search capability for table J/A+A/648/A122/catalog (Binary morphology SDSS galaxies catalog)https://vizier.cds.unistra.fr/viz-bin/conesearch/J/A+A/648/A122/catalog?https://vizier.iucaa.in/viz-bin/conesearch/J/A+A/648/A122/catalog?http://vizieridia.saao.ac.za/viz-bin/conesearch/J/A+A/648/A122/catalog?GETtext/xml+votable180.050000true0.0064585607-0.09259815760.0055555555555555561/5 8 10 27 2/16-17 19 25 28 36 38 103 107 3/72-73 75 97 116 176-178 184 407 409-411 423 427 491 494 4/296-297 299 399 468-469 472 592 594 600 602 624 716 718 724 740 744-746 773-774 1109-1110 1114 1125-1126 1129-1130 1216 1367 1373 1375 1599 1621-1623 1625-1627 1685-1687 1690-1691 1701 1703 1707 1961-1963 1980 1982-1983 2027 5/0 10 136 138 267 295 419 425 1192-1193 1195 1540-1541 1543 1549 1585 1588-1589 1591 1684-1685 1728-1729 1732-1733 1880-1882 1896-1898 1900-1901 2372 2374 2380-2381 2504 2506 2515 2518 2521 2523-2524 2526 2528 2530 2536 2545 2547-2548 2550 2553 2555-2556 2868 2870 2876 2878 2968-2970 2988 3077 3089-3090 3100-3101 3136-3138 3153 4223 4287 4303 4307-4310 4312-4314 4323 4325-4326 4328-4330 4350-4351 4373-4375 4377-4380 4387-4390 4392-4394 4415-4416 4423 4433 4444 4450 4453-4455 4460-4461 4463 4466-4468 4472-4473 4475 4495 4498-4499 4508-4509 4513-4515 4524 4533 4544-4545 4547-4548 4550-4551 4556 4560 4562 4566 4569 4574-4575 4582 4596-4598 4601-4602 4629-4631 4633-4636 4645 4647 4651-4652 4654 4656 4672 4685 4687 4693-4698 4700-4701 4706 4709-4714 4716-4717 4719-4720 4736-4738 4750-4751 4757-4759 4761-4762 4764 4766 4773-4774 4776-4778 4782-4783 4788-4790 4792 4794-4798 4800 4802 4831 4835 4838 4842 4845-4847 4850-4854 4856 4858 4872 4917-4919 4921-4924 4933-4935 4937-4940 4944 4960 4995 4997-5002 5008 5461-5463 5491 5588-5589 5591 5597 5621 5623 5679 5761-5765 5768 5786 5795 5797-5798 5801-5802 6391 6461-6463 6477-6479 6481-6483 6497-6499 6541-6543 6735 6737-6739 6757-6759 6809-6811 6821-6823 6825-6827 7508-7510 7786 7823 7829-7831 7833-7834 7839 7841-7843 7882-7883 7886 7924 7926-7927 8099 8102-8103 8105-8107 8114-8115 8120-8122 8125 8127 8170-8171 9179 9181-9183 9191 9194-9196 9200-9202 11261-11263 12247 12253-12254 12271 12273-12276 12280 12282 6/4 8-9 12 14-15 26 32 34-36 38 521-524 526-527 538 548-550 556 640 723 993 1043-1045 1049 1051-1053 1055 1061-1063 1065 1067 1072 1075 1082 1086 1090 1153 1156-1157 1169 1171-1172 1174-1177 1205 1218 1224 1226-1227 1248 1690 1697 1712 1714 4776-4777 4779 6148-6150 6168-6169 6205 6337 6339 6348-6349 6360-6361 6363 6976-6977 6980-6981 6992-6993 6996-6997 7532-7533 7536-7538 7568-7570 7572 7576 7579 7582-7583 7596-7597 7608-7609 7612 7680-7681 7684-7685 7696-7697 7700-7701 8165 9494 9500 9503 9528 9530 9532 9616 9618 9624-9626 9648 9650 9656 9658 10000 10020-10022 10028 10030 10067 10070 10116 10118 10124 10152-10154 10177 10179 10185 10187 10209 10211 10217 10219 10232-10234 11476-11478 11484 11486 11508 11520 11522 11528 11530 11551-11552 11572-11573 11600 11602 11608 11610 11616-11617 11620-11621 11856 11858 11864 11884 11956 11960 11968-11970 12288-12290 12304-12305 12307 12313 12316-12317 12319 12341 12343 12352 12354-12355 12364 12408-12410 12480-12481 12484 12556-12558 12560-12561 12564 12568 12576 12609 12621 12632 15918 16887 16891 17207 17211 17223 17227 17244-17246 17260-17262 17264-17265 17287 17297-17299 17308-17310 17324-17326 17328-17330 17344 17346 17374-17375 17389 17391 17396-17397 17399 17469-17471 17485-17487 17490-17491 17505-17507 17524 17528 17547 17564-17566 17580-17582 17584-17586 17600-17602 17631 17647 17649-17650 17652-17654 17656-17658 17668-17670 17672-17673 17681-17683 17686 17689 17716 17718-17719 17723 17725-17727 17729 17731 17738 17741-17743 17780 17782-17786 17788 17790-17791 17794-17795 17798-17799 17805-17807 17809-17811 17848-17849 17851 17856-17858 17876-17878 17880-17881 17883-17884 17896-17898 17904-17905 17907-17908 17910-17911 17913-17916 17920-17922 17949 17951 17966-17967 17972 17974 17976 17978 17986 17989 17991 18040-18041 18043-18044 18046-18047 18049-18051 18100-18102 18104-18106 18109 18112-18114 18118-18120 18122-18125 18128 18130-18131 18136-18137 18139 18144-18145 18148-18150 18197-18199 18210 18212-18213 18215-18216 18221 18229-18231 18233-18238 18244-18245 18247 18253-18255 18258 18272-18274 18281-18285 18287-18288 18290-18292 18294-18295 18317 18319 18341 18352 18365-18367 18372-18373 18375 18381-18383 18396 18398 18401-18403 18412-18414 18416-18418 18495 18509-18511 18513-18515 18529-18531 18548 18552 18575 18579 18585-18587 18597-18599 18601-18603 18612-18614 18628 18632-18634 18653 18655 18677 18679 18683 18685-18687 18719 18744-18745 18747 18762 18765-18767 18769-18771 18796-18798 18808 18829-18831 18833-18835 18860-18862 18872-18873 18875 18886-18887 18889-18894 18906 18914 18916-18917 18920 18922-18923 18956 18958 18960 18976 18978 18989 18991 19021-19023 19025-19027 19041-19043 19052-19054 19061-19063 19068 19071 19080 19082-19083 19085-19087 19089-19091 19100-19102 19116-19118 19120-19122 19125 19127 19136-19138 19140-19141 19143-19144 19147 19149-19151 19164-19165 19167 19173-19175 19196-19197 19199 19204 19206 19213-19214 19216 19218-19222 19225-19228 19232-19233 19236 19238 19241-19242 19244 19264 19319 19322-19323 19334-19338 19347 19356 19358-19360 19362-19365 19367 19373-19377 19379 19397-19399 19420 19428-19430 19436 19438 19440 19472 19492-19494 19583 19645-19647 19661-19663 19665-19667 19681-19683 19700 19704 19725-19727 19729 19731 19747 19764 19768 19780 19784 19844 19848 19979 19985-19987 20012-20014 20016-20018 20036 20040 20096 21783 21839 21843 21959 21963 21988 21991 21997 21999 22351 22360-22361 22363 22384-22385 22396-22397 22399 22517 22519 22710-22711 22713-22715 22760 22762-22763 22875 23043 23064-23066 23076-23077 23080 23101-23104 23138 23150 23179 23185-23187 23196-23198 23201-23203 23212-23214 23216-23218 23224 23232-23234 25559 25575 25579 25581-25583 25821-25823 25837-25839 25841-25843 25885-25887 25901-25903 25905-25907 25922-25923 25985-25987 26135 26139 26141-26143 26155 26157-26159 26161-26163 26877-26879 26903 26909-26911 26933 26935 26945-26947 27015 27019 27021-27023 27025-27027 27197-27199 27213-27215 27233-27235 27278-27279 27281-27283 27297 27299 29973 30016 30029-30031 30044-30046 30064-30065 30067-30068 30973-30975 31138-31139 31148 31150 31286 31289-31291 31307 31309-31311 31313-31315 31329-31331 31340-31342 31344-31346 31351 31353-31355 31363 31488-31490 31548 31550-31551 31594 31598-31599 31611 31702 32104 32386-32387 32390-32392 32394-32395 32402-32403 32406-32407 32417-32419 32451 32471-32472 32474-32475 32477-32479 32492 32494-32495 32497-32499 32505-32507 32642 32650 32672 32674 32696 36607 36703 36715 36721-36723 36759 36761-36763 36771 36773-36775 36788-36790 36792-36794 36799 36812 36814 36816-36818 36832 36842 36846 36858-36859 36861-36863 40957 40959 45023 45039 45043 48983 49005 49007 49009-49011 49020-49022 49077-49079 49081 49091 49108 49112 49114 49119 49124-49125 49141 49147 49149-491512.381800341673347e-19 6.090060298487514e-19https://cdsarc.cds.unistra.fr/viz-bin/moc/J/A+A/648/A122?format=asciiOpticaldefaultJ/A+A/648/A122/catalogBinary morphology SDSS galaxies catalogRAJ2000Right ascension (J2000)degpos.eq.ra;meta.mainindexedrecnoRecord number assigned by the VizieR team. Should Not be used for identification.meta.recordintobjIDLong object SDSS identification, which is a bit-encoded integer of run, rerun, camcol, field, objectmeta.id;meta.mainDEJ2000Declination (J2000)degpos.eq.dec;meta.mainindexedumagModel magnitude in u-band taken from SDSS (modelMag_u)magphot.mag;em.opt.UdoublegmagModel magnitude in g-band taken from SDSS (modelMag_g)magphot.mag;em.opt.BdoublermagModel magnitude in r-band taken from SDSS (modelMag_r)magphot.mag;em.opt.RdoubleimagModel magnitude in i-band taken from SDSS (modelMag_i)magphot.mag;em.opt.IdoublezmagModel magnitude in z-band taken from SDSS (modelMag_z)magphot.mag;em.opt.IdoubleExtuGalactic extinction in u-band taken from SDSS (Extinction_u)magphys.absorptiondoubleExtgGalactic extinction in g-band taken from SDSS (Extinction_g)magphys.absorptiondoubleExtrGalactic extinction in r-band taken from SDSS (Extinction_r)magphys.absorptiondoubleExtiGalactic extinction in i-band taken from SDSS (Extinction_i)magphys.absorptiondoubleExtzGalactic extinction in z-band taken from SDSS (Extinction_z)magphys.absorptiondoubleR50Radius containing 50% of the Petrosian flux for r-band from SDSS (petroR50_r)arcsecphys.angSize;srcdoubleR90Radius containing 90% of the Petrosian flux for r-band from SDSS (petroR90_r)arcsecphys.angSize;srcdoubleR50/R90Inverse concentration index (petroR50_r/petroR90_r)phys.size;arith.ratiodoublezRedshift from SDSS (z)src.redshiftdoubleDLLuminosity distance (DL) (1)Mpcpos.distancedoubleuMAGAbsolute stellar magnitude calculated for u-band: umag-5*log10(DL)-25-Extu-kcoru (Mu)magphys.magAbs;meta.modelleddoublegMAGAbsolute stellar magnitude calculated for g-band: gmag-5*log10(DL)-25-Extg-kcorg (Mg)magphys.magAbs;meta.modelleddoublerMAGAbsolute stellar magnitude calculated for r-band: rmag-5*log10(DL)-25-Extr-kcorr (Mr)magphys.magAbs;meta.modelleddoubleiMAGAbsolute stellar magnitude calculated for i-band: imag-5*log10(DL)-25-Exti-kcori (Mi)magphys.magAbs;meta.modelleddoublezMAGAbsolute stellar magnitude calculated for z-band: zmag-5*log10(DL)-25-Extz-kcorz (Mz)magphys.magAbs;meta.modelleddoubleu-rColor indices calculated in u-r bands: umag-rmag-(Extu-Extr)-(kcoru-kcorr) (Mu-Mr)magphot.color;em.opt.U;em.opt.Rdoubleg-iColor indices calculated in g-i bands: gmag-imag-(Extg-Exti)-(kcorg-kcori) (Mg-Mi)magphot.color;em.opt;em.optdoubler-zColor indices calculated in r-z bands: rmag-zmag-(Extr-Extz)-(kcorr-kcorz) (Mr-Mz)magphot.color;em.opt;em.optdoubleKcorgK-correction in g-band (kcorrect_g) (2)magarith.factor;phot.magdoubleKcoriK-correction in i-band (kcorrect_i) (2)magarith.factor;phot.magdoubleKcorrK-correction in r-band (kcorrect_r) (2)magarith.factor;phot.magdoubleKcoruK-correction in u-band (kcorrect_u) (2)magarith.factor;phot.magdoubleKcorzK-correction in z-band (kcorrect_z) (2)magarith.factor;phot.magdoubleSVMPython[0/1] Morphological type of the galaxy determined by Support Vector Machine method (SVM_Python) (3)meta.codeintRFPython[0/1] Morphological type determined by Random Forest method (RF_Python) (3)meta.codeintSloanDisplay the SDSS data for this objectmeta.ref.urlchar