J/A+A/688/A34ivo://CDS.VizieR/J/A+A/688/A34doi:10.26093/cds/vizier.36880034CDSGrespan M.Thuruthipilly H.Pollo A.Lochner M.Biesiada M.Etsebeth V.2024-11-29T20:05:01Z2024-08-02T09:21:17ZCDS support team

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

cds-question@unistra.frgravitational-lensingredshiftedWe applied a state-of-the-art transformer algorithm to the 221deg^2^ of the Kilo Degree Survey (KiDS) to search for new strong gravitational lenses (SGLs). We tested four transformer encoders trained on simulated data from the Strong Lens Finding Challenge on KiDS data. The best performing model was fine-tuned on real images of SGL candidates identified in previous searches. To expand the dataset for fine-tuning, data augmentation techniques were employed, including rotation, flipping, transposition, and white noise injection. The network fine-tuned with rotated, flipped, and transposed images exhibited the best performance and was used to hunt for SGLs in the overlapping region of the Galaxy And Mass Assembly (GAMA) and KiDS surveys on galaxies up to z=0.8. Candidate SGLs were matched with those from other surveys and examined using GAMA data to identify blended spectra resulting from the signal from multiple objects in a GAMA fiber. Fine-tuning the transformer encoder to the KiDS data reduced the number of false positives by 70%. Additionally, applying the fine-tuned model to a sample of ~5000000 galaxies resulted in a list of ~51000 SGL candidates. Upon visual inspection, this list was narrowed down to 231 candidates. Combined with the SGL candidates identified in the model testing, our final sample comprises 264 candidates, including 71 high-confidence SGLs; of these 71, 44 are new discoveries. We propose fine-tuning via real augmented images as a viable approach to mitigating false positives when transitioning from simulated lenses to real surveys. While our model shows improvement, it still does not achieve the same accuracy as previously proposed models trained directly on galaxy images from KiDS with added simulated lensing arcs. This suggests that a larger fine- tuning set is necessary for a competitive performance. Additionally, we provide a list of 121 false positives that exhibit features similar to lensed objects, which can be used in the training of future machine learning models in this field.2024A&A...688A..34Ghttps://cdsarc.cds.unistra.fr/viz-bin/cat/J/A+A/688/A34CatalogResearchIsServedByTAP VizieR generic serviceIsServedByConesearch servicerelated-toII/344 : KiDS-ESO-DR2 multi-band source catalog (de Jong+, 2015)II/347 : KiDS-ESO-DR3 multi-band source catalog (de Jong+, 2017)https://kids.strw.leidenuniv.nl/DR4 : KiDS DR4 Home Pagehttps://cds.unistra.fr/vizier-org/licences_vizier.htmlhttps://vizier.cds.unistra.fr/viz-bin/VizieR-2?-source=J/A+A/688/A34https://vizier.iucaa.in/viz-bin/VizieR-2?-source=J/A+A/688/A34http://vizieridia.saao.ac.za/viz-bin/VizieR-2?-source=J/A+A/688/A34https://vizier.cds.unistra.fr/viz-bin/votable?-source=J/A+A/688/A34https://vizier.iucaa.in/viz-bin/votable?-source=J/A+A/688/A34http://vizieridia.saao.ac.za/viz-bin/votable?-source=J/A+A/688/A34GETtext/xml+votablehttps://tapvizier.cds.unistra.fr/TAPVizieR/tapCone search capability for table J/A+A/688/A34/tablea1 (List of the strong lenses, grade 1)https://vizier.cds.unistra.fr/viz-bin/conesearch/J/A+A/688/A34/tablea1?https://vizier.iucaa.in/viz-bin/conesearch/J/A+A/688/A34/tablea1?http://vizieridia.saao.ac.za/viz-bin/conesearch/J/A+A/688/A34/tablea1?GETtext/xml+votable180.050000true359.5499-28.4880.005555555555555556Cone search capability for table J/A+A/688/A34/tablec1 (List of the strong lenses, grade 2)https://vizier.cds.unistra.fr/viz-bin/conesearch/J/A+A/688/A34/tablec1?https://vizier.iucaa.in/viz-bin/conesearch/J/A+A/688/A34/tablec1?http://vizieridia.saao.ac.za/viz-bin/conesearch/J/A+A/688/A34/tablec1?GETtext/xml+votable180.050000true0.104-28.09090.005555555555555556Cone search capability for table J/A+A/688/A34/table6 (Machine learning candidates)https://vizier.cds.unistra.fr/viz-bin/conesearch/J/A+A/688/A34/table6?https://vizier.iucaa.in/viz-bin/conesearch/J/A+A/688/A34/table6?http://vizieridia.saao.ac.za/viz-bin/conesearch/J/A+A/688/A34/table6?GETtext/xml+votable180.050000true212.90961.05750.0055555555555555564/1365 1622 1642 1685 1706 2911 2932 5/1024-1026 4138 5469 6397-6399 6479 6483-6484 6486-6487 6492-6494 6501 6512-6514 6562 6737 6830 6912 10239 11643 11719 11732-11734 11736-11737 6/4108 4112 4128 8200 8202-8203 8224 16544 16546-16547 16556 16896 21829-21831 21836-21837 21839 21872-21873 21875 21881 21884 25567 25583 25587 25909-25911 25913-25915 25925-25927 25929-25931 25940 25942-25943 25980 26001 26003 26012-26013 26015 26060 26064 26080 26243 26246 26252 26254-26255 26288 26290-26291 26296-26298 26947 26953 26956-26957 26959 26992-26993 26995-26998 27273-27276 27278-27279 27312 27314-27315 27318 27324 27652-27654 27656-27658 40949-40951 40953-40955 45050-45051 46555 46558-46559 46567 46571 46871 46875 46900-46901 46903 46909 46940 46952-46953 46955-46956 46960https://cdsarc.cds.unistra.fr/viz-bin/moc/J/A+A/688/A34?format=asciidefaultJ/A+A/688/A34/tablea1List of the strong lenses, grade 1recnoRecord number assigned by the VizieR team. Should Not be used for identification.meta.recordintID[0/70] Object Identifier in the publicationmeta.idintKiDSTilePointing in AW convention in which the object has been observed in KiDS DR4obs.fieldcharKiDSIDObject ID (JHHMMSS.sss+DDMMSS.ss, ICR coordinates)meta.id;meta.maincharRAJ2000Centroid sky position right ascension (J2000)degpos.eq.ra;meta.mainDEJ2000Centroid sky position declination (J2000)degpos.eq.dec;meta.mainzphotBPZ photometric redshift estimation from BPZ code from KiDS DR4src.redshiftfloatzspec? AUTOZ spectroscopic redshift estimate of the blended spectra of the first correlation peak from GAMA DR4 (AATSpecAutozAllv27_DR4 catalog)src.redshiftfloatnullablezspec2? AUTOZ spectroscopic redshift estimate of the blended spectra from GAMA DR4 of the second correlation peak (AATSpecAutozAllv27_DR4 catalog)src.redshift;pos.heliocentricfloatnullabletestIdentifier of the paper section in which the candidate has been detectedmeta.codecharCrosscheckAdditional comments on previous detections of the objectmeta.notecharJ/A+A/688/A34/tablec1List of the strong lenses, grade 2recnoRecord number assigned by the VizieR team. Should Not be used for identification.meta.recordintID[0/192] Object Identifier in the publicationmeta.idintKiDSIDObject ID (JHHMMSS.sss+DDMMSS.ss, ICR coordinates)meta.id;meta.maincharRAJ2000Centroid sky position right ascension (J2000)degpos.eq.ra;meta.mainDEJ2000Centroid sky position declination (J2000)degpos.eq.dec;meta.mainzphotBPZ photometric redshift estimation from BPZ code from KiDS DR4src.redshiftfloattestIdentifier of the paper section in which the candidate has been detectedmeta.codecharJ/A+A/688/A34/table6Machine learning candidatesrecnoRecord number assigned by the VizieR team. Should Not be used for identification.meta.recordintID[0/51626] Object Identifier in the publicationmeta.idintKiDSTilePointing in AW convention in which the object has been observed in KiDS DR4obs.fieldcharKiDSIDObject ID (JHHMMSS.sss+DDMMSS.ss, ICR coordinates)meta.id;meta.maincharRAJ2000Centroid sky position right ascension (J2000)degpos.eq.ra;meta.mainindexedDEJ2000Centroid sky position declination (J2000)degpos.eq.dec;meta.mainindexedzphotBPZ photometric redshift estimation from BPZ code from KiDS DR4src.redshiftfloatGrade[0/3] Object grade after visual inspection (1)meta.codefloatProbPredicition probability given by the modelstat.probability;meta.modelledfloat