upjs_gaia_eb.claivo://astro.upjs/upjs_gaia_eb/q/classification_rawUPJŠ DC TeamParimucha, Š., Gabdeev, M., Vaňko, M., Markus, Y., Vozyakova, O.GAIA Collaboration2026-10-25T20:10:13ZUPJŠ Archive

Jesenná 5, 040 01 Košice, Slovakia

olga.vozyakova@student.upjs.sklight-curvesvariable-starstime-domain-astronomyeclipsing-binary-starssemi-detached-binary-starsstarspotsstellar-classification This resource provides the results of a morphological classification of 2,184,283 eclipsing binary candidates from the Gaia DR3 catalogue. The systems are classified into EA/EB and EW types, followed by the identification of starspot signatures within both morphological classes. The classification was performed using a hierarchical computer-vision pipeline based on a fine-tuned ResNet-18 convolutional neural network trained on synthetic light curves generated with the ELISa code. The phase-folded Gaia G-band light curves are represented as 3-channel 128×128 pixel images encoding the flux distribution, its polar transformation, and the flux gradient. A tailored augmentation scheme calibrated to the Gaia cadence distribution was applied to reduce the synthetic-to-real domain gap (in prep). Because the morphological classification is based on single-passband Gaia G photometry alone, EW and ellipsoidal systems cannot be reliably distinguished. Therefore, systems with orbital periods P > 3 d initially classified as EW are explicitly reassigned as "ellipsoidal", since such long-period EW-type systems are physically unlikely for main-sequence stars.Parimucha, S. and all, in prep.https://skvo.science.upjs.sk/tableinfo/upjs_gaia_eb.classification_rawCatalogResearchGaia0/0-111.986445857e-19 6.112141099e-19Opticalupjs_gaia_eb This resource provides the results of a morphological classification of 2,184,283 eclipsing binary candidates from the Gaia DR3 catalogue. The systems are classified into EA/EB and EW types, followed by the identification of starspot signatures within both morphological classes. The classification was performed using a hierarchical computer-vision pipeline based on a fine-tuned ResNet-18 convolutional neural network trained on synthetic light curves generated with the ELISa code. The phase-folded Gaia G-band light curves are represented as 3-channel 128×128 pixel images encoding the flux distribution, its polar transformation, and the flux gradient. A tailored augmentation scheme calibrated to the Gaia cadence distribution was applied to reduce the synthetic-to-real domain gap (in prep). Because the morphological classification is based on single-passband Gaia G photometry alone, EW and ellipsoidal systems cannot be reliably distinguished. Therefore, systems with orbital periods P > 3 d initially classified as EW are explicitly reassigned as "ellipsoidal", since such long-period EW-type systems are physically unlikely for main-sequence stars.upjs_gaia_eb.classification_raw This resource provides the results of a morphological classification of 2,184,283 eclipsing binary candidates from the Gaia DR3 catalogue. The systems are classified into EA/EB and EW types, followed by the identification of starspot signatures within both morphological classes. The classification was performed using a hierarchical computer-vision pipeline based on a fine-tuned ResNet-18 convolutional neural network trained on synthetic light curves generated with the ELISa code. The phase-folded Gaia G-band light curves are represented as 3-channel 128×128 pixel images encoding the flux distribution, its polar transformation, and the flux gradient. A tailored augmentation scheme calibrated to the Gaia cadence distribution was applied to reduce the synthetic-to-real domain gap (in prep). Because the morphological classification is based on single-passband Gaia G photometry alone, EW and ellipsoidal systems cannot be reliably distinguished. Therefore, systems with orbital periods P > 3 d initially classified as EW are explicitly reassigned as "ellipsoidal", since such long-period EW-type systems are physically unlikely for main-sequence stars.2200000source_idGaia DR3 identifiermeta.id;meta.mainlongindexedprimaryperiodPeriod of the variable star calcukated from Gaia DR3 frequencydsrc.var;time.perioddoubleteffEffective temperature from Gaia DR3 GSP-Phot Aeneas best library using BP/RP spectraKphys.temperature.effectivefloatnullablemain_classEA/EB, EW or Ellispsoidalmeta.code.classcharprob_ea_ebProbability of classification as EA/EBmeta.code.class;stat.probabilityfloatprob_ewProbability of classification as EWmeta.code.class;stat.probabilityfloatspot_classPresence of spotsmeta.code.classcharprob_spotProbability of classification as spottedmeta.code.class;stat.probabilityfloat