Information on resource 'Morphological classification of eclipsing binaries from the Gaia'

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.

Services defined within this resource descriptor

Tables defined within this resource descriptor

[Manage RD]