Identifying Dust-lane Spheroidal Galaxies in DESI Legacy Imaging Surveys Using Semisupervised Methods

Abstract Dust-lane spheroidal galaxies (DLSGs) are unique astrophysical systems that exhibit the morphology of early-type galaxies (ETGs) but are distinguished by prominent dust lanes. Recent studies propose that they form through minor mergers between ETGs and gas-rich dwarf galaxies, offering a window into the interstellar medium (ISM) of ETGs and star formation triggered by small-scale interactions. However, their rarity poses a challenge for assembling large, statistically robust samples via manual selection. To overcome this limitation, we employ GC-SWGAN, a semisupervised learning method developed by Z. Luo et al., to systematically identify DLSGs within the DESI Legacy Imaging Surveys (DESI-LS). The methodology involves training a generative adversarial network on unlabeled galaxy images to extract morphological features, followed by fine-tuning the model using a small data set of labeled DLSGs. In our experiments, despite DLSGs constituting only ∼3.7% of the test set, GC-SWGAN achieves remarkable performance, with an 87% recall rate, 84% accuracy, and an F1 score of 86%, underscoring its efficacy for DLSG detection. By applying this model to ∼310,000 DESI-LS galaxies that meet the criteria m r < 17.0 and 0.01 < z < 0.07 we compile the largest catalog of DLSG candidates to date, identifying 9482 dust-lane ETGs. A preliminary analysis reveals that these DLSGs exhibit significantly redder g − r colors and higher specific star formation rates compared to non-DLSGs. This catalog enables future studies of ISM properties in ETGs and the role of minor mergers in driving star formation in the nearby Universe.