Machine learning technique for morphological classification of galaxies from the SDSS. III. Image-based inference of detailed features

Abstract

This paper follows series of our works on the applicability of various machine learning methods to the morphological galaxy classification (Vavilova et al., 2021, 2022). We exploited the sample of 315776 SDSS DR9 galaxies with absolute stellar magnitudes of -24m<Mr<-19.4m at 0.003<z<0.1 as a target data set for the CNN classifier based on the DenseNet-201. Because it is tightly overlapped with the Galaxy Zoo 2 (GZ2) sample, we use these annotated data as the training data set to classify galaxies into 34 detailed features. In the presence of a pronounced difference of visual parameters between galaxies from the GZ2 training data set and galaxies without known morphological parameters, we applied novel procedures, which allowed us for the first time to get rid of this difference for smaller and fainter SDSS galaxies. We describe in detail the adversarial validation technique as well as how we managed the optimal train-test split of galaxies from the training data set. We have also found optimal galaxy image transformations to increase the classifier generalization ability. It can be considered as another way to improve the human bias for those galaxy images that had a poor vote classification in the GZ project. Such an approach, likely auto-immunization, when the CNN classifier trained on very good images is able to retrain bad images from the same homogeneous sample, can be considered co-planar to other methods of combating the human bias. The accuracy of CNN classifier is in the range of 83.3-99.4 percent depending on 32 features. As a result, for the first time, we assigned the detailed morphological classification for more than 140K low-redshift galaxies, especially at the fainter end. We accentuate on the typical problem points of galaxy CNN image classification from the astronomical point of view. The catalogs will be available through the VizieR.

42 pages, 4 tables, 13 figures, 122 references

References in corpus (29)

• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Classifying Radio Galaxies with Convolutional Neural Network
• Galaxy Zoo: comparing the demographics of spiral arm number and a new method for correcting redshift bias
• Deep learning predictions of galaxy merger stage and the importance of observational realism
• Incidence of WISE-Selected Obscured AGNs in Major Mergers and Interactions from the SDSS
• Galaxy Zoo: Quantitative Visual Morphological Classifications for 48,000 galaxies from CANDELS
• Identifying Galaxy Mergers in Observations and Simulations with Deep Learning
• The Catalog of Edge-on Disk Galaxies from SDSS. Part I: the catalog and the Structural Parameters of Stellar Disks
• VDES J2325-5229 a z=2.7 gravitationally lensed quasar discovered using morphology independent supervised machine learning
• Data Mining for Gravitationally Lensed Quasars
• Improved $\gamma$/hadron separation for the detection of faint gamma-ray sources using boosted decision trees
• Atlas and Catalog of Collisional Ring Galaxies
• Galaxy Morphology Network: A Convolutional Neural Network Used to Study Morphology and Quenching in $\sim 100,000$ SDSS and $\sim 20,000$ CANDELS Galaxies
• Pushing automated morphological classifications to their limits with the Dark Energy Survey
• Fanaroff-Riley classification of radio galaxies using group-equivariant convolutional neural networks
• Evaluating the optical classification of Fermi BCUs using machine learning
• An environmental dependence of the physical and structural properties in the Hydra Cluster galaxies
• North Ecliptic Pole merging galaxy catalogue
• Cosmic voids detection without density measurements
• Galaxy And Mass Assembly: Automatic Morphological Classification of Galaxies Using Statistical Learning
• New exocomets of $\beta$ Pic
• The Vanishing & Appearing Sources during a Century of Observations project: I. USNO objects missing in modern sky surveys and follow-up observations of a "missing star"
• Towards an Understanding of the Massive Red Spiral Galaxy Formation
• A Bayesian Framework for Cosmic String Searches in CMB Maps
• A method of immediate detection of objects with a near-zero apparent motion in series of CCD-frames
• Deep Learning in Searching the Spectroscopic Redshift of Quasars
• The luminosity function of ringed galaxies
• Applications of Machine-Learning Algorithms for Infrared Colour Selection of Galactic Wolf-Rayet Stars
• Automatic identification of outliers in Hubble Space Telescope galaxy images

Cited by in corpus (3)

• FNet II: Spectral Classification of Quasars, Galaxies, Stars, and broad absorption line (BAL) Quasars
• Visual inspection of potential exocomet transits identified through machine learning and statistical methods
• Milky Way galaxy-analogs and isolated galaxies with bars: environmental density in the Local Volume