Identification of tidal features in deep optical galaxy images with Convolutional Neural Networks

Abstract

Interactions between galaxies leave distinguishable imprints in the form of tidal features which hold important clues about their mass assembly. Unfortunately, these structures are difficult to detect because they are low surface brightness features so deep observations are needed. Upcoming surveys promise several orders of magnitude increase in depth and sky coverage, for which automated methods for tidal feature detection will become mandatory. We test the ability of a convolutional neural network to reproduce human visual classifications for tidal detections. We use as training $\sim$6000 simulated images classified by professional astronomers. The mock Hyper Suprime Cam Subaru (HSC) images include variations with redshift, projection angle and surface brightness (${\mu }_{lim}$ =26-35 mag arcsec${}^{-2}$). We obtain satisfactory results with accuracy, precision and recall values of Acc=0.84, P=0.72 and R=0.85, respectively, for the test sample. While the accuracy and precision values are roughly constant for all surface brightness, the recall (completeness) is significantly affected by image depth. The recovery rate shows strong dependence on the type of tidal features: we recover all the images showing shell features and 87% of the tidal streams; these fractions are below 75% for mergers, tidal tails and bridges. When applied to real HSC images, the performance of the model worsens significantly. We speculate that this is due to the lack of realism of the simulations and take it as a warning on applying deep learning models to different data domains without prior testing on the actual data.

13 pages, 10 figures, accepted for publication in MNRAS

References in corpus (27)

• Dust Masses, PAH Abundances, and Starlight Intensities in the SINGS Galaxy Sample
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Tracing Galaxy Formation with Stellar Halos II: Relating Substructure in Phase- and Abundance-Space to Accretion Histories
• The Atlas3D project -- XXIX. The new look of early-type galaxies and surrounding fields disclosed by extremely deep optical images
• The Burrell Schmidt Deep Virgo Survey: Tidal Debris, Galaxy Halos, and Diffuse Intracluster Light in the Virgo Cluster
• A chronicle of galaxy mass assembly in the EAGLE simulation
• The shape of the inner Milky Way halo from observations of the Pal 5 and GD-1 stellar streams
• Halo Mass and Assembly History Exposed in the Faint Outskirts: the Stellar and Dark Matter Haloes of Illustris Galaxies
• Deep learning predictions of galaxy merger stage and the importance of observational realism
• Discovery of a Giant Stellar Tidal Stream Around the Disk Galaxy NGC 4013
• Probing the merger history of red early-type galaxies with their faint stellar substructures
• On the lifetime of merger features of equal-mass disk mergers
• Convolutional neural network identification of galaxy post-mergers in UNIONS using IllustrisTNG
• Preparing for low surface brightness science with the Vera C. Rubin Observatory: characterisation of tidal features from mock images
• The Fornax Deep Survey with VST. VIII. Connecting the accretion history with the cluster density
• The buildup of the intracluster light of Abell 85 as seen by Subaru's Hyper Suprime-Cam
• Action-space clustering of tidal streams to infer the Galactic potential
• Major mergers are not significant drivers of star formation or morphological transformation around the epoch of peak cosmic star formation
• Galaxy Morphology Network: A Convolutional Neural Network Used to Study Morphology and Quenching in $\sim 100,000$ SDSS and $\sim 20,000$ CANDELS Galaxies
• Bulge plus disc and Sérsic decomposition catalogues for 16,908 galaxies in the SDSS Stripe 82 co-adds: A detailed study of the $ugriz$ structural measurements
• Characterization of Low Surface Brightness structures in annotated deep images
• Pushing automated morphological classifications to their limits with the Dark Energy Survey
• The limited role of galaxy mergers in driving stellar mass growth over cosmic time
• Galaxy interactions in IllustrisTNG-100, I: The power and limitations of visual identification
• Mapping Dark Matter with Extragalactic Stellar Streams: the Case of Centaurus A
• Towards robust determination of non-parametric morphologies in marginal astronomical data: resolving uncertainties with cosmological hydrodynamical simulations
• Massive Early-Type Galaxies in the HSC-SSP: Flux Fraction of Tidal Features and Merger Rates

Cited by in corpus (13)

• IllustrisTNG in the HSC-SSP: image data release and the major role of mini mergers as drivers of asymmetry and star formation
• The morphological mix of dwarf galaxies in the nearby Universe
• The SAMI Galaxy Survey: Using Tidal Streams and Shells to Trace the Dynamical Evolution of Massive Galaxies
• Galaxy merger challenge: A comparison study between machine learning-based detection methods
• Extragalactic Stellar Tidal Streams in the Dark Energy Survey
• Tidal features and disc thicknesses of edge-on galaxies in the SDSS Stripe 82
• Uncovering Tidal Treasures: Automated Classification of Faint Tidal Features in DECaLS Data
• Search for the edge-on galaxies using an artificial neural network
• STRRINGS: STReams in Residual Images of Nearby GalaxieS
• The Ly$\alpha$ and Continuum Origins Survey. III. Investigating the Link between Galaxy Morphology, Merger Properties and LyC Escape
• Modeling Tidal Streams and Tidal Tails around Galaxies Using Deep Wendelstein Imaging Data
• J-PAS: A Neural Network Approach to Single Stellar Population Characterization
• Tidal Structures Around Edge-On Galaxies in Deep Imaging Surveys