Morpheus: A Deep Learning Framework For Pixel-Level Analysis of Astronomical Image Data

Abstract

We present Morpheus, a new model for generating pixel-level morphological classifications of astronomical sources. Morpheus leverages advances in deep learning to perform source detection, source segmentation, and morphological classification pixel-by-pixel via a semantic segmentation algorithm adopted from the field of computer vision. By utilizing morphological information about the flux of real astronomical sources during object detection, Morpheus shows resiliency to false-positive identifications of sources. We evaluate Morpheus by performing source detection, source segmentation, morphological classification on the Hubble Space Telescope data in the five CANDELS fields with a focus on the GOODS South field, and demonstrate a high completeness in recovering known GOODS South 3D-HST sources with H < 26 AB. We release the code publicly, provide online demonstrations, and present an interactive visualization of the Morpheus results in GOODS South.

arXiv comment47 pages, 33 figures. Version accepted by ApJS. More information about Morpheus is available at https://morpheus-project.github.io/morpheus/

References in corpus (90)

• The NumPy array: a structure for efficient numerical computation
• scikit-image: Image processing in Python
• Binary companions of evolved stars in APOGEE DR14: Search method and catalog of ~5,000 companions
• LSST: from Science Drivers to Reference Design and Anticipated Data Products
• Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations
• The slope of the black-hole mass versus velocity dispersion correlation
• CANDELS: The Cosmic Assembly Near-infrared Deep Extragalactic Legacy Survey
• CANDELS: The Cosmic Assembly Near-infrared Deep Extragalactic Legacy Survey - The Hubble Space Telescope Observations, Imaging Data Products and Mosaics
• The James Webb Space Telescope
• Detailed Decomposition of Galaxy Images. II. Beyond Axisymmetric Models
• Galaxy Zoo : Morphologies derived from visual inspection of galaxies from the Sloan Digital Sky Survey
• 3D-HST+CANDELS: The Evolution of the Galaxy Size-Mass Distribution since $z=3$
• The size distribution of galaxies in the Sloan Digital Sky Survey
• The Hyper Suprime-Cam SSP Survey: Overview and Survey Design
• Evolution since z = 0.5 of the Morphology-Density relation for Clusters of Galaxies
• The Dark Energy Survey: more than dark energy - an overview
• 3D-HST WFC3-selected Photometric Catalogs in the Five CANDELS/3D-HST Fields: Photometry, Photometric Redshifts and Stellar Masses
• The Relationship Between Stellar Light Distributions of Galaxies and their Formation Histories
• A New Non-Parametric Approach to Galaxy Morphological Classification
• The Growth of Massive Galaxies Since z=2
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Galaxy Structure and Mode of Star Formation in the SFR-Mass Plane from z ~ 2.5 to z ~ 0.1
• The 3D-HST Survey: Hubble Space Telescope WFC3/G141 grism spectra, redshifts, and emission line measurements for $\sim 100,000$ galaxies
• Galaxy Zoo 2: detailed morphological classifications for 304,122 galaxies from the Sloan Digital Sky Survey
• First Data Release of the Hyper Suprime-Cam Subaru Strategic Program
• Structural Parameters of Galaxies in CANDELS
• CANDELS Multi-wavelength Catalogs: Source Detection and Photometry in the GOODS-South Field
• Galaxy morphology to I=25 mag in the Hubble Deep Field
• The size evolution of galaxies since z~3: combining SDSS, GEMS and FIRES
• The Spitzer Survey of Stellar Structure in Galaxies (S^4G)
• The Asymmetry of Galaxies: Physical Morphology for Nearby and High Redshift Galaxies
• The Evolution of Galaxy Mergers and Morphology at z<1.2 in the Extended Groth Strip
• Structure and star formation in galaxies out to z=3: evidence for surface density dependent evolution and upsizing
• Evolution of the Bar Fraction in COSMOS: Quantifying the Assembly of the Hubble Sequence
• CANDELS: Constraining the AGN-Merger Connection with Host Morphologies at z~2
• What turns galaxies off? The different morphologies of star-forming and quiescent galaxies since z~2 from CANDELS
• A catalog of visual-like morphologies in the 5 CANDELS fields using deep-learning
• Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
• HST and Spitzer imaging of red and blue galaxies at z~2.5: A correlation between size and star formation activity from compact quiescent galaxies to extended star forming galaxies
• The Luminosity, Stellar Mass, and Number Density Evolution of Field Galaxies of Known Morphology from z = 0.5 - 3
• Mapping the Galaxy Color-Redshift Relation: Optimal Photometric Redshift Calibration Strategies for Cosmology Surveys
• NICMOS Imaging of DRGs in the HDF-S: A Relation Between Star-Formation and Size at z ~ 2.5
• The DEEP3 Galaxy Redshift Survey: The Impact of Environment on the Size Evolution of Massive Early-type Galaxies at Intermediate Redshift
• Galaxy Morphologies in the Hubble Ultra Deep Field: Dominance of Linear Structures at the Detection Limit
• The JWST Extragalactic Mock Catalog: Modeling galaxy populations from the UV through the near-IR over thirteen billion years of cosmic history
• The Morphologies of Massive Galaxies at 1<z<3 in the CANDELS-UDS Field: Compact Bulges, and the Rise and Fall of Massive Disks
• Galaxy Zoo: Probabilistic Morphology through Bayesian CNNs and Active Learning
• Effect of local environment and stellar mass on galaxy quenching and morphology at $0.5<z<2.0$
• A Catalog of Morphological Types in 10 Distant Rich Clusters of Galaxies
• CANDELS Visual Classifications: Scheme, Data Release, and First Results
• The Luminosity-Size and Mass-Size Relations of Galaxies out to z~3
• Galaxy Structure as a Driver of the Star Formation Sequence Slope and Scatter
• Galaxy Zoo: CANDELS Barred Disks and Bar Fractions
• Galaxy Zoo: Quantitative Visual Morphological Classifications for 48,000 galaxies from CANDELS
• Mass assembly and morphological transformations since $z\sim 3$ from CANDELS
• The Hubble Sequence at $z\sim 0$ in the IllustrisTNG simulation with deep learning
• Transfer learning for galaxy morphology from one survey to another
• An automatic taxonomy of galaxy morphology using unsupervised machine learning
• Galaxy Zoo: Morphological Classifications for 120,000 Galaxies in HST Legacy Imaging
• Deep Learning Identifies High-z Galaxies in a Central Blue Nugget Phase in a Characteristic Mass Range
• Deep learning for galaxy surface brightness profile fitting
• The Size Evolution of Star-forming Galaxies Since z~7 Using ZFOURGE
• CANDELS: The correlation between galaxy morphology and star formation activity at z~2
• Tight Correlations Between Massive Galaxy Structural Properties and Dynamics: The Mass Fundamental Plane Was in Place by z~2
• A catalog of polychromatic bulge-disk decompositions of ~ 17.600 galaxies in CANDELS
• The evolution of galaxy shapes in CANDELS: from prolate to oblate
• Scientific Synergy Between LSST and Euclid
• Galaxy Zoo: the dependence of the star formation-stellar mass relation on spiral disk morphology
• The Morphological Evolution of Galaxies
• The Relation between Galaxy Structure and Spectral Type: Implications for the Buildup of the Quiescent Galaxy Population at 0.5<z<2.0
• Data-Driven Reconstruction of Gravitationally Lensed Galaxies using Recurrent Inference Machines
• Integrating human and machine intelligence in galaxy morphology classification tasks
• Major mergers are not significant drivers of star formation or morphological transformation around the epoch of peak cosmic star formation
• Data Mining for Gravitationally Lensed Quasars
• The evolution of galaxy size and morphology at z~0.5-3.0 in the GOODS-N region with HST/WFC3 data
• Photometry of high-redshift blended galaxies using deep learning
• Beyond Spheroids and Discs: Classifications of CANDELS Galaxy Structure at 1.4 < z < 2 via Principal Component Analysis
• The Structural Evolution of Milky Way-like Star Forming Galaxies since z~1.3
• The Formation of Bulges, Discs and Two Component Galaxies in the CANDELS Survey at z < 3
• Morphological Classification of Galaxies by Shapelet Decomposition in the Sloan Digital Sky Survey
• Morphology Dependence Of Stellar Age in Quenched Galaxies at Redshift ~ 1.2: Massive Compact Galaxies Are Older Than More Extended Ones
• Photometric Redshift Calibration Requirements for WFIRST Weak Lensing Cosmology: Predictions from CANDELS
• A New View of the Size-Mass Distribution of Galaxies: Using $r_{20}$ and $r_{80}$ instead of $r_{50}$
• Galaxy Zoo: major galaxy mergers are not a significant quenching pathway
• A catalogue of structural and morphological measurements for DES Y1
• Generative deep fields: arbitrarily sized, random synthetic astronomical images through deep learning
• The bulge-disk decomposition of AGN host galaxies
• Morphology and the Color-Mass Diagram as Clues to Galaxy Evolution at z~1
• Morphological Classification of Galaxies by Shapelet Decomposition in the Sloan Digital Sky Survey II: Multiwavelength Classification
• The Isophotal Structure of Star-forming Galaxies at $0.5<z<1.8$ in CANDELS: Implications for the Evolution of Galaxy Structure

Cited by in corpus (43)

• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• Morpheus Reveals Distant Disk Galaxy Morphologies with JWST: The First AI/ML Analysis of JWST Images
• Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy
• Galaxy Morphological Classification Catalogue of the Dark Energy Survey Year 3 data with Convolutional Neural Networks
• Automated galaxy-galaxy strong lens modelling: no lens left behind
• Pushing automated morphological classifications to their limits with the Dark Energy Survey
• Photometric selection and redshifts for quasars in the Kilo-Degree Survey Data Release 4
• Star formation characteristics of CNN-identified post-mergers in the Ultraviolet Near Infrared Optical Northern Survey (UNIONS)
• {\sc mirkwood:} Fast and Accurate SED Modeling Using Machine Learning
• Detection, Instance Segmentation, and Classification for Astronomical Surveys with Deep Learning (DeepDISC): Detectron2 Implementation and Demonstration with Hyper Suprime-Cam Data
• Detecting gravitational lenses using machine learning: exploring interpretability and sensitivity to rare lensing configurations
• Extracting the Subhalo Mass Function from Strong Lens Images with Image Segmentation
• Identification of tidal features in deep optical galaxy images with Convolutional Neural Networks
• AGN in post-mergers from the Ultraviolet Near Infrared Optical Northern Survey
• SILVERRUSH X: Machine Learning-Aided Selection of $9318$ LAEs at $z=2.2$, $3.3$, $4.9$, $5.7$, $6.6$, and $7.0$ from the HSC SSP and CHORUS Survey Data
• Supervised machine learning on Galactic filaments Revealing the filamentary structure of the Galactic interstellar medium
• The PAU survey: Estimating galaxy photometry with deep learning
• The nature of giant clumps in high-z discs: a deep-learning comparison of simulations and observations
• SCSS-Net: Solar Corona Structures Segmentation by Deep Learning
• Point Spread Function Estimation for Wide Field Small Aperture Telescopes with Deep Neural Networks and Calibration Data
• Deep Learning Assessment of galaxy morphology in S-PLUS DataRelease 1
• GaMPEN: A Machine Learning Framework for Estimating Bayesian Posteriors of Galaxy Morphological Parameters
• Photometric classification of HSC transients using machine learning
• Morphological Parameters and Associated Uncertainties for 8 Million Galaxies in the Hyper Suprime-Cam Wide Survey
• Study of star clusters in the M83 galaxy with a convolutional neural network
• The redshift evolution of the S0 fraction for $z<1$ in COSMOS
• Lessons Learned from the Two Largest Galaxy Morphological Classification Catalogues built by Convolutional Neural Networks
• Black Hole Weather Forecasting with Deep Learning: A Pilot Study
• Noise reduction on single-shot images using an autoencoder
• Segmentation of spectroscopic images of the low solar atmosphere by the Self Organizing Map technique
• Inferring redshift and galaxy properties via a multi-task neural net with probabilistic outputs: An application to simulated MOONS spectra
• The Three Hundred Project: Mapping The Matter Distribution in Galaxy Clusters Via Deep Learning from Multiview Simulated Observations
• Efficient Identification of Broad Absorption Line Quasars using Dimensionality Reduction and Machine Learning
• A morphological segmentation approach to determining bar lengths
• Identifying diffuse spatial structures in high-energy photon lists
• Galactic Component Mapping of Galaxy UGC 2885 by Machine Learning Classification
• Automatic Machine Learning Framework to Study Morphological Parameters of AGN Host Galaxies within $z<1.4$ in the Hyper Supreme-Cam Wide Survey
• Adaptive Weight Modified Riesz Mean Filter For High-Density Salt and Pepper Noise Removal
• Automated galaxy sizes in Euclid images using the Segment Anything Model
• The Next Generation Virgo Cluster Survey (NGVS). XL. The Morphological Classification of Virgo Cluster Galaxies
• Background Intensity Estimation for Cassini-ISS Image Using Deep Learning-Based Diffusion Model
• Machine learning application to Fermi-LAT data: sharpening all-sky map and emphasizing variable sources
• Can AI Dream of Unseen Galaxies? Conditional Diffusion Model for Galaxy Morphology Augmentation