Galaxy Zoo: Probabilistic Morphology through Bayesian CNNs and Active Learning

Abstract

We use Bayesian convolutional neural networks and a novel generative model of Galaxy Zoo volunteer responses to infer posteriors for the visual morphology of galaxies. Bayesian CNN can learn from galaxy images with uncertain labels and then, for previously unlabelled galaxies, predict the probability of each possible label. Our posteriors are well-calibrated (e.g. for predicting bars, we achieve coverage errors of 11.8% within a vote fraction deviation of 0.2) and hence are reliable for practical use. Further, using our posteriors, we apply the active learning strategy BALD to request volunteer responses for the subset of galaxies which, if labelled, would be most informative for training our network. We show that training our Bayesian CNNs using active learning requires up to 35-60% fewer labelled galaxies, depending on the morphological feature being classified. By combining human and machine intelligence, Galaxy Zoo will be able to classify surveys of any conceivable scale on a timescale of weeks, providing massive and detailed morphology catalogues to support research into galaxy evolution.

Accepted by MNRAS. 21 pages, including appendices

References in corpus (62)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Scikit-learn: Machine Learning in Python
• The electronic properties of graphene
• Astropy: A Community Python Package for Astronomy
• The Astropy Project: Building an inclusive, open-science project and status of the v2.0 core package
• scikit-image: Image processing in Python
• The Seventh Data Release of the Sloan Digital Sky Survey
• Nine-Year Wilkinson Microwave Anisotropy Probe (WMAP) Observations: Cosmological Parameter Results
• Spectroscopic Target Selection in the Sloan Digital Sky Survey: The Main Galaxy Sample
• Overview of the DESI Legacy Imaging Surveys
• Galaxy Zoo : Morphologies derived from visual inspection of galaxies from the Sloan Digital Sky Survey
• Going Deeper with Convolutions
• The Hyper Suprime-Cam SSP Survey: Overview and Survey Design
• LSST Science Book, Version 2.0
• The Relationship Between Stellar Light Distributions of Galaxies and their Formation Histories
• A New Non-Parametric Approach to Galaxy Morphological Classification
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
• Galaxy Zoo 2: detailed morphological classifications for 304,122 galaxies from the Sloan Digital Sky Survey
• A survey of active learning algorithms for supervised remote sensing image classification
• The Thirteenth Data Release of the Sloan Digital Sky Survey: First Spectroscopic Data from the SDSS-IV Survey MApping Nearby Galaxies at Apache Point Observatory
• Bayesian Active Learning for Classification and Preference Learning
• A Catalog of Detailed Visual Morphological Classifications for 14034 Galaxies in the Sloan Digital Sky Survey
• Improving galaxy morphologies for SDSS with Deep Learning
• The first and second data releases of the Kilo-Degree Survey
• A catalog of visual-like morphologies in the 5 CANDELS fields using deep-learning
• Search for invisible decays of a Higgs boson produced through vector boson fusion in proton-proton collisions at $\sqrt{s}=$ 13 TeV
• Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
• Star-galaxy Classification Using Deep Convolutional Neural Networks
• GAMA/G10-COSMOS/3D-HST: The 0<z<5 cosmic star-formation history, stellar- and dust-mass densities
• Revisiting the Hubble sequence in the SDSS DR7 spectroscopic sample: a publicly available bayesian automated classification
• Galaxy Zoo: Reproducing Galaxy Morphologies Via Machine Learning
• CMU DeepLens: Deep Learning For Automatic Image-based Galaxy-Galaxy Strong Lens Finding
• Fast Radio Burst 121102 Pulse Detection and Periodicity: A Machine Learning Approach
• Galaxy Zoo and ALFALFA: Atomic Gas and the Regulation of Star Formation in Barred Disc Galaxies
• The EFIGI catalogue of 4458 nearby galaxies with detailed morphology
• Using transfer learning to detect galaxy mergers
• Galaxy Zoo: comparing the demographics of spiral arm number and a new method for correcting redshift bias
• Space Warps: I. Crowd-sourcing the Discovery of Gravitational Lenses
• Galaxy Zoo: Secular evolution of barred galaxies from structural decomposition of multi-band images
• SDSS-IV MaNGA PyMorph Photometric and Deep Learning Morphological Catalogs and implications for bulge properties and stellar angular momentum
• Transfer learning for galaxy morphology from one survey to another
• An automatic taxonomy of galaxy morphology using unsupervised machine learning
• New Image Statistics for Detecting Disturbed Galaxy Morphologies at High Redshift
• 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
• Galaxy Zoo: the effect of bar-driven fueling on the presence of an active galactic nucleus in disc galaxies
• The Imprint of Reionization on the Star Formation Histories of Dwarf Galaxies
• Optimizing spectroscopic follow-up strategies for supernova photometric classification with active learning
• Identification of Low Surface Brightness Tidal Features in Galaxies Using Convolutional Neural Networks
• Active Learning to Overcome Sample Selection Bias: Application to Photometric Variable Star Classification
• Integrating human and machine intelligence in galaxy morphology classification tasks
• Beyond Spheroids and Discs: Classifications of CANDELS Galaxy Structure at 1.4 < z < 2 via Principal Component Analysis
• A transient search using combined human and machine classifications
• Deep Learning at Scale for the Construction of Galaxy Catalogs in the Dark Energy Survey
• Loss-Calibrated Approximate Inference in Bayesian Neural Networks
• Galaxy Zoo: Finding offset discs and bars in SDSS galaxies
• Multiband galaxy morphologies for CLASH: a convolutional neural network transferred from CANDELS
• The Effect of Minor and Major Mergers on the Evolution of Low Excitation Radio Galaxies
• An Active Instance-based Machine Learning method for Stellar Population Studies
• Labeling Bias in Galaxy Morphologies
• Tuning target selection algorithms to improve galaxy redshift estimates

Cited by in corpus (74)

• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• Galaxy Zoo DECaLS: Detailed Visual Morphology Measurements from Volunteers and Deep Learning for 314,000 Galaxies
• Fink, a new generation of broker for the LSST community
• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• Morpheus: A Deep Learning Framework For Pixel-Level Analysis of Astronomical Image Data
• Self-Supervised Representation Learning for Astronomical Images
• Astronomaly: Personalised Active Anomaly Detection in Astronomical Data
• Practical Galaxy Morphology Tools from Deep Supervised Representation Learning
• Galaxy Morphological Classification Catalogue of the Dark Energy Survey Year 3 data with Convolutional Neural Networks
• Mining for Strong Gravitational Lenses with Self-supervised Learning
• YSE-PZ: A Transient Survey Management Platform that Empowers the Human-in-the-Loop
• AstroVaDEr: Astronomical Variational Deep Embedder for Unsupervised Morphological Classification of Galaxies and Synthetic Image Generation
• Active Anomaly Detection for time-domain discoveries
• A review of unsupervised learning in astronomy
• Pushing automated morphological classifications to their limits with the Dark Energy Survey
• Fanaroff-Riley classification of radio galaxies using group-equivariant convolutional neural networks
• Transient-optimised real-bogus classification with Bayesian Convolutional Neural Networks -- sifting the GOTO candidate stream
• Learning Uncertainty with Artificial Neural Networks for Improved Predictive Process Monitoring
• Hubble Asteroid Hunter: II. Identifying strong gravitational lenses in HST images with crowdsourcing
• Fink: early supernovae Ia classification using active learning
• The evolution of barred galaxies in the EAGLE simulations
• Gravity Spy: Lessons Learned and a Path Forward
• A Morphological Classification of 18190 Molecular Clouds Identified in ${}^{12}$CO Data from the MWISP Survey
• Explaining deep learning of galaxy morphology with saliency mapping
• Galaxy classification: a deep learning approach for classifying Sloan Digital Sky Survey images
• Hubble Asteroid Hunter: I. Identifying asteroid trails in Hubble Space Telescope images
• Automatic detection of low surface brightness galaxies from SDSS images
• Deep learning with photosensor timing information as a background rejection method for the Cherenkov Telescope Array
• Galaxy classification: deep learning on the OTELO and COSMOS databases
• Variational Inference as an alternative to MCMC for parameter estimation and model selection
• Comparison of Observed Galaxy Properties with Semianalytic Model Predictions using Machine Learning
• Wat zei je? Detecting Out-of-Distribution Translations with Variational Transformers
• Photometric identification of compact galaxies, stars and quasars using multiple neural networks
• Galaxy morphoto-Z with neural Networks (GaZNets). I. Optimized accuracy and outlier fraction from Imaging and Photometry
• Astronomaly at scale: searching for anomalies amongst 4 million galaxies
• Galaxy merger challenge: A comparison study between machine learning-based detection methods
• Deep-CEE I: Fishing for Galaxy Clusters with Deep Neural Nets
• Deep Learning Assessment of galaxy morphology in S-PLUS DataRelease 1
• Morphological Classification of Radio Galaxies with wGAN-supported Augmentation
• Radio source-component association for the LOFAR Two-metre Sky Survey with region-based convolutional neural networks
• Morphological Parameters and Associated Uncertainties for 8 Million Galaxies in the Hyper Suprime-Cam Wide Survey
• GaMPEN: A Machine Learning Framework for Estimating Bayesian Posteriors of Galaxy Morphological Parameters
• A Bayesian Approach to Strong Lens Finding in the Era of Wide-area Surveys
• Lessons Learned from the Two Largest Galaxy Morphological Classification Catalogues built by Convolutional Neural Networks
• Finding AGN remnant candidates based on radio morphology with machine learning
• A Comparison of Deep Learning Architectures for Optical Galaxy Morphology Classification
• Merger identification through photometric bands, colours, and their errors
• Uncovering Tidal Treasures: Automated Classification of Faint Tidal Features in DECaLS Data
• Machine learning technique for morphological classification of galaxies from the SDSS. III. Image-based inference of detailed features
• Machine learning technique for morphological classification of galaxies from SDSS. II. The image-based morphological catalogs of galaxies at 0.02<z<0.1
• DeepGalaxy: Deducing the Properties of Galaxy Mergers from Images Using Deep Neural Networks
• CzSL: Learning from citizen science, experts and unlabelled data in astronomical image classification
• Galaxy Zoo JWST: Up to 75% of discs are featureless at $3<z<7$
• Identification of single spectral lines in large spectroscopic surveys using UMLAUT: an Unsupervised Machine Learning Algorithm based on Unbiased Topology
• Finding radio transients with anomaly detection and active learning based on volunteer classifications
• Image feature extraction and galaxy classification: a novel and efficient approach with automated machine learning
• AstronomicAL: An interactive dashboard for visualisation, integration and classification of data using Active Learning
• The Ly$\alpha$ and Continuum Origins Survey. III. Investigating the Link between Galaxy Morphology, Merger Properties and LyC Escape
• Using Machine Learning to Determine Morphologies of $z<1$ AGN Host Galaxies in the Hyper Suprime-Cam Wide Survey
• Identification of ram pressure stripping features in galaxies using citizen science
• Bayesian and Convolutional Networks for Hierarchical Morphological Classification of Galaxies
• A self-supervised, physics-aware, Bayesian neural network architecture for modelling galaxy emission-line kinematics
• Planet Four: A Neural Network's Search For Polar Spring-time Fans On Mars
• AGN -- host galaxy photometric decomposition using a fast, accurate and precise deep learning approach
• Automated galaxy sizes in Euclid images using the Segment Anything Model
• Exploring the Universe with SNAD: Anomaly Detection in Astronomy
• Automatic Machine Learning Framework to Study Morphological Parameters of AGN Host Galaxies within $z<1.4$ in the Hyper Supreme-Cam Wide Survey
• The Next Generation Virgo Cluster Survey (NGVS). XL. The Morphological Classification of Virgo Cluster Galaxies
• BASS. XLIV. Morphological preferences of local hard X-ray selected AGN
• Semi-supervised Learning of Galaxy Morphology using Equivariant Transformer Variational Autoencoders
• Radio Galaxy Zoo: Giant Radio Galaxy Classification using Multi-Domain Deep Learning
• Exploring Late Stellar Evolution in the Era of Large Surveys: Machine Learning Prospects for Hot Subdwarfs and White Dwarfs
• Quantifying the Poor Purity and Completeness of Morphological Samples Selected by Galaxy Colour
• A Simulation Driven Deep Learning Approach for Separating Mergers and Star Forming Galaxies: The Formation Histories of Clumpy Galaxies in all the CANDELS Fields