AstroVaDEr: Astronomical Variational Deep Embedder for Unsupervised Morphological Classification of Galaxies and Synthetic Image Generation

Abstract

We present AstroVaDEr, a variational autoencoder designed to perform unsupervised clustering and synthetic image generation using astronomical imaging catalogues. The model is a convolutional neural network that learns to embed images into a low dimensional latent space, and simultaneously optimises a Gaussian Mixture Model (GMM) on the embedded vectors to cluster the training data. By utilising variational inference, we are able to use the learned GMM as a statistical prior on the latent space to facilitate random sampling and generation of synthetic images. We demonstrate AstroVaDEr's capabilities by training it on gray-scaled \textit{gri} images from the Sloan Digital Sky Survey, using a sample of galaxies that are classified by Galaxy Zoo 2. An unsupervised clustering model is found which separates galaxies based on learned morphological features such as axis ratio, surface brightness profile, orientation and the presence of companions. We use the learned mixture model to generate synthetic images of galaxies based on the morphological profiles of the Gaussian components. AstroVaDEr succeeds in producing a morphological classification scheme from unlabelled data, but unexpectedly places high importance on the presence of companion objects---demonstrating the importance of human interpretation. The network is scalable and flexible, allowing for larger datasets to be classified, or different kinds of imaging data. We also demonstrate the generative properties of the model, which allow for realistic synthetic images of galaxies to be sampled from the learned classification scheme. These can be used to create synthetic image catalogs or to perform image processing tasks such as deblending.

arXiv commentAccepted in MNRAS. 23 Pages, 16 Figures. GitHub: https://github.com/AshleySpindler/AstroVaDEr-Public

References in corpus (44)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Scikit-learn: Machine Learning in Python
• Deep Residual Learning for Image Recognition
• LSST: from Science Drivers to Reference Design and Anticipated Data Products
• Generative Adversarial Text to Image Synthesis
• Overview of the DESI Legacy Imaging Surveys
• The Hyper Suprime-Cam SSP Survey: Overview and Survey Design
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Galaxy Zoo 2: detailed morphological classifications for 304,122 galaxies from the Sloan Digital Sky Survey
• Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders
• A catalog of visual-like morphologies in the 5 CANDELS fields using deep-learning
• Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit
• CMU DeepLens: Deep Learning For Automatic Image-based Galaxy-Galaxy Strong Lens Finding
• Photometric redshift estimation via deep learning
• Galaxy Zoo: Probabilistic Morphology through Bayesian CNNs and Active Learning
• The Strong Gravitational Lens Finding Challenge
• Unsupervised Deep Embedding for Clustering Analysis
• LinKS: Discovering galaxy-scale strong lenses in the Kilo-Degree Survey using Convolutional Neural Networks
• From Variational to Deterministic Autoencoders
• Big Universe, Big Data: Machine Learning and Image Analysis for Astronomy
• Galaxies, Human Eyes and Artificial Neural Networks
• An automatic taxonomy of galaxy morphology using unsupervised machine learning
• Diagnosing and Enhancing VAE Models
• Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering
• The Ecological Impact of High-performance Computing in Astrophysics
• Galaxy morphological classification in deep-wide surveys via unsupervised machine learning
• Identifying Strong Lenses with Unsupervised Machine Learning using Convolutional Autoencoder
• Unsupervised self-organised mapping: a versatile empirical tool for object selection, classification and redshift estimation in large surveys
• New high-quality strong lens candidates with deep learning in the Kilo Degree Survey
• Radio Galaxy Zoo: Unsupervised Clustering of Convolutionally Auto-encoded Radio-astronomical Images
• Tackling Over-pruning in Variational Autoencoders
• Generative deep fields: arbitrarily sized, random synthetic astronomical images through deep learning
• Automated Lensing Learner: Automated Strong Lensing Identification with a Computer Vision Technique
• Eigengalaxies: describing galaxy morphology using principal components in image space
• Classification of pulsars with Dirichlet process Gaussian mixture model
• Sparsity in Variational Autoencoders
• The VIMOS Public Extragalactic Redshift Survey (VIPERS). Unsupervised classification with photometric redshifts: a method to accurately classify large galaxy samples without spectroscopic information
• Learning Global and Local Features of Normal Brain Anatomy for Unsupervised Abnormality Detection
• Balancing reconstruction error and Kullback-Leibler divergence in Variational Autoencoders
• Simple, Scalable, and Stable Variational Deep Clustering
• Unsupervised Star Galaxy Classification with Cascade Variational Auto-Encoder
• Variational Clustering: Leveraging Variational Autoencoders for Image Clustering
• Deep Clustering for Mars Rover image datasets

Cited by in corpus (31)

• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• Self-Supervised Representation Learning for Astronomical Images
• Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy
• Practical Galaxy Morphology Tools from Deep Supervised Representation Learning
• Characterization of Low Surface Brightness structures in annotated deep images
• Realistic galaxy image simulation via score-based generative models
• A review of unsupervised learning in astronomy
• Galaxy Morphology Classification using Neural Ordinary Differential Equations
• Detecting gravitational lenses using machine learning: exploring interpretability and sensitivity to rare lensing configurations
• Variational Inference as an alternative to MCMC for parameter estimation and model selection
• A Robust Study of High-Redshift Galaxies: Unsupervised Machine Learning for Characterising morphology with JWST up to z ~ 8
• Enabling Unsupervised Discovery in Astronomical Images through Self-Supervised Representations
• Structured Variational Inference for Simulating Populations of Radio Galaxies
• Survey2Survey: A deep learning generative model approach for cross-survey image mapping
• Using Bayesian Deep Learning to infer Planet Mass from Gaps in Protoplanetary Disks
• The VVV near-IR galaxy catalogue in a Northern part of the Galactic disc
• Pix2Prof: fast extraction of sequential information from galaxy imagery via a deep natural language 'captioning' model
• Uncovering Tidal Treasures: Automated Classification of Faint Tidal Features in DECaLS Data
• Search for the edge-on galaxies using an artificial neural network
• CzSL: Learning from citizen science, experts and unlabelled data in astronomical image classification
• A post-merger enhancement only in star-forming Type 2 Seyfert galaxies: the deep learning view
• A survey on Variational Autoencoders from a GreenAI perspective
• Denoising Diffusion Probabilistic Model for realistic and fast generated \textit{Euclid}-like data for weak lensing analysis
• Deep learning-based astronomical multimodal data fusion: A comprehensive review
• Euclid preparation. LXVII. Deep learning true galaxy morphologies for weak lensing shear bias calibration
• A machine learning approach to assessing the presence of substructure in quasar host galaxies using the Hyper Suprime-Cam Subaru Strategic Program
• Investigation on deep learning-based galaxy image translation models
• Radio Galaxy Zoo: Using semi-supervised learning to leverage large unlabelled data-sets for radio galaxy classification under data-set shift
• Enhancing variational generation through self-decomposition
• Timing the last major merger of galaxy clusters with large halo sparsity
• Sifting the debris: Patterns in the SNR population with unsupervised ML methods