Show simple item record

dc.contributor.authorSpindler, Ashley
dc.contributor.authorGeach, James E.
dc.contributor.authorSmith, Michael J.
dc.date.accessioned2021-05-12T23:05:55Z
dc.date.available2021-05-12T23:05:55Z
dc.date.issued2021-03-01
dc.identifier.citationSpindler , A , Geach , J E & Smith , M J 2021 , ' AstroVaDEr: Astronomical Variational Deep Embedder for Unsupervised Morphological Classification of Galaxies and Synthetic Image Generation ' , Monthly Notices of the Royal Astronomical Society , vol. 502 , no. 1 , pp. 985–1007 . https://doi.org/10.1093/mnras/staa3670
dc.identifier.issn0035-8711
dc.identifier.otherPURE: 24343607
dc.identifier.otherPURE UUID: fbd381cb-ebfc-4070-8647-a8435b57e253
dc.identifier.otherArXiv: http://arxiv.org/abs/2009.08470v2
dc.identifier.urihttp://hdl.handle.net/2299/24480
dc.description© 2020 The Author(s). Published by Oxford University Press on behalf of the Royal Astronomical Society. https://doi.org/10.1093/mnras/staa3670
dc.description.abstractWe 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.en
dc.format.extent23
dc.language.isoeng
dc.relation.ispartofMonthly Notices of the Royal Astronomical Society
dc.subjectastro-ph.IM
dc.subjectastro-ph.GA
dc.titleAstroVaDEr: Astronomical Variational Deep Embedder for Unsupervised Morphological Classification of Galaxies and Synthetic Image Generationen
dc.contributor.institutionSchool of Physics, Engineering & Computer Science
dc.description.statusPeer reviewed
dc.relation.school
dcterms.dateAccepted2021-03-01
rioxxterms.versionAM
rioxxterms.versionofrecordhttps://doi.org/10.1093/mnras/staa3670
rioxxterms.typeJournal Article/Review
herts.preservation.rarelyaccessedtrue


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record