University of Tasmania
Browse

File(s) under permanent embargo

Radio galaxy zoo: Unsupervised clustering of convolutionally auto-encoded radio-astronomical images

journal contribution
posted on 2023-05-20, 09:49 authored by Ralph, NO, Norris, RP, Fang, G, Park, LAF, Galvin, TJ, Alger, MJ, Andernach, H, Lintott, C, Rudnick, L, Stanislav ShabalaStanislav Shabala, Wong, OI
This paper demonstrates a novel and efficient unsupervised clustering method with the combination of a self-organizing map (SOM) and a convolutional autoencoder. The rapidly increasing volume of radio-astronomical data has increased demand for machine-learning methods as solutions to classification and outlier detection. Major astronomical discoveries are unplanned and found in the unexpected, making unsupervised machine learning highly desirable by operating without assumptions and labeled training data. Our approach shows SOM training time is drastically reduced and high-level features can be clustered by training on auto-encoded feature vectors instead of raw images. Our results demonstrate this method is capable of accurately separating outliers on a SOM with neighborhood similarity and K-means clustering of radio-astronomical features. We present this method as a powerful new approach to data exploration by providing a detailed understanding of the morphology and relationships of Radio Galaxy Zoo (RGZ) data set image features which can be applied to new radio survey data.

History

Publication title

Publications of the Astronomical Society of the Pacific

Volume

131

Issue

1004

Article number

108011

Number

108011

Pagination

1-17

ISSN

0004-6280

Department/School

School of Natural Sciences

Publisher

Univ Chicago Press

Place of publication

1427 E 60Th St, Chicago, USA, Il, 60637-2954

Rights statement

© 2019. The Astronomical Society of the Pacific

Repository Status

  • Restricted

Socio-economic Objectives

Expanding knowledge in the physical sciences

Usage metrics

    University Of Tasmania

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC