ORCID Profile
0000-0002-6408-4181
Current Organisations
University of Oxford
,
University of Toronto
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: Oxford University Press (OUP)
Date: 11-04-2023
Abstract: We present a novel natural language processing (NLP) approach to deriving plain English descriptors for science cases otherwise restricted by obfuscating technical terminology. We address the limitations of common radio galaxy morphology classifications by applying this approach. We experimentally derive a set of semantic tags for the Radio Galaxy Zoo EMU (Evolutionary Map of the Universe) project and the wider astronomical community. We collect 8486 plain English annotations of radio galaxy morphology, from which we derive a taxonomy of tags. The tags are plain English. The result is an extensible framework, which is more flexible, more easily communicated, and more sensitive to rare feature combinations, which are indescribable using the current framework of radio astronomy classifications.
Publisher: Oxford University Press (OUP)
Date: 29-04-2022
Abstract: In this work, we examine the classification accuracy and robustness of a state-of-the-art semi-supervised learning (SSL) algorithm applied to the morphological classification of radio galaxies. We test if SSL with fewer labels can achieve test accuracies comparable to the supervised state of the art and whether this holds when incorporating previously unseen data. We find that for the radio galaxy classification problem considered, SSL provides additional regularization and outperforms the baseline test accuracy. However, in contrast to model performance metrics reported on computer science benchmarking data sets, we find that improvement is limited to a narrow range of label volumes, with performance falling off rapidly at low label volumes. Additionally, we show that SSL does not improve model calibration, regardless of whether classification is improved. Moreover, we find that when different underlying catalogues drawn from the same radio survey are used to provide the labelled and unlabelled data sets required for SSL, a significant drop in classification performance is observed, highlighting the difficulty of applying SSL techniques under data set shift. We show that a class-imbalanced unlabelled data pool negatively affects performance through prior probability shift, which we suggest may explain this performance drop, and that using the Fréchet distance between labelled and unlabelled data sets as a measure of data set shift can provide a prediction of model performance, but that for typical radio galaxy data sets with labelled s le volumes of $\\mathcal {O}(10^3)$, the s le variance associated with this technique is high and the technique is in general not sufficiently robust to replace a train–test cycle.
Publisher: American Astronomical Society
Date: 18-06-2019
Publisher: Oxford University Press (OUP)
Date: 03-11-2022
Abstract: Galaxies fall broadly into two categories: star-forming (blue) galaxies and quiescent (red) galaxies. In between, one finds the less populated ‘green valley’. Some of these galaxies are suspected to be in the process of ceasing their star formation through a gradual exhaustion of gas supply, or already dead and experiencing a rejuvenation of star formation through fuel injection. We use the Galaxy And Mass Assembly (GAMA) database and the Galaxy Zoo citizen science morphological estimates to compare the morphology of galaxies in the green valley with those in the red sequence and blue cloud. Our goal is to examine the structural differences within galaxies that fall in the green valley, and what brings them there. Previous results found that disc features such as rings and lenses are more prominently represented in the green-valley population. We revisit this with a similar sized data set of galaxies with morphology labels provided by the Galaxy Zoo for the GAMA fields based on new Kilo-Degree Survey (KiDS) images. Our aim is to compare the results from expert classification qualitatively with those of citizen science. We observe that ring structures are indeed found more commonly in green-valley galaxies compared with their red and blue counterparts. We suggest that ring structures are a consequence of disc galaxies in the green valley actively exhibiting the characteristics of fading discs and evolving disc morphology of galaxies. We note that the progression from blue to red correlates with loosening spiral-arm structure.
Location: United Kingdom of Great Britain and Northern Ireland
Location: United Kingdom of Great Britain and Northern Ireland
No related grants have been discovered for Mike Walmsley.