Galaxy zoo: Probabilistic morphology through Bayesian CNNs and active learning
Monthly Notices of the Royal Astronomical Society Oxford University Press 491:2 (2019) 1554-1574
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 per cent 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 per cent 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 time-scale of weeks, providing massive and detailed morphology catalogues to support research into galaxy evolution.A ghost in the toast: TESS background light produces a false “transit” across τ Ceti
Research Notes of the AAS American Astronomical Society 3:10 (2019) 145
Accretion and star formation in ‘radio-quiet’ quasars
Proceedings of the International Astronomical Union Cambridge University Press (CUP) 15:S356 (2019) 204-208
Better support for collaborations preparing for large-scale projects: the case study of the LSST Science Collaborations
Bulletin of the American Astronomical Society American Astronomical Society 51:7 (2019) 185
Abstract:
Through the lens of the LSST Science Collaborations’ experience, we advocate for new, improved ways to fund large, complex collaborations as they work in preparation for and on peta-scale surveys. We advocate for the establishment of programs to support research and infrastructure that enables innovative collaborative research on such scales.Radio galaxy zoo: Unsupervised clustering of convolutionally auto-encoded radio-astronomical images
Publications of the Astronomical Society of the Pacific IOP Publishing 131:1004 (2019) 108011