Galaxy Zoo: Probabilistic morphology through Bayesian CNNs and active learning

Mike Walmsley; Lewis Smith; Chris Lintott; Yarin Gal; Steven Bamford; Hugh Dickinson; Lucy Fortson; Sandor Kruk; Karen Masters; Claudia Scarlata; Brooke Simmons; Rebecca Smethurst; Darryl Wright

doi:10.1093/mnras/stz2816

Galaxy Zoo: Probabilistic morphology through Bayesian CNNs and active learning

Mike Walmsley, Lewis Smith, Chris Lintott, Yarin Gal, Steven Bamford, Hugh Dickinson, Lucy Fortson, Sandor Kruk, Karen Masters, Claudia Scarlata, Brooke Simmons, Rebecca Smethurst, Darryl Wright

Physics and Astronomy (Twin Cities)

Research output: Contribution to journal › Article › peer-review

62 Scopus citations

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.

Original language	English (US)
Pages (from-to)	1554-1574
Number of pages	21
Journal	Monthly Notices of the Royal Astronomical Society
Volume	491
Issue number	2
DOIs	https://doi.org/10.1093/mnras/stz2816
State	Published - Jan 1 2020

Bibliographical note

Funding Information:
MW would like to thank H. Domínguez Sanchez and M. Huertas-Company for helpful discussions. MW acknowledges funding from the Science and Technology Funding Council (STFC) Grant Code ST/R505006/1. We also acknowledge support from STFC under grant ST/N003179/1. LF, CS, HD, and DW acknowledge partial support from one or more of the US National Science Foundation grants IIS-1619177, OAC-1835530, and AST-1716602. This research made use of the open-source PYTHON scientific computing ecosystem, including SCIPY (Jones et al. 2001), MAT-PLOTLIB (Hunter 2007), SCIKIT-LEARN (Pedregosa et al. 2011), SCIKIT-IMAGE (van der Walt et al. 2014), and PANDAS (McKinney 2010). This research made use of ASTROPY, a community-developed core PYTHON package for Astronomy (The Astropy Collaboration 2013, 2018). This research made use of TENSORFLOW (Abadi et al. 2015). All code is publicly available on GitHub at www.github.com/m walmsley/galaxy-zoo-bayesian-cnn (Walmsley 2019).

Funding Information:
MW acknowledges funding from the Science and Technology Funding Council (STFC) Grant Code ST/R505006/1. We also acknowledge support from STFC under grant ST/N003179/1. LF, CS, HD, and DW acknowledge partial support from one or more of the US National Science Foundation grants IIS-1619177, OAC-1835530, and AST-1716602.

Publisher Copyright:
© 2019 The Author(s).

Keywords

Galaxies: evolution
Galaxies: statistics
Galaxies: structure
Methods: data analysis
Methods: statistical

Publisher link

10.1093/mnras/stz2816

https://eprints.lancs.ac.uk/id/eprint/138288/1/stz2816.pdf

Find It

Find It at U of M Libraries

Cite this

@article{43984aa273d347138015843b9f732143,

title = "Galaxy Zoo: Probabilistic morphology through Bayesian CNNs and active learning",

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.",

keywords = "Galaxies: evolution, Galaxies: statistics, Galaxies: structure, Methods: data analysis, Methods: statistical",

author = "Mike Walmsley and Lewis Smith and Chris Lintott and Yarin Gal and Steven Bamford and Hugh Dickinson and Lucy Fortson and Sandor Kruk and Karen Masters and Claudia Scarlata and Brooke Simmons and Rebecca Smethurst and Darryl Wright",

note = "Funding Information: MW would like to thank H. Dom{\'i}nguez Sanchez and M. Huertas-Company for helpful discussions. MW acknowledges funding from the Science and Technology Funding Council (STFC) Grant Code ST/R505006/1. We also acknowledge support from STFC under grant ST/N003179/1. LF, CS, HD, and DW acknowledge partial support from one or more of the US National Science Foundation grants IIS-1619177, OAC-1835530, and AST-1716602. This research made use of the open-source PYTHON scientific computing ecosystem, including SCIPY (Jones et al. 2001), MAT-PLOTLIB (Hunter 2007), SCIKIT-LEARN (Pedregosa et al. 2011), SCIKIT-IMAGE (van der Walt et al. 2014), and PANDAS (McKinney 2010). This research made use of ASTROPY, a community-developed core PYTHON package for Astronomy (The Astropy Collaboration 2013, 2018). This research made use of TENSORFLOW (Abadi et al. 2015). All code is publicly available on GitHub at www.github.com/m walmsley/galaxy-zoo-bayesian-cnn (Walmsley 2019). Funding Information: MW acknowledges funding from the Science and Technology Funding Council (STFC) Grant Code ST/R505006/1. We also acknowledge support from STFC under grant ST/N003179/1. LF, CS, HD, and DW acknowledge partial support from one or more of the US National Science Foundation grants IIS-1619177, OAC-1835530, and AST-1716602. Publisher Copyright: {\textcopyright} 2019 The Author(s).",

year = "2020",

month = jan,

day = "1",

doi = "10.1093/mnras/stz2816",

language = "English (US)",

volume = "491",

pages = "1554--1574",

journal = "Monthly Notices of the Royal Astronomical Society",

issn = "0035-8711",

publisher = "Oxford University Press",

number = "2",

}

TY - JOUR

T1 - Galaxy Zoo

T2 - Probabilistic morphology through Bayesian CNNs and active learning

AU - Walmsley, Mike

AU - Smith, Lewis

AU - Lintott, Chris

AU - Gal, Yarin

AU - Bamford, Steven

AU - Dickinson, Hugh

AU - Fortson, Lucy

AU - Kruk, Sandor

AU - Masters, Karen

AU - Scarlata, Claudia

AU - Simmons, Brooke

AU - Smethurst, Rebecca

AU - Wright, Darryl

N1 - Funding Information: MW would like to thank H. Domínguez Sanchez and M. Huertas-Company for helpful discussions. MW acknowledges funding from the Science and Technology Funding Council (STFC) Grant Code ST/R505006/1. We also acknowledge support from STFC under grant ST/N003179/1. LF, CS, HD, and DW acknowledge partial support from one or more of the US National Science Foundation grants IIS-1619177, OAC-1835530, and AST-1716602. This research made use of the open-source PYTHON scientific computing ecosystem, including SCIPY (Jones et al. 2001), MAT-PLOTLIB (Hunter 2007), SCIKIT-LEARN (Pedregosa et al. 2011), SCIKIT-IMAGE (van der Walt et al. 2014), and PANDAS (McKinney 2010). This research made use of ASTROPY, a community-developed core PYTHON package for Astronomy (The Astropy Collaboration 2013, 2018). This research made use of TENSORFLOW (Abadi et al. 2015). All code is publicly available on GitHub at www.github.com/m walmsley/galaxy-zoo-bayesian-cnn (Walmsley 2019). Funding Information: MW acknowledges funding from the Science and Technology Funding Council (STFC) Grant Code ST/R505006/1. We also acknowledge support from STFC under grant ST/N003179/1. LF, CS, HD, and DW acknowledge partial support from one or more of the US National Science Foundation grants IIS-1619177, OAC-1835530, and AST-1716602. Publisher Copyright: © 2019 The Author(s).

PY - 2020/1/1

Y1 - 2020/1/1

N2 - 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.

AB - 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.

KW - Galaxies: evolution

KW - Galaxies: statistics

KW - Galaxies: structure

KW - Methods: data analysis

KW - Methods: statistical

UR - http://www.scopus.com/inward/record.url?scp=85079671660&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85079671660&partnerID=8YFLogxK

U2 - 10.1093/mnras/stz2816

DO - 10.1093/mnras/stz2816

M3 - Article

AN - SCOPUS:85079671660

SN - 0035-8711

VL - 491

SP - 1554

EP - 1574

JO - Monthly Notices of the Royal Astronomical Society

JF - Monthly Notices of the Royal Astronomical Society

IS - 2

ER -

Galaxy Zoo: Probabilistic morphology through Bayesian CNNs and active learning

Abstract

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this