Advanced search
1 file | 8.95 MB Add to list

Rotation-invariant convolutional neural networks for galaxy morphology prediction

Sander Dieleman (UGent) , Kyle Willett and Joni Dambre (UGent)
Author
Organization
Abstract
Measuring the morphological parameters of galaxies is a key requirement for studying their formation and evolution. Surveys such as the Sloan Digital Sky Survey have resulted in the availability of very large collections of images, which have permitted population-wide analyses of galaxy morphology. Morphological analysis has traditionally been carried out mostly via visual inspection by trained experts, which is time consuming and does not scale to large (≳104) numbers of images. Although attempts have been made to build automated classification systems, these have not been able to achieve the desired level of accuracy. The Galaxy Zoo project successfully applied a crowdsourcing strategy, inviting online users to classify images by answering a series of questions. Unfortunately, even this approach does not scale well enough to keep up with the increasing availability of galaxy images. We present a deep neural network model for galaxy morphology classification which exploits translational and rotational symmetry. It was developed in the context of the Galaxy Challenge, an international competition to build the best model for morphology classification based on annotated images from the Galaxy Zoo project. For images with high agreement among the Galaxy Zoo participants, our model is able to reproduce their consensus with near-perfect accuracy (>99 per cent) for most questions. Confident model predictions are highly accurate, which makes the model suitable for filtering large collections of images and forwarding challenging images to experts for manual annotation. This approach greatly reduces the experts’ workload without affecting accuracy. The application of these algorithms to larger sets of training data will be critical for analysing results from future surveys such as the Large Synoptic Survey Telescope.
Keywords
deep learning. DIGITAL-SKY-SURVEY, convolutional neural networks, computer vision, galaxy morphology classification, ESTIMATING PHOTOMETRIC REDSHIFTS, ZOO, CLASSIFICATION, STAR, RECOGNITION, EXTRACTION, DEPENDENCE, FRACTION, SAMPLE

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 8.95 MB

Citation

Please use this url to cite or link to this publication:

MLA
Dieleman, Sander, et al. “Rotation-Invariant Convolutional Neural Networks for Galaxy Morphology Prediction.” MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY, vol. 450, no. 2, Oxford University Press, 2015, pp. 1441–59, doi:10.1093/mnras/stv632.
APA
Dieleman, S., Willett, K., & Dambre, J. (2015). Rotation-invariant convolutional neural networks for galaxy morphology prediction. MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY, 450(2), 1441–1459. https://doi.org/10.1093/mnras/stv632
Chicago author-date
Dieleman, Sander, Kyle Willett, and Joni Dambre. 2015. “Rotation-Invariant Convolutional Neural Networks for Galaxy Morphology Prediction.” MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY 450 (2): 1441–59. https://doi.org/10.1093/mnras/stv632.
Chicago author-date (all authors)
Dieleman, Sander, Kyle Willett, and Joni Dambre. 2015. “Rotation-Invariant Convolutional Neural Networks for Galaxy Morphology Prediction.” MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY 450 (2): 1441–1459. doi:10.1093/mnras/stv632.
Vancouver
1.
Dieleman S, Willett K, Dambre J. Rotation-invariant convolutional neural networks for galaxy morphology prediction. MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY. 2015;450(2):1441–59.
IEEE
[1]
S. Dieleman, K. Willett, and J. Dambre, “Rotation-invariant convolutional neural networks for galaxy morphology prediction,” MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY, vol. 450, no. 2, pp. 1441–1459, 2015.
@article{5943926,
  abstract     = {{Measuring the morphological parameters of galaxies is a key requirement for studying their formation and evolution. Surveys such as the Sloan Digital Sky Survey have resulted in the availability of very large collections of images, which have permitted population-wide analyses of galaxy morphology. Morphological analysis has traditionally been carried out mostly via visual inspection by trained experts, which is time consuming and does not scale to large (≳104) numbers of images. Although attempts have been made to build automated classification systems, these have not been able to achieve the desired level of accuracy. The Galaxy Zoo project successfully applied a crowdsourcing strategy, inviting online users to classify images by answering a series of questions. Unfortunately, even this approach does not scale well enough to keep up with the increasing availability of galaxy images. We present a deep neural network model for galaxy morphology classification which exploits translational and rotational symmetry. It was developed in the context of the Galaxy Challenge, an international competition to build the best model for morphology classification based on annotated images from the Galaxy Zoo project. For images with high agreement among the Galaxy Zoo participants, our model is able to reproduce their consensus with near-perfect accuracy (>99 per cent) for most questions. Confident model predictions are highly accurate, which makes the model suitable for filtering large collections of images and forwarding challenging images to experts for manual annotation. This approach greatly reduces the experts’ workload without affecting accuracy. The application of these algorithms to larger sets of training data will be critical for analysing results from future surveys such as the Large Synoptic Survey Telescope.}},
  author       = {{Dieleman, Sander and Willett, Kyle and Dambre, Joni}},
  issn         = {{0035-8711}},
  journal      = {{MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY}},
  keywords     = {{deep learning. DIGITAL-SKY-SURVEY,convolutional neural networks,computer vision,galaxy morphology classification,ESTIMATING PHOTOMETRIC REDSHIFTS,ZOO,CLASSIFICATION,STAR,RECOGNITION,EXTRACTION,DEPENDENCE,FRACTION,SAMPLE}},
  language     = {{eng}},
  number       = {{2}},
  pages        = {{1441--1459}},
  publisher    = {{Oxford University Press}},
  title        = {{Rotation-invariant convolutional neural networks for galaxy morphology prediction}},
  url          = {{http://dx.doi.org/10.1093/mnras/stv632}},
  volume       = {{450}},
  year         = {{2015}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: