“Galaxy morphology auto classification”的版本间差异

来自cluster
跳到导航 跳到搜索
第10行: 第10行:
===possibilities===
===possibilities===
* Classification in parameter space (e.g. parameters from Sextractor)
* Classification in parameter space (e.g. parameters from Sextractor)
* Pixel-based deep learning technic
* Special objects from auto-classification
* Special objects from auto-classification



2022年2月17日 (四) 06:40的版本

  • This page makes collections for galaxy morphology auto classification project of CSST image survey

projects

started

possibilities

  • Classification in parameter space (e.g. parameters from Sextractor)
  • Special objects from auto-classification

Meetings

datasets

  • galaxy zoo data [2]
  • Galaxy Zoo DECaLS[3]

Methods

  • Non-Negative Matrix Factorization
  • Image Fourier Power Spectrum
  • Auto-encoders (Rupesh)
  • Watershed (Image Segmentation)

tools

  • Morpheus [6]
  • DeepGalaxy (Deep learning to classify the properties of galaxy mergers) [7]
  • GalaxyMorphology [8]
  • lenstronomy [9]
  • Unsupervised Image Classification [10]
  • Copulas [11]

references

  1. Deep learning for galaxy surface brightness profile fitting, MNRAS, Volume 475, Issue 1, March 2018 [12]
  2. The weirdest SDSS galaxies: results from an outlier detection algorithm, 2017, MNRAS,465,4530B, [13]
  3. An automatic taxonomy of galaxy morphology using unsupervised machine learning, 2018, MNRAS, 473, 1108, [14]
  4. Galaxy morphology classification with deep convolutional neural networks, 2019, Astrophysics and Space Science, Volume 364, Issue 4, article id. 55, [15]
  5. Machine and Deep Learning Applied to Galaxy Morphology -- A Comparative Study, 2020, Astronomy and Computing, Volume 30, article id. 100334, [16]
  6. Shadows in the Dark: Low-surface-brightness Galaxies Discovered in the Dark Energy Survey,2021,ApJS,252,18T,[17]
  7. Dwarfs from the Dark (Energy Survey): a machine learning approach to classify dwarf galaxies from multi-band image, arXiv:2102.12776,[18]

links

  • THE COSMOSTATISTICS INITIATIVE [19]