Multivariate Approaches to Classification in Extragalactic Astronomy

This the title of our paper that makes a review of the tentative to base a (unsupervised) classification of galaxies on learning machine techniques :

Multivariate Approaches to Classification in Extragalactic Astronomy
Didier Fraix-Burnet, Marc Thuillard, Asis Kumar Chattopadhyay
Frontiers in Astronomy and Space Sciences, 2015, 2 (3)

It is an Open Access publication (not a scandalous hybrid option, but a true OA in this true OA new journal).

Our goal was to:

  1. review the different techniques that have been used since the 80s ;
  2. explain the differences and similarities between the approaches ;
  3. put the phylogenetic methods in the clustering context ;
  4. show that multivariate statistical analyses is used and is useful in astrophysics ;
  5. encourage more astronomers to embark in these new directions, ideally in collaboration with statisticians.

We thus hope to trigger some impetus on this important subject that seeks to renew our one-century old galaxy classification.

The techniques that we present have been used in the extragalactic astrophysical community:

  • Principal Component Analysis (PCA)
  • Independent Component Analysis (ICA)
  • Support Vector Machine
  • K-Means
  • Fuzzy Clustering
  • Information Bottleneck Technique
  • Mixture Models
  • Wavelet Analysis
  • Hierarchical Clustering
  • Minimum Spanning Tree
  • Neighbor Joining Tree Estimation
  • Maximum Likelihood
  • Maximum Parsimony (Cladistics)
  • Outer Planar Networks


  1. Leave a comment

Leave a Comment

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: