Machine-assisted discovery of relationships in astronomy

TL;DR

This paper explores automated systems for discovering meaningful relationships in large astronomical datasets, demonstrating methods that match traditional techniques and discussing their implications for feature selection.

Contribution

It applies evolutionary programming and information-theory techniques to astronomy data, showing their effectiveness in identifying known and new relationships.

Findings

Comparable results to decision trees in relationship discovery

Effective identification of classical astronomical relationships

Potential for improved feature selection and extraction

Abstract

High-volume feature-rich data sets are becoming the bread-and-butter of 21st century astronomy but present significant challenges to scientific discovery. In particular, identifying scientifically significant relationships between sets of parameters is non-trivial. Similar problems in biological and geosciences have led to the development of systems which can explore large parameter spaces and identify potentially interesting sets of associations. In this paper, we describe the application of automated discovery systems of relationships to astronomical data sets, focussing on an evolutionary programming technique and an information-theory technique. We demonstrate their use with classical astronomical relationships - the Hertzsprung-Russell diagram and the fundamental plane of elliptical galaxies. We also show how they work with the issue of binary classification which is relevant to the next generation of large synoptic sky surveys, such as LSST. We find that comparable results to more familiar techniques, such as decision trees, are achievable. Finally, we consider the reality of the relationships discovered and how this can be used for feature selection and extraction.