Machine-assisted discovery of relationships in astronomy

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.

16 pages, 9 figures, accepted for publication in MNRAS

References in corpus (9)

• Learning When Training Data are Costly: The Effect of Class Distribution on Tree Induction
• The Milky Way Tomography with SDSS: II. Stellar Metallicity
• The Radial Velocity Experiment (RAVE): second data release
• Automated supervised classification of variable stars I. Methodology
• Results from the Supernova Photometric Classification Challenge
• The expected performance of stellar parametrization with Gaia spectrophotometry
• Semi-analytical formulas for the Hertzsprung-Russell Diagram
• Mapping the Galactic Halo with SDSS, LINEAR and PTF RR Lyrae Stars
• RR Lyrae Period-Amplitude Diagrams: From Bailey to Today

Cited by in corpus (22)

• Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
• Deep symbolic regression for physics guided by units constraints: toward the automated discovery of physical laws
• Robust PCA and MIC statistics of baryons in early mini-haloes
• AutoRegressive Planet Search: Methodology
• The SZ flux-mass ($Y$-$M$) relation at low halo masses: improvements with symbolic regression and strong constraints on baryonic feedback
• Augmenting astrophysical scaling relations with machine learning: application to reducing the Sunyaev-Zeldovich flux-mass scatter
• Feature Selection Strategies for Classifying High Dimensional Astronomical Data Sets
• The first analytical expression to estimate photometric redshifts suggested by a machine
• Real-Time Data Mining of Massive Data Streams from Synoptic Sky Surveys
• Automatic Survey-Invariant Variable Star Classification
• Machines Learn to Infer Stellar Parameters Just by Looking at a Large Number of Spectra
• Analytic Continued Fractions for Regression: A Memetic Algorithm Approach
• ANTARES: A Prototype Transient Broker System
• Sacrificing information for the greater good: how to select photometric bands for optimal accuracy
• Nonparametric Transient Classification using Adaptive Wavelets
• Generation of a Supervised Classification Algorithm for Time-Series Variable Stars with an Application to the LINEAR Dataset
• Variable Star Classification Using Multi-View Metric Learning
• A Detection Metric Designed for O'Connell Effect Eclipsing Binaries
• Variable Star Signature Classification using Slotted Symbolic Markov Modeling
• Automated Real-Time Classification and Decision Making in Massive Data Streams from Synoptic Sky Surveys
• AMADA-Analysis of Multidimensional Astronomical Datasets
• Advanced Astroinformatics for Variable Star Classification