IVOA KDD-IG: A user guide for Data Mining in Astronomy

Who's interested?

NickBall
KirkBorne
RaffaeleDAbrusco

Purpose of this Guide

The purpose of this guide is to show how the techniques of data mining, a large well-known field with a wide array of applications, can be used within astronomy to improve the science that is done with the available data. It is written with the typical astronomer in mind, i.e., one whose first priority is to get good science done.

Table of contents

• 1: What is 'data mining' and why is it important in astronomy?
• 2: Examples of improved results enabled by data mining techniques
• 3: Overview of the data mining process
• 4: The main data mining algorithms
• 5: Which algorithm to use?
• 6: Present and future directions
• 7: Algorithms and techniques astronomers could benefit from but seldom use
• 8: Links: Books, papers, websites
• 9: Worked example

Authors

• Nick Ball is an active participant in the Next Generation Virgo Cluster Survey at the Herzberg Institute for Astrophysics in Victoria, British Columbia, Canada. His research interests include the galaxy luminosity function, galaxy, AGN, and quasar properties versus environment, photometric redshifts and classification, and data mining.

• Sabine McConnell (main author of sections 3 and 4) is an Assistant Professor in the Department of Computing and Information Systems at Trent University, Peterborough, Ontario, Canada.

-- NickBall - 18 Mar 2011
-- NickBall - 23 Sep 2011