Some Pattern Recognition Challenges in Data-Intensive Astronomy

Abstract

We review some of the recent developments and challenges posed by the data analysis in modern digital sky surveys, which are representative of the information-rich astronomy in the context of Virtual Observatory. Illustrative examples include the problems of an automated star-galaxy classification in complex and heterogeneous panoramic imaging data sets, and an automated, iterative, dynamical classification of transient events detected in synoptic sky surveys. These problems offer good opportunities for productive collaborations between astronomers and applied computer scientists and statisticians, and are representative of the kind of challenges now present in all data-intensive fields. We discuss briefly some emergent types of scalable scientific data analysis systems with a broad applicability.

8 pages, compressed pdf file, figures downgraded in quality in order to match the arXiv size limit

References in corpus (9)

• Large Synoptic Survey Telescope: Overview
• Variable Faint Optical Sources Discovered by Comparing POSS and SDSS Catalogs
• A Census of Object Types and Redshift Estimates in the SDSS Photometric Catalog from a Trained Decision-Tree Classifier
• Virtual Astronomy, Information Technology, and the New Scientific Methodology
• Variability Studies with SDSS
• Exploring the Time Domain with the Palomar-QUEST Sky Survey
• Grist: Grid-based Data Mining for Astronomy
• Challenges for Cluster Analysis in a Virtual Observatory
• Time Domain Explorations With Digital Sky Surveys

Cited by in corpus (6)

• Computational Intelligence Challenges and Applications on Large-Scale Astronomical Time Series Databases
• Automated Probabilistic Classification of Transients and Variables
• Data challenges of time domain astronomy
• Sky Surveys
• Flashes in a Star Stream: Automated Classification of Astronomical Transient Events
• Blueshifted hydrogen emission and shock wave of RR Lyrae variables in SDSS and LAMOST