Artificial Intelligence (AI) Approchaes for Analyzing Automatically Zillions of Eclipsing Binary Light Curves (Abstract)

Volume 39 number 1 (2011)

Edward F. Guinan

Astronomy Department, Villanova University, Villanova, PA 19085; edward.guinan@villanova.edu

Abstract

(Abstract only) Major advances in observing technology promise to vastly increase discovery rates of eclipsing binaries (EBs) as well as other types of variable stars. For example, missions such as the Large Synoptic Survey Telescope (LSST), the Panoramic Survey Telescope and Rapid Response System (Pan-STARRS), Gaia, and the AAVSO Photometric All-Sky Survey (APASS) are expected to yield hundreds of thousands (even millions) of new variable stars and eclipsing binaries. Current personal interactive (and time consuming) methods of determining the physical and orbital parameters of eclipsing binaries from the current practice of analyzing their light curves will be inadequate to keep up with the overwhelming influx of new data. At present, the currently-used methods require significant technical skill and experience; it typically takes 2 to 3 weeks to model a single binary. We are therefore developing an Artificial Intelligence / Neural Network system with the hope of creating a fully automated, high throughput process for gleaning the orbital and physical properties of EB systems from the observations of tens of thousands of eclipsing binaries at a time. The EBAI project — Eclipsing Binaries with Artificial Intelligence —aims to provide estimates of principal parameters for thousands of eclipsing binaries in a matter of seconds. Initial tests of the neural network’s performance and reliability have been conducted and are presented here. Several practical applications also will be presented. This research is supported by the National Science Foundation: Research at Undergraduate Instituions (RUI) Program Grant AST-0507542.