Applying Deep Learning on Time Series Astronomical Data

Robert J. Brunner, University of Illinois at Urbana-Champaign

Usage Details

This project proposes to apply advanced machine learning techniques to time series data in order to optimize accurate classification. As a result of large, synoptic sky surveys, extremely large amounts of astronomical data are collected. As a result, it is extremely important to develop robust, automated methods that can quickly, accurately, and efficiently process these large data sets. Developing advanced machine learning techniques will allow for the rapid processing of these large sets of data in an automated manner without the need of constant manual intervention. In addition, these processes will also be developed to work on data that is noisy and is irregularly sampled. The algorithms and methods we develop can be reapplied and specified to other fields that are generating large data sets that require automated classification.