Light curve fingerprints: an automated approach to the extraction of X-ray variability patterns with feature aggregation -- an example application to GRS 1915+105

Abstract

Time series data mining is an important field of research in the era of "Big Data". Next generation astronomical surveys will generate data at unprecedented rates, creating the need for automated methods of data analysis. We propose a method of light curve characterisation that employs a pipeline consisting of a neural network with a Long-Short Term Memory Variational Autoencoder architecture and a Gaussian mixture model. The pipeline performs extraction and aggregation of features from light curve segments into feature vectors of fixed length which we refer to as light curve "fingerprints". This representation can be readily used as input of down-stream machine learning algorithms. We demonstrate the proposed method on a data set of Rossi X-ray Timing Explorer observations of the galactic black hole X-ray binary GRS 1915+105, which was chosen because of its observed complex X-ray variability. We find that the proposed method can generate a representation that characterises the observations and reflects the presence of distinct classes of GRS 1915+105 X-ray flux variability. We find that this representation can be used to perform efficient classification of light curves. We also present how the representation can be used to quantify the similarity of different light curves, highlighting the problem of the popular classification system of GRS 1915+105 observations, which does not account for intermediate class behaviour.

References in corpus (15)

• cuDNN: Efficient Primitives for Deep Learning
• ULTRACAM: an ultra-fast, triple-beam CCD camera for high-speed astrophysics
• A recurrent neural network for classification of unevenly sampled variable stars
• Inclination-dependent spectral and timing properties in transient black hole X-ray binaries
• Scalable End-to-end Recurrent Neural Network for Variable star classification
• The Host Galaxies of Rapidly Evolving Transients in the Dark Energy Survey
• Unsupervised Classification of Variable Stars
• Exploring the Long-Term Evolution of GRS 1915+105
• Spectral states of the X-ray binary IGR J17091--3624 observed by INTEGRAL and RXTE
• Discovery of GRS 1915+105 variability patterns in the Rapid Burster
• Classification of Periodic Variable Stars with Novel Cyclic-Permutation Invariant Neural Networks
• HiPERCAM: A high-speed, quintuple-beam CCD camera for the study of rapid variability in the Universe
• A Machine Learning Approach For Classifying Low-mass X-ray Binaries Based On Their Compact Object Nature
• A non-linear mathematical model for the X-ray variability classes of the microquasar GRS 1915+105 -- II: transition and swaying classes
• An Algorithm for the Visualization of Relevant Patterns in Astronomical Light Curves

Cited by in corpus (1)

• Mapping the X-ray variability of GRS1915+105 with machine learning