A recurrent neural network for classification of unevenly sampled variable stars
arXiv:1711.10609 · doi:10.1038/s41550-017-0321-z
Abstract
Astronomical surveys of celestial sources produce streams of noisy time series measuring flux versus time ("light curves"). Unlike in many other physical domains, however, large (and source-specific) temporal gaps in data arise naturally due to intranight cadence choices as well as diurnal and seasonal constraints. With nightly observations of millions of variable stars and transients from upcoming surveys, efficient and accurate discovery and classification techniques on noisy, irregularly sampled data must be employed with minimal human-in-the-loop involvement. Machine learning for inference tasks on such data traditionally requires the laborious hand-coding of domain-specific numerical summaries of raw data ("features"). Here we present a novel unsupervised autoencoding recurrent neural network (RNN) that makes explicit use of sampling times and known heteroskedastic noise properties. When trained on optical variable star catalogs, this network produces supervised classification models that rival other best-in-class approaches. We find that autoencoded features learned on one time-domain survey perform nearly as well when applied to another survey. These networks can continue to learn from new unlabeled observations and may be used in other unsupervised tasks such as forecasting and anomaly detection.
23 pages, 14 figures. The published version is at Nature Astronomy (https://www.nature.com/articles/s41550-017-0321-z). Source code for models, experiments, and figures at https://github.com/bnaul/IrregularTimeSeriesAutoencoderPaper (Zenodo Code DOI: 10.5281/zenodo.1045560)
References in corpus (3)
Cited by in corpus (22)
- The Zwicky Transient Facility: Science Objectives
- Machine Learning for the Zwicky Transient Facility
- Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
- Scalable End-to-end Recurrent Neural Network for Variable star classification
- Double-, triple-line spectroscopic candidates in the LAMOST Medium-Resolution Spectroscopic Survey
- Searching for changing-state AGNs in massive datasets -- I: applying deep learning and anomaly detection techniques to find AGNs with anomalous variability behaviours
- Applications of Machine Learning to Predicting Core-collapse Supernova Explosion Outcomes
- Deep Neural Network Classifier for Variable Stars with Novelty Detection Capability
- Stellar population of the Rosette Nebula and NGC 2244: application of the probabilistic random forest
- LSST Cadence Strategy Evaluations for AGN Time-series Data in Wide-Fast-Deep Field
- Clumpiness: Time-domain classification of red-giant evolutionary states
- The effect of phased recurrent units in the classification of multiple catalogs of astronomical lightcurves
- Near-Infrared Search for Fundamental-mode RR Lyrae Stars Toward the Inner Bulge by Deep Learning
- Periodic Variable Star Classification with Deep Learning: Handling Data Imbalance in an Ensemble Augmentation Way
- Semi-Supervised Classification and Clustering Analysis for Variable Stars
- A Detection Metric Designed for O'Connell Effect Eclipsing Binaries
- An Information Theory Approach on Deciding Spectroscopic Follow Ups
- Informative Bayesian model selection for RR Lyrae star classifiers
- YOUNG Star detrending for Transiting Exoplanet Recovery (YOUNGSTER) II: Using Self-Organising Maps to explore young star variability in Sectors 1-13 of TESS data
- Construction of a far ultraviolet all sky map from an incomplete survey: Application of a deep learning algorithm
- Informative regularization for a multi-layer perceptron RR Lyrae classifier under data shift
- Light curve fingerprints: an automated approach to the extraction of X-ray variability patterns with feature aggregation -- an example application to GRS 1915+105