A Deep-learning Approach for Live Anomaly Detection of Extragalactic Transients

  title={A Deep-learning Approach for Live Anomaly Detection of Extragalactic Transients},
  author={V. Ashley Villar and M. Cranmer and Edo Berger and Gabriella Contardo and Shirley Ho and Griffin Hosseinzadeh and Joshua Yao-Yu Lin},
  journal={The Astrophysical Journal Supplement Series},
There is a shortage of multiwavelength and spectroscopic follow-up capabilities given the number of transient and variable astrophysical events discovered through wide-field optical surveys such as the upcoming Vera C. Rubin Observatory and its associated Legacy Survey of Space and Time. From the haystack of potential science targets, astronomers must allocate scarce resources to study a selection of needles in real time. Here we present a variational recurrent autoencoder neural network to… 

Detecting Dispersed Radio Transients in Real Time using Convolutional Neural Networks

Radio astronomy has entered an era of fast-cadence imaging [Prasad and Wijnholds, 2012]. Among others, this allows for transient hunting in the long-wavelength regime. For example, fast radio bursts

ParSNIP: Generative Models of Transient Light Curves with Physics-enabled Deep Learning

We present a novel method to produce empirical generative models of all kinds of astronomical transients from data sets of unlabeled light curves. Our hybrid model, which we call ParSNIP, uses a

Autonomous Real-Time Science-Driven Follow-up of Survey Transients

Astronomical surveys continue to provide unprecedented insights into the time-variable Universe and will remain the source of groundbreaking discoveries for years to come. However, their data

UvA-DARE (Digital Academic Repository) Detecting dispersed radio transients in real time using convolutional neural networks

We present a methodology for automated real-time analysis of a radio image data stream with the goal to find transient sources. Contrary to previous works, the transients we are interested in occur

Searching for Anomalies in the ZTF Catalog of Periodic Variable Stars

Periodic variables illuminate the physical processes of stars throughout their lifetime. Wide-field surveys continue to increase our discovery rates of periodic variable stars. Automated approaches



RAPID: Early Classification of Explosive Transients using Deep Learning

We present Real-time Automated Photometric IDentification (RAPID), a novel time series classification tool capable of automatically identifying transients from within a day of the initial alert, to

Anomaly Detection in the Open Supernova Catalog

This work performs for the first time an automated anomaly detection analysis in the photometric data of the Open Supernova Catalog, which serves as a proof of concept for the applicability of these methods to future large scale surveys.

Classifying Image Sequences of Astronomical Transients with Deep Neural Networks

The TAO-Net (for Transient Astronomical Objects Network) architecture achieves on the five-type classification task an average F1-score of 54.32, almost nine points higher than the F1 -score of 45.75 from the random forest classification on light curves.

Photometric Classification of 2315 Pan-STARRS1 Supernovae with Superphot

The classification of supernovae (SNe) and its impact on our understanding of explosion physics and progenitors have traditionally been based on the presence or absence of certain spectral features.

Anomaly detection in gravitational waves data using convolutional autoencoders

This paper proposes an alternative generic method of studying GW data based on detecting anomalies that is not limited only to GW alone, but also includes glitches occurring in the real LIGO/Virgo dataset available at the Gravitational Waves Open Science Center.

SuperRAENN: A Semisupervised Supernova Photometric Classification Pipeline Trained on Pan-STARRS1 Medium-Deep Survey Supernovae

A novel semisupervised machine learning algorithm is trained to photometrically classify 2315 new SN-like light curves with host galaxy spectroscopic redshifts, which has an accuracy of 87% across five SN classes and macro-averaged purity and completeness of 66% and 69%, respectively.

Avocado: Photometric Classification of Astronomical Transients with Gaussian Process Augmentation

  • Kyle Boone
  • Physics, Computer Science
    The Astronomical Journal
  • 2019
The results suggest that spectroscopic campaigns used for training photometric classifiers should focus on typing large numbers of well-observed, intermediate-redshift transients, instead of attempting to type a sample of transients that is directly representative of the full data set being classified.

A classification algorithm for time-domain novelties in preparation for LSST alerts: Application to variable stars and transients detected with DECam in the Galactic Bulge.

With the advent of the Legacy Survey of Space and Time, time-domain astronomy will be faced with an unprecedented volume and rate of data. Real-time processing of variables and transients detected by

Supernova Photometric Classification Pipelines Trained on Spectroscopically Classified Supernovae from the Pan-STARRS1 Medium-deep Survey

This study serves as a guide to developing and training classification algorithms for a wide range of SN types with a purely empirical training set, particularly one that is similar in its characteristics to the expected LSST main survey strategy.

Superluminous Supernovae in LSST: Rates, Detection Metrics, and Light-curve Modeling

We explore and demonstrate the capabilities of the upcoming Large Synoptic Survey Telescope (LSST) to study Type I superluminous supernovae (SLSNe). We fit the light curves of 58 known SLSNe at z ≈