Unsupervised machine learning for transient discovery in Deeper, Wider, Faster light curves

Abstract

Identification of anomalous light curves within time-domain surveys is often challenging. In addition, with the growing number of wide-field surveys and the volume of data produced exceeding astronomers ability for manual evaluation, outlier and anomaly detection is becoming vital for transient science. We present an unsupervised method for transient discovery using a clustering technique and the Astronomaly package. As proof of concept, we evaluate 85553 minute-cadenced light curves collected over two 1.5 hour periods as part of the Deeper, Wider, Faster program, using two different telescope dithering strategies. By combining the clustering technique HDBSCAN with the isolation forest anomaly detection algorithm via the visual interface of Astronomaly, we are able to rapidly isolate anomalous sources for further analysis. We successfully recover the known variable sources, across a range of catalogues from within the fields, and find a further 7 uncatalogued variables and two stellar flare events, including a rarely observed ultra fast flare (5 minute) from a likely M-dwarf.

Accepted 7 Aug 2020, 19 pages, 8 figures,

References in corpus (17)

• The Zwicky Transient Facility: System Overview, Performance, and First Results
• A bright millisecond radio burst of extragalactic origin
• The K2 Mission: Characterization and Early results
• The Zwicky Transient Facility: Science Objectives
• SkyMapper Southern Survey: Second Data Release (DR2)
• Follow up of GW170817 and its electromagnetic counterpart by Australian-led observing programs
• Automated supervised classification of variable stars I. Methodology
• The EPOCH Project: I. Periodic variable stars in the EROS-2 LMC database
• Photometric classification of type Ia supernovae in the SuperNova Legacy Survey with supervised learning
• Systematic Serendipity: A Test of Unsupervised Machine Learning as a Method for Anomaly Detection
• An improved quasar detection method in EROS-2 and MACHO LMC datasets
• Unsupervised Classification of Variable Stars
• Optical Observations of Gamma-Ray Bursts, the Discovery of Supernovae 2005bv, 2005ee, and 2006ak, and Searches for Transients Using the "MASTER" Robotic Telescope
• Identification of RR Lyrae stars in multiband, sparsely-sampled data from the Dark Energy Survey using template fitting and Random Forest classification
• Mary, a pipeline to aid discovery of optical transients
• An optical search for transients lasting a few seconds
• Enabling near real-time remote search for fast transient events with lossy data compression