Understanding of the properties of neural network approaches for transient light curve approximations

Abstract

Modern-day time-domain photometric surveys collect a lot of observations of various astronomical objects and the coming era of large-scale surveys will provide even more information on their properties. Spectroscopic follow-ups are especially crucial for transients such as supernovae and most of these objects have not been subject to such studies. }{Flux time series are actively used as an affordable alternative for photometric classification and characterization, for instance, peak identifications and luminosity decline estimations. However, the collected time series are multidimensional and irregularly sampled, while also containing outliers and without any well-defined systematic uncertainties. This paper presents a search for the best-performing methods to approximate the observed light curves over time and wavelength for the purpose of generating time series with regular time steps in each passband.}{We examined several light curve approximation methods based on neural networks such as multilayer perceptrons, Bayesian neural networks, and normalizing flows to approximate observations of a single light curve. Test datasets include simulated PLAsTiCC and real Zwicky Transient Facility Bright Transient Survey light curves of transients.}{The tests demonstrate that even just a few observations are enough to fit the networks and improve the quality of approximation, compared to state-of-the-art models. The methods described in this work have a low computational complexity and are significantly faster than Gaussian processes. Additionally, we analyzed the performance of the approximation techniques from the perspective of further peak identification and transients classification. The study results have been released in an open and user-friendly Fulu Python library available on GitHub for the scientific community.

References in corpus (14)

• The Zwicky Transient Facility: Surveys and Scheduler
• Inferring probabilistic stellar rotation periods using Gaussian processes
• Early-time light curves of Type Ib/c supernovae from the SDSS-II Supernova Survey
• Results from the Supernova Photometric Classification Challenge
• A recurrent neural network for classification of unevenly sampled variable stars
• The Young Supernova Experiment: Survey Goals, Overview, and Operations
• The ANTARES Astronomical Time-Domain Event Broker
• Machine learning search for variable stars
• Scalable End-to-end Recurrent Neural Network for Variable star classification
• A Deep Learning Approach for Active Anomaly Detection of Extragalactic Transients
• Real-Time Detection of Anomalies in Large-Scale Transient Surveys
• Pan-chromatic photometric classification of supernovae from multiple surveys and transfer learning for future surveys
• What can Gaussian Processes really tell us about supernova lightcurves? Consequences for Type II(b) morphologies and genealogies
• SCONE: Supernova Classification with a Convolutional Neural Network

Cited by in corpus (2)

• Applications of machine learning in gravitational wave research with current interferometric detectors
• Gamma-Ray Burst Light Curve Reconstruction: A Comparative Machine and Deep Learning Analysis