AI-driven spatio-temporal engine for finding gravitationally lensed type Ia supernovae

Abstract

We present a spatio-temporal AI framework that concurrently exploits both the spatial and time-variable features of gravitationally lensed supernovae in optical images to ultimately aid in future discoveries of such exotic transients in wide-field surveys. Our spatio-temporal engine is designed using recurrent convolutional layers, while drawing from recent advances in variational inference to quantify approximate Bayesian uncertainties via a confidence score. Using simulated Young Supernova Experiment (YSE) images of lensed and non-lensed supernovae as a showcase, we find that the use of time-series images adds relevant information from time variability of spatial light distribution of partially blended images of lensed supernova, yielding a substantial gain of around 20 per cent in classification accuracy over single-epoch observations. Preliminary application of our network to mock observations from the Legacy Survey of Space and Time (LSST) results in detections with accuracy reaching around 99 percent. Our innovative deep learning machinery is versatile and can be employed to search for any class of sources which exhibit variability both in flux and spatial distribution of light.

14 pages, 13 figures, 2 tables. Accepted for publication in MNRAS

References in corpus (18)

• Multiple Images of a Highly Magnified Supernova Formed by an Early-Type Cluster Galaxy Lens
• Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
• Uncertainties in Parameters Estimated with Neural Networks: Application to Strong Gravitational Lensing
• Detection of the Gravitational Lens Magnifying a Type Ia Supernova
• Microlensing of Lensed Supernovae
• How to Find Gravitationally Lensed Type Ia Supernovae
• Using Convolutional Neural Networks to identify Gravitational Lenses in Astronomical images
• Turning Gravitationally Lensed Supernovae into Cosmological Probes
• Interpreting the strongly lensed supernova iPTF16geu: time delay predictions, microlensing, and lensing rates
• The use of convolutional neural networks for modelling large optically-selected strong galaxy-lens samples
• Improved time-delay lens modelling and $H_0$ inference with transient sources
• Machine learning astrophysics from 21 cm lightcones: impact of network architectures and signal contamination
• Transient-optimised real-bogus classification with Bayesian Convolutional Neural Networks -- sifting the GOTO candidate stream
• Large-Scale Gravitational Lens Modeling with Bayesian Neural Networks for Accurate and Precise Inference of the Hubble Constant
• Strong lens modelling: comparing and combining Bayesian neural networks and parametric profile fitting
• Auto-identification of unphysical source reconstructions in strong gravitational lens modelling
• Difference Imaging of Lensed Quasar Candidates in the SDSS Supernova Survey Region
• Simulating time-varying strong lenses

Cited by in corpus (7)

• Strong lensing time-delay cosmography in the 2020s
• Strong gravitational lensing and microlensing of supernovae
• A search for gravitationally lensed supernovae within the Zwicky Transient Facility public survey
• DeepGraviLens: a Multi-Modal Architecture for Classifying Gravitational Lensing Data
• Detecting unresolved lensed SNe Ia in LSST using blended light curves
• DeepRed: an architecture for redshift estimation
• DeepZipper II: Searching for Lensed Supernovae in Dark Energy Survey Data with Deep Learning