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

TL;DR

This paper introduces an AI framework that combines spatial and temporal features to identify gravitationally lensed supernovae, significantly improving detection accuracy in wide-field astronomical surveys.

Contribution

The paper presents a novel spatio-temporal AI engine using recurrent convolutional layers and variational inference for Bayesian uncertainty quantification, enhancing detection of lensed supernovae.

Findings

20% accuracy improvement with time-series data

99% detection accuracy on LSST mock data

Versatile approach applicable to variable sources

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.