HOLISMOKES XVII: Detecting strongly lensed SNe Ia from time series of multi-band LSST-like imaging data

TL;DR

This paper presents a deep learning pipeline using ConvLSTM2D architecture to detect strongly lensed Type Ia supernovae in multi-band, multi-epoch imaging data, achieving high detection efficiency early in the observation sequence.

Contribution

The work introduces a novel deep learning method tailored for early detection of lensed SNe Ia in time-series imaging data, trained on realistic simulations matching LSST-like surveys.

Findings

High detection efficiency: >70% TPR by the 9th observation at 0.01% FPR.

Effective discrimination between lensed and unlensed SNe Ia, especially in larger separation systems.

Model applicable to any cadenced imaging survey, including LSST.

Abstract

Strong gravitationally lensed supernovae (LSNe), though rare, are exceptionally valuable probes for cosmology and astrophysics. Upcoming time-domain surveys like the Vera Rubin Observatory's Legacy Survey of Space and Time (LSST) offer a major opportunity to discover them in large numbers. Early identification is crucial for timely follow-up observations. We develop a deep learning pipeline to detect LSNe using multi-band, multi-epoch image cutouts. Our model is based on a 2D convolutional long short-term memory (ConvLSTM2D) architecture, designed to capture both spatial and temporal correlations in time-series imaging data. Predictions are made after each observation in the time series, with accuracy improving as more data arrive. We train the model on realistic simulations derived from Hyper Suprime-Cam (HSC) data, which closely matches LSST in depth and filters. This work focuses exclusively on Type Ia supernovae (SNe Ia). LSNe Ia are injected onto HSC luminous red galaxies (LRGs) at various phases of evolution to create positive examples. Negative examples include variable sources from HSC Transient Survey (including unclassified transients), and simulated unlensed SNe Ia in LRG and spiral galaxies. Our multi-band model shows rapid classification improvements during the initial few observations and quickly reaches high detection efficiency: at a fixed false-positive rate (FPR) of $0.01\%$, the true-positive rate (TPR) reaches $\gtrsim 60\%$ by the 7th observation and exceeds $\gtrsim 70\%$ by the 9th. Among the negative examples, SNe in LRGs remain the primary source of FPR, as they can resemble their lensed counterparts under certain conditions. The model detects quads more effectively than doubles and performs better on systems with larger image separations. Although trained and tested on HSC-like data, our approach applies to any cadenced imaging survey, particularly LSST.