HOLISMOKES -- VII. Time-delay measurement of strongly lensed Type Ia supernovae using machine learning

TL;DR

This paper develops machine learning methods, specifically random forests, to accurately measure time delays in strongly lensed Type Ia supernovae, which can improve independent estimates of the Hubble constant.

Contribution

It introduces and compares neural network and random forest approaches for time-delay measurement, finding RF to be more accurate and suitable for real data applications.

Findings

Random forest achieves less than 1% bias in time-delay estimation.

Using three photometric bands reduces uncertainty to about 1 day.

RF method achieves approximately 1.5-day precision for typical sources.

Abstract

The Hubble constant ($H_0$) is one of the fundamental parameters in cosmology, but there is a heated debate around the $>$4$\sigma$ tension between the local Cepheid distance ladder and the early Universe measurements. Strongly lensed Type Ia supernovae (LSNe Ia) are an independent and direct way to measure $H_0$, where a time-delay measurement between the multiple supernova (SN) images is required. In this work, we present two machine learning approaches for measuring time delays in LSNe Ia, namely, a fully connected neural network (FCNN) and a random forest (RF). For the training of the FCNN and the RF, we simulate mock LSNe Ia from theoretical SN Ia models that include observational noise and microlensing. We test the generalizability of the machine learning models by using a final test set based on empirical LSN Ia light curves not used in the training process, and we find that only the RF provides a low enough bias to achieve precision cosmology; as such, RF is therefore preferred over our FCNN approach for applications to real systems. For the RF with single-band photometry in the $i$ band, we obtain an accuracy better than 1\% in all investigated cases for time delays longer than 15 days, assuming follow-up observations with a 5$\sigma$ point-source depth of 24.7, a two day cadence with a few random gaps, and a detection of the LSNe Ia 8 to 10 days before peak in the observer frame. In terms of precision, we can achieve an approximately 1.5-day uncertainty for a typical source redshift of $\sim$0.8 on the $i$ band under the same assumptions. To improve the measurement, we find that using three bands, where we train a RF for each band separately and combine them afterward, helps to reduce the uncertainty to $\sim$1.0 day. We have publicly released the microlensed spectra and light curves used in this work.