Next Generation Strong Lensing Time Delay Estimation with Gaussian Processes

TL;DR

This paper introduces a Gaussian Process cross-correlation method for estimating time delays in strong gravitational lensing, achieving high accuracy and robustness, crucial for precise cosmological measurements like the Hubble constant.

Contribution

The paper develops and validates a Gaussian Process-based technique for accurate, unbiased time delay estimation from noisy lightcurves, enhancing the reliability of cosmological inferences.

Findings

Bias within 0.1% for delay estimation

80% of delays within 1 day accuracy

Robust against cadence variations shorter than 6 days

Abstract

Strong gravitational lensing forms multiple, time delayed images of cosmological sources, with the "focal length" of the lens serving as a cosmological distance probe. Robust estimation of the time delay distance can tightly constrain the Hubble constant as well as the matter density and dark energy. Current and next generation surveys will find hundreds to thousands of lensed systems but accurate time delay estimation from noisy, gappy lightcurves is potentially a limiting systematic. Using a large sample of blinded lightcurves from the Strong Lens Time Delay Challenge we develop and demonstrate a Gaussian Process crosscorrelation technique that delivers an average bias within 0.1% depending on the sampling, necessary for subpercent Hubble constant determination. The fits are accurate (80% of them within 1 day) for delays from 5-100 days and robust against cadence variations shorter than 6 days. We study the effects of survey characteristics such as cadence, season, and campaign length, and derive requirements for time delay cosmology: in order not to bias the cosmology determination by $0.5\sigma$, the mean time delay fit accuracy must be better than 0.2%.