Scalable and Robust Multiband Modeling of AGN Light Curves in Rubin-LSST

TL;DR

The paper addresses the challenge of extracting stochastic AGN variability properties and interband continuum lags from LSST-scale, multiband light curves. It introduces EzTaoX, a multiband Gaussian-process framework that uses a DRW-like latent kernel and a lag parameter to jointly model variability and interband delays, with the likelihood evaluated in a 1D GP after band-shifting. Implemented in JAX via tinygp and the accelerated celerite algorithm, EzTaoX achieves $\sim 10^2$-$10^4\times$ CPU speedups over prior tools and accommodates CARMA kernels for flexible PSDs. This enables CRM and lag measurements for all LSST AGNs and supports high-cadence variability studies to identify low-mass AGNs, advancing our understanding of accretion-disk geometry and SMBH demographics in the LSST era.

Abstract

The Vera C. Rubin Observatory's Legacy Survey of Space and Time (LSST) will monitor tens of millions of active galactic nuclei (AGNs) for a period of 10 years with an average cadence of 3 days in six broad photometric bands. This unprecedented dataset will enable robust characterizations of AGN UV/optical variability across a wide range of AGN physical properties. However, existing tools for modeling AGN light curves are not yet capable of fully leveraging the volume, cadence, and multiband nature of LSST data. We present EzTaoX, a scalable light curve modeling tool designed to take advantage of LSST's multiband observations to simultaneously characterize AGN UV/optical stochastic variability and measure interband time delays. EzTaoX achieves a speed increase of $\sim 10^2-10^4 \times$ on CPUs over current tools with similar capabilities, while maintaining equal or better accuracy in recovering simulated variability properties. This performance gain enables continuum time-delay measurements for all AGNs discovered by LSST -- both in the Wide Fast Deep survey and the Deep Drilling Fields -- thereby opening new opportunities to probe AGN accretion-flow geometries. In addition, EzTaoX's multiband capability allows robust characterization of AGN stochastic variability down to hourly timescales, facilitating the identification of accreting low-mass AGNs -- such as those residing in dwarf galaxies -- through their distinctive variability signatures.