Joint Modeling of Quasar Variability and Accretion Disk Reprocessing using Latent Stochastic Differential Equations
arXiv:2410.18423 · doi:10.3847/1538-4357/addabc
Abstract
Quasars are bright active galactic nuclei powered by the accretion of matter around supermassive black holes at the center of galaxies. Their stochastic brightness variability depends on the physical properties of the accretion disk and black hole. The upcoming Rubin Observatory Legacy Survey of Space and Time (LSST) is expected to observe tens of millions of quasars, so there is a need for efficient techniques like machine learning that can handle the large volume of data. Quasar variability is believed to be driven by an X-ray corona, which is reprocessed by the accretion disk and emitted as UV/optical variability. We are the first to introduce an auto-differentiable simulation of the accretion disk and reprocessing. We use the simulation as a direct component of our neural network to jointly model the driving variability and reprocessing, trained with supervised learning on simulated LSST-like 10 yr quasar light curves. We encode the light curves using a transformer encoder, and the driving variability is reconstructed using latent stochastic differential equations, a physically motivated generative deep learning method that can model continuous-time stochastic dynamics. By embedding the physical processes of the driving signal and reprocessing into our network, we achieve a model that is more robust and interpretable. We demonstrate that our model outperforms a Gaussian process regression baseline and can infer accretion disk parameters and time delays between wave bands, even for out-of-distribution driving signals. Our approach provides a powerful framework that can be adapted to solve other inverse problems in multivariate time series.
28 pages, 10 figures
References in corpus (67)
- SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
- Array Programming with NumPy
- The Astropy Project: Building an inclusive, open-science project and status of the v2.0 core package
- LSST: from Science Drivers to Reference Design and Anticipated Data Products
- A luminous quasar at a redshift of z = 7.085
- A Unified Model for the Evolution of Galaxies and Quasars
- An 800-million-solar-mass black hole in a significantly neutral Universe at redshift 7.5
- Fast and scalable Gaussian process modeling with applications to astronomical time series
- Modeling the Time Variability of SDSS Stripe 82 Quasars as a Damped Random Walk
- Foundations of Black Hole Accretion Disk Theory
- Combined Long and Short Timescale X-ray Variability of NGC4051 with RXTE and XMM-Newton
- An Alternative Approach To Measuring Reverberation Lags in Active Galactic Nuclei
- Is Quasar Optical Variability a Damped Random Walk?
- Space Telescope and Optical Reverberation Mapping Project. III. Optical Continuum Emission and Broad-Band Time Delays in NGC 5548
- Testing thermal reprocessing in AGN accretion discs
- Magnetic Stress at the Marginally Stable Orbit: Altered Disk Structure, Radiation, and Black Hole Spin Evolution
- Reverberation mapping of Active Galactic Nuclei: from X-ray corona to dusty torus
- MCG-6-30-15: Long Timescale X-Ray Variability, Black Hole Mass and AGN High States
- The Spatial Structure of An Accretion Disk
- The Kepler Light Curves of AGN: A Detailed Analysis
- On the Relationship between Galaxy Formation and Quasar Evolution
- The relationship between X-ray variability amplitude and black hole mass in active galactic nuclei
- Using quasar X-ray and UV flux measurements to constrain cosmological model parameters
- Improving Damped Random Walk parameters for SDSS Stripe 82 Quasars with Pan-STARRS1
- Quasar Accretion Disk Sizes From Continuum Reverberation Mapping From the Dark Energy Survey
- Application of Stochastic Modeling to Analysis of Photometric Reverberation Mapping Data
- Accretion Disc Time Lag Distributions: Applying CREAM to Simulated AGN Light Curves
- Continuum Reverberation Mapping of the Accretion Disks in Two Seyfert 1 Galaxies
- Optical Variability of Quasars with 20-Year Photometric Light Curves
- Microlensing Evidence That A Type 1 Quasar Is Viewed Face On
- Modelling type 1 quasar colours in the era of Rubin and Euclid
- Data-Driven Reconstruction of Gravitationally Lensed Galaxies using Recurrent Inference Machines
- Examining AGN UV/optical Variability Beyond the Simple Damped Random Walk
- Accretion Disk Sizes from Continuum Reverberation Mapping of AGN Selected from the ZTF Survey
- Multi-timescale X-ray reverberation mapping of accreting black holes
- Hierarchical Inference With Bayesian Neural Networks: An Application to Strong Gravitational Lensing
- Accretion Disk Size Measurement and Time Delays in the Lensed Quasar WFI 2033-4723
- Searching for changing-state AGNs in massive datasets -- I: applying deep learning and anomaly detection techniques to find AGNs with anomalous variability behaviours
- The Structure of HE 1104-1805 from Infrared to X-Ray
- General relativistic spectra of accretion disks around rotating neutron stars
- Thin accretion disk luminosity and its image around rotating black holes in perfect fluid dark matter
- Winds Can "Blow Up" AGN Accretion Disk Sizes
- Accretion Disk Size Measurements of Active Galactic Nuclei Monitored by the Zwicky Transient Facility
- Deep modeling of quasar variability
- Current and future applications of Reverberation-mapped quasars in Cosmology
- Quasar Microlensing Variability Studies Favor Shallow Accretion Disk Temperature Profiles
- Structure of the Accretion Disk in the Lensed Quasar Q2237+0305 from Multi-Epoch and Multi-Wavelength Narrow Band Photometry
- Reconciling the Quasar Microlensing Disc Size Problem with a Wind Model of Active Galactic Nucleus
- A forward modelling approach to AGN variability -- Method description and early applications
- Estimating the size of X-ray lamppost coronae in active galactic nuclei
- Quasar microlensing light curve analysis using deep machine learning
- Testing wind as an explanation for the spin problem in the continuum-fitting method
- A unified accretion disc model for supermassive black holes in galaxy formation simulations: method and implementation
- Estimating AGN Black Hole Masses via Continuum Reverberation Mapping in the Era of LSST
- Expectations for time-delay measurements in active galactic nuclei with the Vera Rubin Observatory
- The X-ray Power Spectral Density Function of the Seyfert Active Galactic Nucleus NGC 7469
- LSST Cadence Strategy Evaluations for AGN Time-series Data in Wide-Fast-Deep Field
- A Negative Long Lag from the Optical to the UV Continuum in Fairall 9
- Latent Stochastic Differential Equations for Modeling Quasar Variability and Inferring Black Hole Properties
- Pixelated Reconstruction of Foreground Density and Background Surface Brightness in Gravitational Lensing Systems using Recurrent Inference Machines
- Resolving the Vicinity of Supermassive Black Holes with Gravitational Microlensing
- Conditional Neural Process for non-parametric modeling of AGN light curve
- Exploring the Link between the X-ray Power Spectra and Energy Spectra of Active Galactic Nuclei
- The relationship of SMBHs and host galaxies at in the deep optical variability-selected AGN sample in the COSMOS field
- High frequency breaks in optical active galactic nuclei power spectral density
- Predicting High-magnification Events in Microlensed Quasars in the Era of LSST using Recurrent Neural Networks
- Amoeba: An AGN Model of Optical Emissions Beyond steady-state Accretion discs