Conditional Neural Process for non-parametric modeling of AGN light curve

Abstract

The consequences of complex disturbed environments in the vicinity of a supermassive black hole are not well represented by standard statistical models of optical variability in active galactic nuclei (AGN). Thus, developing new methodologies for investigating and modeling AGN light curves is crucial. Conditional Neural Processes (CNPs) are nonlinear function models that forecast stochastic time-series based on a finite amount of known data without the use of any additional parameters or prior knowledge (kernels). We provide a CNP algorithm that is specifically designed for simulating AGN light curves. It was trained using data from the All-Sky Automated Survey for Supernovae, which included 153 AGN. We present CNP modeling performance for a subsample of five AGNs with distinctive difficult-to-model properties. The performance of CNP in predicting temporal flux fluctuation was assessed using a minimizing loss function, and the results demonstrated the algorithm's usefulness. Our preliminary parallelization experiments show that CNP can efficiently handle large amounts of data. These results imply that CNP can be more effective than standard tools in modeling large volumes of AGN data (as anticipated from time-domain surveys such as the Vera C. Rubin Observatory's Legacy Survey of Space and Time).

arXiv commentThe manuscript was accepted for publication in the Astronomische Nachrichten Special Issue

References in corpus (38)

• Adam: A Method for Stochastic Optimization
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Unified Schemes for Radio-Loud Active Galactic Nuclei
• LSST: from Science Drivers to Reference Design and Anticipated Data Products
• The Man Behind the Curtain: X-rays Drive the UV through NIR Variability in the 2013 AGN Outburst in NGC 2617
• Central Masses and Broad-Line Region Sizes of Active Galactic Nuclei. II. A Homogeneous Analysis of a Large Reverberation-Mapping Database
• Spectral Energy Distributions and Multiwavelength Selection of Type 1 Quasars
• The All-Sky Automated Survey for Supernovae (ASAS-SN) Light Curve Server v1.0
• The Low-Luminosity End of the Radius-Luminosity Relationship for Active Galactic Nuclei
• Are the Variations in Quasar Optical Flux Driven by Thermal Fluctuations?
• A Structure for Quasars
• A systematic search for close supermassive black hole binaries in the Catalina Real-Time Transient Survey
• Swift BAT Survey of AGN
• Optical Continuum and Emission-Line Variability of Seyfert 1 Galaxies
• The New Generation Atlas of Quasar Spectral Energy Distributions from Radio to X-rays
• The First Swift Intensive AGN Accretion Disk Reverberation Mapping Survey
• Diverse Broad Line Region Kinematic Signatures From Reverberation Mapping
• A Cutoff in the X-ray Fluctuation Power Density Spectrum of the Seyfert 1 Galaxy NGC 3516
• A Stochastic Model for the Luminosity Fluctuations of Accreting Black Holes
• Reverberation Mapping of Optical Emission Lines in Five Active Galaxies
• New changing look case in NGC 1566
• AGN Variability Analysis Handbook
• Quasar Variability in the Framework of Poissonian Models
• The QUEST-La Silla AGN variability survey: connection between AGN variability and black hole physical properties
• The ASAS-SN Bright Supernova Catalog -- III. 2016
• Long-term optical spectral monitoring of a changing-look AGN NGC 3516 I: Continuum and broad-line flux variability
• A parallax distance to 3C 273 through spectroastrometry and reverberation mapping
• Searching for changing-state AGNs in massive datasets -- I: applying deep learning and anomaly detection techniques to find AGNs with anomalous variability behaviours
• The optical variability of Supermassive Black Hole Binary Candidate PG1302-102: Periodicity and perturbation in the light curve
• Deep modeling of quasar variability
• Oscillatory patterns in the light curves of 5 long-term monitored type 1 AGN
• Photometric redshift estimation using Gaussian processes
• A flare in the optical spotted in the changing-look Seyfert NGC 3516
• A Method to Measure the Unbiased Decorrelation Timescale of the AGN Variable Signal from Structure Functions
• Multi-wavelength Variability of the Broad Line Radio Galaxy 3C 120
• H$\alpha$ Reverberation Mapping of the Intermediate-Mass Active Galactic Nucleus in NGC 4395
• Active Galaxy Science in the LSST Deep-Drilling Fields: Footprints, Cadence Requirements, and Total-Depth Requirements
• On possible proxies of AGN light curves cadence selection in future time domain surveys

Cited by in corpus (5)

• The LSST era of supermassive black holes accretion-disk reverberation mapping
• Latent Stochastic Differential Equations for Modeling Quasar Variability and Inferring Black Hole Properties
• Parameterizing pressure-temperature profiles of exoplanet atmospheres with neural networks
• Joint Modeling of Quasar Variability and Accretion Disk Reprocessing using Latent Stochastic Differential Equations
• Modeling quasar variability through self-organizing map-based process