Fast and Flexible Inference Framework for Continuum Reverberation Mapping Using Simulation-based Inference with Deep Learning

Continuum reverberation mapping (CRM) of active galactic nuclei (AGN) monitors multiwavelength variability signatures to constrain accretion disk structure and supermassive black hole (SMBH) properties. The upcoming Vera Rubin Observatory’s Legacy Survey of Space and Time will survey tens of million...

Full description

Saved in:
Bibliographic Details
Main Authors: Jennifer I-Hsiu Li, Sean D. Johnson, Camille Avestruz, Sreevani Jarugula, Yue Shen, Elise Kesler, Zhuoqi (Will) Liu, Nishant Mishra
Format: Article
Language:English
Published: IOP Publishing 2024-01-01
Series:The Astrophysical Journal
Subjects:
Online Access:https://doi.org/10.3847/1538-4357/ad900d
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850257428135804928
author Jennifer I-Hsiu Li
Sean D. Johnson
Camille Avestruz
Sreevani Jarugula
Yue Shen
Elise Kesler
Zhuoqi (Will) Liu
Nishant Mishra
author_facet Jennifer I-Hsiu Li
Sean D. Johnson
Camille Avestruz
Sreevani Jarugula
Yue Shen
Elise Kesler
Zhuoqi (Will) Liu
Nishant Mishra
author_sort Jennifer I-Hsiu Li
collection DOAJ
description Continuum reverberation mapping (CRM) of active galactic nuclei (AGN) monitors multiwavelength variability signatures to constrain accretion disk structure and supermassive black hole (SMBH) properties. The upcoming Vera Rubin Observatory’s Legacy Survey of Space and Time will survey tens of millions of AGN over the next decade, with thousands of AGN monitored with almost daily cadence in the deep drilling fields. However, existing CRM methodologies often require long computation time and are not designed to handle such large amounts of data. In this paper, we present a fast and flexible inference framework for CRM using simulation-based inference (SBI) with deep learning to estimate SMBH properties from AGN light curves. We use a long short-term memory summary network to reduce the high dimensionality of the light curve data and then use a neural density estimator to estimate the posterior of SMBH parameters. Using simulated light curves, we find SBI can produce more accurate SMBH parameter estimation with 10 ^3 –10 ^5 times speed up in inference efficiency compared to traditional methods. The SBI framework is particularly suitable for wide-field CRM surveys as the light curves will have identical observing patterns, which can be incorporated into the SBI simulation. We explore the performance of our SBI model on light curves with irregular-sampled, realistic observing cadence and alternative variability characteristics to demonstrate the flexibility and limitation of the SBI framework.
format Article
id doaj-art-4c4e321623cb4d2191fc2ba96b352f0a
institution OA Journals
issn 1538-4357
language English
publishDate 2024-01-01
publisher IOP Publishing
record_format Article
series The Astrophysical Journal
spelling doaj-art-4c4e321623cb4d2191fc2ba96b352f0a2025-08-20T01:56:25ZengIOP PublishingThe Astrophysical Journal1538-43572024-01-01977222310.3847/1538-4357/ad900dFast and Flexible Inference Framework for Continuum Reverberation Mapping Using Simulation-based Inference with Deep LearningJennifer I-Hsiu Li0https://orcid.org/0000-0002-0311-2812Sean D. Johnson1https://orcid.org/0000-0001-9487-8583Camille Avestruz2https://orcid.org/0000-0001-8868-0810Sreevani Jarugula3https://orcid.org/0000-0002-5386-7076Yue Shen4https://orcid.org/0000-0003-1659-7035Elise Kesler5https://orcid.org/0000-0001-6846-9399Zhuoqi (Will) Liu6https://orcid.org/0000-0002-2662-9363Nishant Mishra7https://orcid.org/0000-0002-9141-9792Michigan Institute for Data Science, University of Michigan , Ann Arbor, MI 48109, USA; Department of Astronomy, University of Michigan , Ann Arbor, MI 48109, USA; Center for AstroPhysical Surveys, National Center for Supercomputing Applications, University of Illinois Urbana-Champaign , Urbana, IL, 61801, USADepartment of Astronomy, University of Michigan , Ann Arbor, MI 48109, USADepartment of Physics, University of Michigan , Ann Arbor, MI 48109, USA; Leinweber Center for Theoretical Physics, University of Michigan , Ann Arbor, MI 48109, USAFermi National Accelerator Laboratory , Batavia, IL 60510, USACenter for AstroPhysical Surveys, National Center for Supercomputing Applications, University of Illinois Urbana-Champaign , Urbana, IL, 61801, USA; Department of Astronomy, University of Illinois at Urbana-Champaign , Urbana, IL 61801, USADepartment of Astronomy, University of Michigan , Ann Arbor, MI 48109, USADepartment of Astronomy, University of Michigan , Ann Arbor, MI 48109, USADepartment of Astronomy, University of Michigan , Ann Arbor, MI 48109, USAContinuum reverberation mapping (CRM) of active galactic nuclei (AGN) monitors multiwavelength variability signatures to constrain accretion disk structure and supermassive black hole (SMBH) properties. The upcoming Vera Rubin Observatory’s Legacy Survey of Space and Time will survey tens of millions of AGN over the next decade, with thousands of AGN monitored with almost daily cadence in the deep drilling fields. However, existing CRM methodologies often require long computation time and are not designed to handle such large amounts of data. In this paper, we present a fast and flexible inference framework for CRM using simulation-based inference (SBI) with deep learning to estimate SMBH properties from AGN light curves. We use a long short-term memory summary network to reduce the high dimensionality of the light curve data and then use a neural density estimator to estimate the posterior of SMBH parameters. Using simulated light curves, we find SBI can produce more accurate SMBH parameter estimation with 10 ^3 –10 ^5 times speed up in inference efficiency compared to traditional methods. The SBI framework is particularly suitable for wide-field CRM surveys as the light curves will have identical observing patterns, which can be incorporated into the SBI simulation. We explore the performance of our SBI model on light curves with irregular-sampled, realistic observing cadence and alternative variability characteristics to demonstrate the flexibility and limitation of the SBI framework.https://doi.org/10.3847/1538-4357/ad900dReverberation mappingNeural networksSupermassive black holes
spellingShingle Jennifer I-Hsiu Li
Sean D. Johnson
Camille Avestruz
Sreevani Jarugula
Yue Shen
Elise Kesler
Zhuoqi (Will) Liu
Nishant Mishra
Fast and Flexible Inference Framework for Continuum Reverberation Mapping Using Simulation-based Inference with Deep Learning
The Astrophysical Journal
Reverberation mapping
Neural networks
Supermassive black holes
title Fast and Flexible Inference Framework for Continuum Reverberation Mapping Using Simulation-based Inference with Deep Learning
title_full Fast and Flexible Inference Framework for Continuum Reverberation Mapping Using Simulation-based Inference with Deep Learning
title_fullStr Fast and Flexible Inference Framework for Continuum Reverberation Mapping Using Simulation-based Inference with Deep Learning
title_full_unstemmed Fast and Flexible Inference Framework for Continuum Reverberation Mapping Using Simulation-based Inference with Deep Learning
title_short Fast and Flexible Inference Framework for Continuum Reverberation Mapping Using Simulation-based Inference with Deep Learning
title_sort fast and flexible inference framework for continuum reverberation mapping using simulation based inference with deep learning
topic Reverberation mapping
Neural networks
Supermassive black holes
url https://doi.org/10.3847/1538-4357/ad900d
work_keys_str_mv AT jenniferihsiuli fastandflexibleinferenceframeworkforcontinuumreverberationmappingusingsimulationbasedinferencewithdeeplearning
AT seandjohnson fastandflexibleinferenceframeworkforcontinuumreverberationmappingusingsimulationbasedinferencewithdeeplearning
AT camilleavestruz fastandflexibleinferenceframeworkforcontinuumreverberationmappingusingsimulationbasedinferencewithdeeplearning
AT sreevanijarugula fastandflexibleinferenceframeworkforcontinuumreverberationmappingusingsimulationbasedinferencewithdeeplearning
AT yueshen fastandflexibleinferenceframeworkforcontinuumreverberationmappingusingsimulationbasedinferencewithdeeplearning
AT elisekesler fastandflexibleinferenceframeworkforcontinuumreverberationmappingusingsimulationbasedinferencewithdeeplearning
AT zhuoqiwillliu fastandflexibleinferenceframeworkforcontinuumreverberationmappingusingsimulationbasedinferencewithdeeplearning
AT nishantmishra fastandflexibleinferenceframeworkforcontinuumreverberationmappingusingsimulationbasedinferencewithdeeplearning