Skip to content
DraconiticResearch
Search Sources API
197,768 studies31 sourcesUpdated 6 min ago
Peer-reviewedCC BY 4.0The Astrophysical Journal

Measuring the Vertical Structure of Active Galactic Nuclei Disks with Transformer Models and the Vera C. Rubin Observatory

  • Amy Secunda1
  • Sebastian Wagner-Carena1
  • Helen Qu1
  • Shirley Ho1,2,3
  1. 1Flatiron Institute
  2. 2Princeton University
  3. 3New York University
Open at sourcePDFDOICite

Abstract

Reverberation mapping is one of the main techniques used to study active galactic nuclei (AGN) accretion disks. Traditional continuum reverberation mapping uses short lags between variability in different wavelength AGN light curves on the light-crossing timescale of the disk to measure the radial structure of the disk. The harder-to-detect long negative lag measures lags on the longer inflow timescale, allowing us to map the vertical structure of AGN disks and test the standard thin disk model. The Vera Rubin Observatory, with its six wavebands, long baseline, and high cadence, will revolutionize our ability to detect long lags. However, many challenges remain to detect these long lags, such as seasonal gaps in Rubin light curves, the weak signal strength of the long lag relative to the short lag, and the enormous influx of data for millions of AGN from Rubin. Machine learning techniques have the potential to solve these issues, but have yet to be applied to the long negative lag problem. We develop and train a transformer-based machine learning model to detect long and short lags in mock Rubin AGN light curves. Our model identifies whether a light curve in our test set has a long negative lag with 96% recall and 0.04% contamination, and is 98% accurate at predicting the true long lag. This accuracy is an enormous improvement over two baseline methods we test on the same mock light curves, the interpolated cross correlation function and javelin , which are only 54% and 21% accurate, respectively.

Related

  1. Vertical gradients of Galactic rotation from Gaia: The limiting-cone and comparison models
    Łukasz Bratek, Joanna Jałocha, Szymon Sikora +1
    Astronomy & AstrophysicsPeer-reviewedPublisher termsSolar & stellar physicsCrossref
  2. Measuring Precipitable Water Vapor through Dual-Band GPS at Rubin Observatory
    Anja Weyant, W. M. Wood-Vasey, Elana K. Urbach +2
    arXivPreprintarXiv licenceFull textInstrumentation & methodsarXiv
  3. The Missing MeV Window for Identifying Galactic PeVatrons: the need for a dedicated MeV Observatory
    Martina Cardillo, Riccardo Campana, Yuri Evangelista +1
    arXivPreprintarXiv licenceFull textHigh-energy astrophysicsInstrumentation & methodsarXiv
  4. Photometric redshifts for active galactic nuclei with LePHARE for the Vera C. Rubin Observatory
    R. Shirley, M. Salvato, J. Cohen-Tanugi +31
    arXivPreprintarXiv licenceFull textGalaxiesarXiv
  5. Photometric redshifts for active galactic nuclei with LePHARE for the Vera C. Rubin Observatory
    Shirley R., Salvato M., Cohen-Tanugi J. +31
    Astronomy & AstrophysicsPeer-reviewedCC BYFull text1 citedGalaxiesDOAJHAL

Cite

BibTeXRIS
BibTeX
@article{secunda2026measuring,
  title = {{Measuring the Vertical Structure of Active Galactic Nuclei Disks with Transformer Models and the Vera C. Rubin Observatory}},
  author = {Amy Secunda and Sebastian Wagner-Carena and Helen Qu and Shirley Ho},
  journal = {The Astrophysical Journal},
  year = {2026},
  month = oct,
  doi = {10.3847/1538-4357/ae9eac},
  url = {https://iopscience.iop.org/article/10.3847/1538-4357/ae9eac},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Measuring the Vertical Structure of Active Galactic Nuclei Disks with Transformer Models and the Vera C. Rubin Observatory
AU  - Amy Secunda
AU  - Sebastian Wagner-Carena
AU  - Helen Qu
AU  - Shirley Ho
PY  - 2026
DA  - 2026/10/13
JO  - The Astrophysical Journal
DO  - 10.3847/1538-4357/ae9eac
UR  - https://iopscience.iop.org/article/10.3847/1538-4357/ae9eac
AB  - Reverberation mapping is one of the main techniques used to study active galactic nuclei (AGN) accretion disks. Traditional continuum reverberation mapping uses short lags between variability in different wavelength AGN light curves on the light-crossing timescale of the disk to measure the radial structure of the disk. The harder-to-detect long negative lag measures lags on the longer inflow timescale, allowing us to map the vertical structure of AGN disks and test the standard thin disk model. The Vera Rubin Observatory, with its six wavebands, long baseline, and high cadence, will revolutionize our ability to detect long lags. However, many challenges remain to detect these long lags, such as seasonal gaps in Rubin light curves, the weak signal strength of the long lag relative to the short lag, and the enormous influx of data for millions of AGN from Rubin. Machine learning techniques have the potential to solve these issues, but have yet to be applied to the long negative lag problem. We develop and train a transformer-based machine learning model to detect long and short lags in mock Rubin AGN light curves. Our model identifies whether a light curve in our test set has a long negative lag with 96% recall and 0.04% contamination, and is 98% accurate at predicting the true long lag. This accuracy is an enormous improvement over two baseline methods we test on the same mock light curves, the interpolated cross correlation function and javelin , which are only 54% and 21% accurate, respectively.
SN  - 0004-637X
SN  - 1538-4357
ER  -