Searching for Changing-state AGNs in Massive Data Sets. I. Applying Deep Learning and Anomaly-detection Techniques to Find AGNs with Anomalous Variability Behaviors

@article{SanchezSaez2021SearchingFC,
  title={Searching for Changing-state AGNs in Massive Data Sets. I. Applying Deep Learning and Anomaly-detection Techniques to Find AGNs with Anomalous Variability Behaviors},
  author={P. S'anchez-S'aez and Hernan Lira and Luis Mart'i and N. S'anchez-Pi and J. Arredondo and Franz Erik Bauer and Amelia Bayo and Guillermo Cabrera-Vives and C. Donoso-Oliva and Pablo A. Est'evez and Susana Eyheramendy and Francisco F{\'o}rster and L. Hernandez-Garcia and Alejandra M. Mu{\~n}oz Arancibia and Manuel P'erez-Carrasco and Jorge R. Vergara},
  journal={The Astronomical Journal},
  year={2021},
  volume={162}
}
The classic classification scheme for active galactic nuclei (AGNs) was recently challenged by the discovery of the so-called changing-state (changing-look) AGNs. The physical mechanism behind this phenomenon is still a matter of open debate and the samples are too small and of serendipitous nature to provide robust answers. In order to tackle this problem, we need to design methods that are able to detect AGNs right in the act of changing state. Here we present an anomaly-detection technique… 

Finding active galactic nuclei through Fink

Results show that the designed feature space enables high performances of traditional machine learning algorithms in this binary classification task.

Changing-look Active Galactic Nuclei

Active Galactic Nuclei (AGN) are known to show flux variability over all observable timescales and across the entire electromagnetic spectrum. Over the past decade, a growing number of sources have

Outlier Detection based on Transformations for Astronomical Time Series

The proposed model outperforms state-of-the-art methods based on time series features and neural network approaches, reaching an average AUCPR of 0.89 for detecting outliers in the three datasets.

Conditional Neural Process for nonparametric modeling of active galactic nuclei light curves

1Department of Astronomy, Faculty of Mathematics, University of Belgrade, Studentski trg 16, 11000 Belgrade, Serbia 2Fellow of Chinese Academy of Sciences President’s International Fellowship

Searching for Anomalies in the ZTF Catalog of Periodic Variable Stars

Periodic variables illuminate the physical processes of stars throughout their lifetime. Wide-field surveys continue to increase our discovery rates of periodic variable stars. Automated approaches

References

SHOWING 1-10 OF 10 REFERENCES

The Physics and Evolution of Active Galactic Nuclei

Preface 1. Observations of active galactic nuclei 2. Nonthermal radiation processes 3. Black holes 4. Accretion disks 5. Physical processes in AGN gas and dust 6. The AGN family 7. Main components of

Google Colaboratory (Berkeley, CA: Apress)

  • 2019

2016, in Positioning and Power in Academic Publishing: Players, Agents and Agendas, ed

  • IOS Press,
  • 2016

2020 , arXiv e - prints , arXiv : 2006 . 12333

    Anomaly Detection Principles

    • Natur,
    • 2010

    2017, mwaskom/seaborn: v0.8.1 (September 2017)

    • 2017

    mwaskom/seaborn: v0

      2019 , arXiv e - prints , arXiv : 1909 . 13260

        Python reference manual (Centrum voor Wiskunde en Informatica Amsterdam)

        • 1995