EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automatic Machine Learning Framework to Study Morphological Parameters of AGN Host Galaxies within z < 1.4 in the Hyper Supreme-Cam Wide Survey

Chuan 川 Tian 田, C. Megan Urry, Aritra Ghosh, Daisuke Nagai, Tonima T. Ananna, Meredith C. Powell, Connor Auge, Aayush Mishra, David B. Sanders, Nico Cappelluti, Kevin Schawinski

The Astrophysical Journal · 01.03.2025 · 981 (1) · 5

DOI: 10.3847/1538-4357/adaec0 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Astrophysical Journal, online erschienen am 21.02.2025. Verfasst von Chuan 川 Tian 田 und 10 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation, National Aeronautics and Space Administration.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We present a composite machine learning framework to estimate posterior probability distributions of bulge-to-total light ratio, half-light radius, and flux for active galactic nucleus (AGN) host galaxies within z < 1.4 and m < 23 in the Hyper Supreme-Cam (HSC) Wide survey. We divide the data into five redshift bins: low (0 < z < 0.25), mid (0.25 < z < 0.5), high (0.5 < z < 0.9), extra (0.9 < z < 1.1), and extreme (1.1 < z < 1.4), and train our models independently in each bin. We use PSFGAN to decompose the AGN point-source light from its host galaxy, and invoke the Galaxy Morphology Posterior Estimation Network (GaMPEN) to estimate morphological parameters of the recovered host galaxy. We first trained our models on simulated data, and then fine-tuned our algorithm via transfer learning using labeled real data. To create training labels for transfer learning, we used GALFIT to fit ∼20,000 real HSC galaxies in each redshift bin. We comprehensively examined that the predicted values from our final models agree well with the GALFIT values for the vast majority of cases. Our PSFGAN + GaMPEN framework runs at least three orders of magnitude faster than traditional light-profile fitting methods, and can be easily retrained for other morphological parameters or on other data sets with diverse ranges of resolutions, seeing conditions, and signal-to-noise ratios, making it an ideal tool for analyzing AGN host galaxies from large surveys coming soon from the Rubin-LSST, Euclid, and Roman telescopes.

Förderung

  • National Science Foundation
  • National Aeronautics and Space Administration

Zitieren

APA

田, C. 川. T., Urry, C. M., Ghosh, A., Nagai, D., Ananna, T. T., Powell, M. C., Auge, C., Mishra, A., Sanders, D. B., Cappelluti, N., & Schawinski, K. (2025). Automatic Machine Learning Framework to Study Morphological Parameters of AGN Host Galaxies within z < 1.4 in the Hyper Supreme-Cam Wide Survey. The Astrophysical Journal, 981(1), 5. https://doi.org/10.3847/1538-4357/adaec0

Vancouver

田 C川T, Urry CM, Ghosh A, Nagai D, Ananna TT, Powell MC, et al. Automatic Machine Learning Framework to Study Morphological Parameters of AGN Host Galaxies within z < 1.4 in the Hyper Supreme-Cam Wide Survey. The Astrophysical Journal. 2025;981(1):5. doi:10.3847/1538-4357/adaec0

BibTeX
@article{2025,
  author = {田, Chuan 川 Tian and Urry, C. Megan and Ghosh, Aritra and Nagai, Daisuke and Ananna, Tonima T. and Powell, Meredith C. and Auge, Connor and Mishra, Aayush and Sanders, David B. and Cappelluti, Nico and Schawinski, Kevin},
  title = {Automatic Machine Learning Framework to Study Morphological Parameters of AGN Host Galaxies within z < 1.4 in the Hyper Supreme-Cam Wide Survey},
  journal = {The Astrophysical Journal},
  year = {2025},
  volume = {981},
  number = {1},
  pages = {5},
  doi = {10.3847/1538-4357/adaec0}
}
Kostenlos starten →