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

2025-01-27

AI Summary

Accurately estimating the bulge-to-total flux ratio, half-light radius, and total flux of active galactic nucleus (AGN) host galaxies at redshifts $z < 1.4$ remains computationally expensive and non-robust with conventional fitting methods. Method: We propose PSFGAN+GaMPEN—a novel hybrid architecture combining generative point-source–galaxy decomposition (PSFGAN) with Bayesian morphological parameter inference (GaMPEN). The framework employs simulation-based pretraining followed by transfer learning on real data, augmented with multi-redshift binning for improved cosmological modeling. Contribution/Results: Validated on Hyper Suprime-Cam (HSC) wide-field survey data, our method achieves photometric and structural accuracy comparable to GALFIT while accelerating inference by over three orders of magnitude. It exhibits strong generalizability across diverse survey configurations and seamlessly adapts to next-generation facilities—including LSST, Euclid, and Roman—enabling scalable, end-to-end statistical analysis of large AGN host galaxy samples.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Deep Neural Architectures and Foundation Models
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

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 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 $sim 20,000$ 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 datasets 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.

Problem

• Active Galactic Nuclei (AGN)
• Morphology
• Luminosity

Innovation

• Intelligent Learning System
• PSFGAN and GaMPEN Tools
• Efficient and Adaptive Processing