Machine Learning Approach for Estimating Magnetic Field Strength in Galaxy Clusters from Synchrotron Emission

Year: 2025

Type: article

Abstract: Magnetic fields play a crucial role in various astrophysical processes within the intracluster medium, including heat conduction, cosmic-ray acceleration, and the generation of synchrotron radiation. However, measuring magnetic field strength is typically challenging due to the limited availability of Faraday rotation measure sources. To address the challenge, we propose a novel method that employs Convolutional Neural Networks (CNNs) alongside synchrotron emission observations to estimate magnetic field strengths in galaxy clusters. Our CNN model is trained on either magnetohydrodynamic (MHD) turbulence simulations or MHD galaxy cluster simulations, which incorporate complex dynamics such as cluster mergers and sloshing motions. The results demonstrate that CNNs can effectively estimate magnetic field strengths with mean-squared error of approximately 0.135 µG2, 0.044 µG2, and 0.02 µG2 for β = 100, 200, and 500 conditions, respectively. Additionally, we have confirmed that our CNN model remains robust against noise and variations in viewing angles with sufficient training, ensuring reliable performance under a wide range of observational conditions. We compare the CNN approach with the traditional magnetic field strength estimate method that assumes equipartition between cosmic-ray electron energy and magnetic field energy. In contrast to the equipartition method, this CNN approach relies on the morphological feature of synchrotron images, offering a new perspective for complementing traditional estimates and enhancing our understanding of cosmic-ray acceleration mechanisms.

Source: The Astrophysical Journal

DOI: 10.3847/1538-4357/adeb7a

Authors: Jiyao Zhang, Yue Hu, Alex Lazarian

Institutions: University of Pennsylvania, Institute for Advanced Study, University of Wisconsin–Madison

Language: English

Topic: Astrophysics and Cosmic Phenomena

Subfield: Nuclear and High Energy Physics

Field: Physics and Astronomy

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $4,499

Funders: National Science Foundation, National Aeronautics and Space Administration, National Centre for Supercomputing Applications, Space Telescope Science Institute, San Diego Supercomputer Center, Office of Advanced Cyberinfrastructure

OpenAlex ID: W4413304016