Physical parameter regression from black hole images via a multiscale adaptive neural network

TL;DR

This paper introduces MANet, a deep learning framework with multiscale and attention mechanisms, to improve high-precision physical parameter regression from black hole images, addressing data scarcity and complex structures.

Contribution

The study presents a novel multiscale adaptive neural network architecture that enhances feature extraction and parameter estimation accuracy in black hole image analysis.

Findings

MANet outperforms baseline methods in accuracy and generalization.

The framework effectively captures fine-grained spatial features.

Experimental results demonstrate robustness to sparse and noisy data.

Abstract

High-precision regression of physical parameters from black hole images generated by General Relativistic Ray Tracing (GRRT) is essential for investigating spacetime curvature and advancing black hole astrophysics. However, due to limitations in observational resolution, high observational costs, and imbalanced distributions of positive and negative samples, black hole images often suffer from data scarcity, sparse parameter spaces, and complex structural characteristics. These factors pose significant challenges to conventional regression methods based on simplified physical models. To overcome these challenges, this study introduces Multiscale Adaptive Network (MANet) , a novel regression framework grounded in deep learning. MANet integrates an Adaptive Channel Attention (ACA) module to selectively enhance features in physically informative regions. Meanwhile, a Multiscale Enhancement Feature Pyramid (MEFP) is employed to capture fine-grained spatial structures such as photon rings and accretion disks, while alleviating information loss due to downsampling. Experimental evaluations on GRRT-simulated datasets demonstrate that MANet substantially improves parameter estimation accuracy and generalization capability in high-dimensional parameter spaces, outperforming existing baseline approaches. This framework presents a promising avenue for high-precision parameter regression in Event Horizon Telescope (EHT) data analysis and broader astrophysical imaging applications characterized by sparse and noisy data.