Hybrid Approaches for Black Hole Spin Estimation: From Classical Spectroscopy to Physics-Informed Machine Learning

TL;DR

This paper introduces a hybrid physics-informed machine learning approach using PINNs for black hole spin estimation, improving accuracy, interpretability, and scalability over traditional methods.

Contribution

It develops a PINN model integrated with Teukolsky formalism for black hole spin estimation, demonstrating superior performance and physical consistency.

Findings

PINN achieves residual loss below 1e-7 and RMSE around 1e-6.

Outperforms classical and data-driven methods in AUC and sensitivity.

Exhibits better interpretability and generalizability with moderate computational cost.

Abstract

The measurement of black hole spin is considered one of the key problems in relativistic astrophysics. Existing methods, such as continuum fitting, X-ray reflection spectroscopy and quasi-periodic oscillation analysis, have systematic limitations in accuracy, interpretability and scalability. In this work, a hybrid approach is proposed in which theoretical models based on the Teukolsky formalism are integrated with Physics-Informed Neural Networks (PINNs). A PINN model is developed to solve the linearized spin problem in the scalar case, with physical constraints directly embedded into the training process. Annotated data are not required; instead, the model is trained using the differential operator and boundary conditions as supervision. It is demonstrated that the PINN converges reliably, with residual loss values below 1e-7 and a root mean squared error (RMSE) of the order of 1e-6 (final approx 5.4 x 1e-8). Benchmarking results indicate that the proposed method outperforms both classical and data-driven machine learning approaches in terms of AUC and sensitivity, while also exhibiting superior interpretability, generalizability and adherence to physical principles, with moderate computational cost. Potential extensions include integration with general relativistic magnetohydrodynamics (GRMHD) solvers and application to real observational data. These findings support the viability of physics-based machine learning as a robust framework for accurate and interpretable black hole spin estimation.