Rapid Spectral Parameter Prediction for Black Hole X-Ray Binaries using Physicalised Autoencoders

Abstract

Black hole X-ray binaries (BHBs) offer insights into extreme gravitational environments and the testing of general relativity. The X-ray spectrum collected by NICER offers valuable information on the properties and behaviour of BHBs through spectral fitting. However, traditional spectral fitting methods are slow and scale poorly with model complexity. This paper presents a new semi-supervised autoencoder neural network for parameter prediction and spectral reconstruction of BHBs, showing an improvement of up to a factor of 2,700 in speed while maintaining comparable accuracy. The approach maps the spectral features from the numerous outbursts catalogued by NICER and generalises them to new systems for efficient and accurate spectral fitting. The effectiveness of this approach is demonstrated in the spectral fitting of BHBs and holds promise for use in other areas of astronomy and physics for categorising large datasets.

13 pages, 13 figures

References in corpus (14)

• WaveNet: A Generative Model for Raw Audio
• X-ray Properties of Black-Hole Binaries
• The James Webb Space Telescope
• Modelling the behaviour of accretion flows in X-ray binaries
• On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
• Testing Accretion Disk Theory in Black Hole X-ray Binaries
• Testing the space-time geometry around black hole candidates with the analysis of the broad K$\alpha$ iron line
• Self-Consistent Black Hole Accretion Spectral Models and the Forgotten Role of Coronal Comptonization of Reflection Emission
• Re-estimating the Spin Parameter of the Black Hole in Cygnus X-1
• Schwarzschild and Kerr Solutions of Einstein's Field Equation -- an introduction
• Line Emission Mapper (LEM): Probing the physics of cosmic ecosystems
• The Importance of Being Interpretable: Toward An Understandable Machine Learning Encoder for Galaxy Cluster Cosmology
• AGN X-ray Spectroscopy with Neural Networks
• The Wide Field Imager Instrument for Athena

Cited by in corpus (1)

• Extracting latent representations from X-ray spectra. Classification, regression, and accretion signatures of Chandra sources