Classification of a black hole spin out of its shadow using support vector machines

Abstract

We use Support Vector Machines (SVMs) to classify the spin of a black hole. The SVMs are trained and tested with a catalog of numerically generated images of black holes, assuming disk and spherical matter models with monochromatic emission with wavelength of 4mm. We determine the accuracy of the SVM to classify the spin in terms of the image resolution, for which we consider three resolutions of $16^2,32^2$ and $64^2$ pixels. Our approach is applied to the specific mass of the Supermassive Black Hole (SMBH) at the center of the Milky Way. Our findings are that when the distribution is a thin disk, the accuracy in the classification resists even the coarsest resolution with accuracy over 90\%, whereas for the spherical distribution it drops below 80\% for low and intermediate resolutions. The results show how the distribution of matter, the angle of vision and the image resolution influence the ease to determine the black hole spin.

arXiv comment6 pages, 5 figures. Accepted for publication in Phys. Rev. D

References in corpus (18)

• Event-horizon-scale structure in the supermassive black hole candidate at the Galactic Centre
• The ACS Fornax Cluster Survey. V. Measurement and Recalibration of Surface Brightness Fluctuations and a Precise Value of the Fornax--Virgo Relative Distance
• Jet Launching Structure Resolved Near the Supermassive Black Hole in M87
• Testing the No-Hair Theorem with Observations in the Electromagnetic Spectrum: II. Black-Hole Images
• The Submillimeter Bump in Sgr A* from Relativistic MHD Simulations
• 1.3 mm Wavelength VLBI of Sagittarius A*: Detection of Time-Variable Emission on Event Horizon Scales
• A Fast New Public Code for Computing Photon Orbits in a Kerr Spacetime
• The old nuclear star cluster in the Milky Way: dynamics, mass, statistical parallax, and black hole mass
• A public code for general relativistic, polarised radiative transfer around spinning black holes
• Plasma diagnostic potential of 2p4f in N${}^{+}$ -- accurate wavelengths and oscillator strengths
• The Power of Imaging: Constraining the Plasma Properties of GRMHD Simulations using EHT Observations of Sgr A*
• Modeling Seven Years of Event Horizon Telescope Observations with Radiatively Inefficient Accretion Flow Models
• Tilted black hole accretion disc models of Sagittarius A*: time-variable millimetre to near-infrared emission
• Event Horizon Telescope Observations as Probes for Quantum Structure of Astrophysical Black Holes
• The puzzling case of the radio-loud QSO 3C 186: a gravitational wave recoiling black hole in a young radio source?
• Constraining the distribution of dark matter at the Galactic centre using the high-resolution Event Horizon Telescope
• Principal Component Analysis as a Tool for Characterizing Black Hole Images and Variability
• Characterizing the velocity of a wandering black hole and properties of the surrounding medium using convolutional neural networks

Cited by in corpus (1)

• A machine-learning photometric classifier for massive stars in nearby galaxies I. The method