A proof-of-concept neural network for inferring parameters of a black hole from partial interferometric images of its shadow

Abstract

We test the possibility of using a convolutional neural network to infer the inclination angle of a black hole directly from the incomplete image of the black hole's shadow in the $uv$-plane. To this end, we develop a proof-of-concept network and use it to explicitly find how the error depends on the degree of coverage, type of input and coverage pattern. We arrive at a typical error of $10^{\circ }$ at a level of absolute coverage $1\%$ (for a pattern covering a central part of the $uv$-plane), $0.3\%$ (pattern covering the central part and the periphery, the $0.3\%$ referring to the central part only), and $14\%$ (uniform pattern). These numbers refer to a network that takes both amplitude and phase of the visibility function as inputs. We find that this type of network works best in terms of the error itself and its distribution for different angles. In addition, the same type of network demonstrates similarly good performance on highly blurred images mimicking sources nearing being unresolved. In terms of coverage, the magnitude of the error does not change much as one goes from the central pattern to the uniform one. We argue that this may be due to the presence of a typical scale which can be mostly learned by the network from the central part alone.

arXiv comment12 pages, 10 figures. For the code and trained models, see https://bitbucket.org/cosmoVlad/neuro-repo

References in corpus (41)

• The NumPy array: a structure for efficient numerical computation
• First M87 Event Horizon Telescope Results. I. The Shadow of the Supermassive Black Hole
• Coevolution (Or Not) of Supermassive Black Holes and Host Galaxies
• First M87 Event Horizon Telescope Results. VI. The Shadow and Mass of the Central Black Hole
• First M87 Event Horizon Telescope Results. IV. Imaging the Central Supermassive Black Hole
• First M87 Event Horizon Telescope Results. V. Physical Origin of the Asymmetric Ring
• The Galactic Center Massive Black Hole and Nuclear Star Cluster
• First M87 Event Horizon Telescope Results. II. Array and Instrumentation
• First M87 Event Horizon Telescope Results. III. Data Processing and Calibration
• Event-horizon-scale structure in the supermassive black hole candidate at the Galactic Centre
• Jet Launching Structure Resolved Near the Supermassive Black Hole in M87
• The Event Horizon General Relativistic Magnetohydrodynamic Code Comparison Project
• Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
• The Shadow of a Spherically Accreting Black Hole
• 1.3 mm Wavelength VLBI of Sagittarius A*: Detection of Time-Variable Emission on Event Horizon Scales
• CMU DeepLens: Deep Learning For Automatic Image-based Galaxy-Galaxy Strong Lens Finding
• Finding Strong Gravitational Lenses in the Kilo Degree Survey with Convolutional Neural Networks
• Uncertainties in Parameters Estimated with Neural Networks: Application to Strong Gravitational Lensing
• Dynamical Measurements of Black Hole Masses in Four Brightest Cluster Galaxies at 100 Mpc
• Finding strong lenses in CFHTLS using convolutional neural networks
• 230 GHz VLBI observations of M87: event-horizon-scale structure at the enhanced very-high-energy $\gamma$-ray state in 2012
• The Size, Shape, and Scattering of Sagittarius A* at 86 GHz: First VLBI with ALMA
• Recurrent Inference Machines for Solving Inverse Problems
• Detection of intrinsic source structure at ~3 Schwarzschild radii with Millimeter-VLBI observations of SAGITTARIUS A*
• Deep Convolutional Neural Networks as strong gravitational lens detectors
• LensExtractor: A Convolutional Neural Network in Search of Strong Gravitational Lenses
• Painting galaxies into dark matter halos using machine learning
• A geometric crescent model for black hole images
• Data-Driven Reconstruction of Gravitationally Lensed Galaxies using Recurrent Inference Machines
• Imaging Black Holes and Jets with a VLBI Array Including Multiple Space-Based Telescopes
• A volumetric deep Convolutional Neural Network for simulation of mock dark matter halo catalogues
• Metrics and Motivations for Earth-Space VLBI: Time-Resolving Sgr A* with the Event Horizon Telescope
• The Chinese space millimeter-wavelength VLBI array - a step toward imaging the most compact astronomical objects
• Deep Horizon; a machine learning network that recovers accreting black hole parameters
• Asymmetric structure in Sgr A* at 3mm from closure phase measurements with VLBA, GBT and LMT
• Using Deep Neural Networks to compute the mass of forming planets
• Analyzing interferometric observations of strong gravitational lenses with recurrent and convolutional neural networks
• Space very long baseline interferometry in China
• Finding Black Holes with Black Boxes -- Using Machine Learning to Identify Globular Clusters with Black Hole Subsystems
• An Illustrated History of Black Hole Imaging : Personal Recollections (1972-2002)
• A proof-of-concept neural network for inferring parameters of a black hole from partial interferometric images of its shadow

Cited by in corpus (2)

• Deep learning inference with the Event Horizon Telescope II. The Zingularity framework for Bayesian artificial neural networks
• A proof-of-concept neural network for inferring parameters of a black hole from partial interferometric images of its shadow