Black Hole Weather Forecasting with Deep Learning: A Pilot Study

Abstract

In this pilot study, we investigate the use of a deep learning (DL) model to temporally evolve the dynamics of gas accreting onto a black hole in the form of a radiatively inefficient accretion flow (RIAF). We have trained a machine to forecast such a spatiotemporally chaotic system -- i.e. black hole weather forecasting -- using a convolutional neural network (CNN) and a training dataset which consists of numerical solutions of the hydrodynamical equations, for a range of initial conditions. We find that deep neural networks seem to learn well black hole accretion physics and evolve the accretion flow orders of magnitude faster than traditional numerical solvers, while maintaining a reasonable accuracy for a long time. For instance, CNNs predict well the temporal evolution of a RIAF over a long duration of $8\times 10^{4}GM/c^3$, which corresponds to 80 dynamical times at $r=100GM/c^2$. The DL model is able to evolve flows from initial conditions not present in the training dataset with good accuracy. Our approach thus seems to generalize well. Once trained, the DL model evolves a turbulent RIAF on a single GPU four orders of magnitude faster than usual fluid dynamics integrators running in parallel on 200 CPU cores. We speculate that a data-driven machine learning approach should be very promising for accelerating not only fluid dynamics simulations, but also general relativistic magnetohydrodynamic ones.

Accepted 2022 March 3. Received 2022 February 10; in original form 2021 January 11 (15 pages, 18 figures)

References in corpus (27)

• First M87 Event Horizon Telescope Results. I. The Shadow of the Supermassive Black Hole
• The EAGLE project: Simulating the evolution and assembly of galaxies and their environments
• Machine Learning for Fluid Mechanics
• PLUTO: a Numerical Code for Computational Astrophysics
• Hot Accretion Flows Around Black Holes
• First M87 Event Horizon Telescope Results. V. Physical Origin of the Asymmetric Ring
• Properties of galaxies reproduced by a hydrodynamic simulation
• Nuclear Activity in Nearby Galaxies
• Machine learning accelerated computational fluid dynamics
• Skillful Precipitation Nowcasting using Deep Generative Models of Radar
• HARM: A Numerical Scheme for General Relativistic Magnetohydrodynamics
• Enhanced Angular Momentum Transport in Accretion Disks
• Hydrodynamical Non-radiative Accretion Flows in Two-Dimensions
• The Event Horizon General Relativistic Magnetohydrodynamic Code Comparison Project
• Deep Fluids: A Generative Network for Parameterized Fluid Simulations
• Machine Learning for Precipitation Nowcasting from Radar Images
• Analog forecasting of extreme-causing weather patterns using deep learning
• Spectral Models for Low-luminosity Active Galactic Nuclei in LINERs: The Role of Advection-dominated Accretion and Jets
• AI-assisted super-resolution cosmological simulations
• Newton vs the machine: solving the chaotic three-body problem using deep neural networks
• Morpheus: A Deep Learning Framework For Pixel-Level Analysis of Astronomical Image Data
• Grand Unification of AGN and the Accretion and Spin Paradigms
• A new equilibrium torus solution and GRMHD initial conditions
• An advanced hybrid deep adversarial autoencoder for parameterized nonlinear fluid flow modelling
• The Paczynski-Wiita potential: A step-by-step "derivation"
• Deep Horizon; a machine learning network that recovers accreting black hole parameters
• Winds and feedback from supermassive black holes accreting at low rates: Hydrodynamical treatment

Cited by in corpus (3)

• Weak baselines and reporting biases lead to overoptimism in machine learning for fluid-related partial differential equations
• 3D Detection and Characterisation of ALMA Sources through Deep Learning
• Deep learning inference with the Event Horizon Telescope II. The Zingularity framework for Bayesian artificial neural networks