Physics-Informed Machine Learning for Modeling Turbulence in Supernovae

Abstract

Turbulence plays an important role in astrophysical phenomena, including core-collapse supernovae (CCSN), but current simulations must rely on subgrid models since direct numerical simulation (DNS) is too expensive. Unfortunately, existing subgrid models are not sufficiently accurate. Recently, Machine Learning (ML) has shown an impressive predictive capability for calculating turbulence closure. We have developed a physics-informed convolutional neural network (CNN) to preserve the realizability condition of Reynolds stress that is necessary for accurate turbulent pressure prediction. The applicability of the ML subgrid model is tested here for magnetohydrodynamic (MHD) turbulence in both the stationary and dynamic regimes. Our future goal is to utilize this ML methodology (available on GitHub) in the CCSN framework to investigate the effects of accurately-modeled turbulence on the explosion of these stars.

arXiv commentFor our ML algorithm on GitHub, see https://github.com/pikarpov-LANL/Sapsan/wiki/Estimators\#physics-informed-cnn-for-turbulence-modeling

References in corpus (23)

• Machine learning and the physical sciences
• Stability of Standing Accretion Shocks, With an Eye Toward Core Collapse Supernovae
• A public turbulence database cluster and applications to study Lagrangian evolution of velocity increments in turbulence
• Inside the Supernova: A Powerful Convective Engine
• A Comprehensive Physics-Informed Machine Learning Framework for Predictive Turbulence Modeling
• Physics-Informed Machine Learning Approach for Augmenting Turbulence Models: A Comprehensive Framework
• Core-Collapse Supernova Explosion Theory
• The Physics of Core-Collapse Supernovae
• A large scale dynamo and magnetoturbulence in rapidly rotating core-collapse supernovae
• Neutrino-driven explosion of a 20 solar-mass star in three dimensions enabled by strange-quark contributions to neutrino-nucleon scattering
• Semi-global simulations of the magneto-rotational instability in core collapse supernovae
• A Perspective on Machine Learning Methods in Turbulence Modelling
• Astrophysical hydromagnetic turbulence
• Crucial Physical Dependencies of the Core-Collapse Supernova Mechanism
• Beyond Mixing-length Theory: a step toward 321D
• Simulating Turbulence-aided Neutrino-driven Core-collapse Supernova Explosions in One Dimension
• Late-Time Convection in the Collapse of a 23 Solar Mass Star
• Large-Eddy Simulations of Magnetohydrodynamic Turbulence in Heliophysics and Astrophysics
• MHD Turbulence
• Turbulence in Core-Collapse Supernovae
• Towards an Understanding of the Resolution Dependence of Core-Collapse Supernova Simulations
• Implicit large eddy simulations of anisotropic weakly compressible turbulence with application to core-collapse supernovae
• Artificial neural network subgrid models of 2-D compressible magnetohydrodynamic turbulence

Cited by in corpus (6)

• Applications of machine learning in gravitational wave research with current interferometric detectors
• Magnetohydrodynamics with Physics Informed Neural Operators
• Applications of Machine Learning to Detecting Fast Neutrino Flavor Instabilities in Core-Collapse Supernova and Neutron Star Merger Models
• Turbulence modelling in neutron star merger simulations
• Solving the Pulsar Equation using Physics-Informed Neural Networks
• Cluster-Weighted Training of Deep Surrogate Models for Subgrid Turbulent Transport