Neural Networks for Nuclear Reactions in MAESTROeX
arXiv:2207.10628 · doi:10.3847/1538-4357/ac9a4b
Abstract
We demonstrate the use of neural networks to accelerate the reaction steps in the MAESTROeX stellar hydrodynamics code. A traditional MAESTROeX simulation uses a stiff ODE integrator for the reactions; here we employ a ResNet architecture and describe details relating to the architecture, training, and validation of our networks. Our customized approach includes options for the form of the loss functions, a demonstration that the use of parallel neural networks leads to increased accuracy, and a description of a perturbational approach in the training step that robustifies the model. We test our approach on millimeter-scale flames using a single-step, 3-isotope network describing the first stages of carbon fusion occurring in Type Ia supernovae. We train the neural networks using simulation data from a standard MAESTROeX simulation, and show that the resulting model can be effectively applied to different flame configurations. This work lays the groundwork for more complex networks, and iterative time-integration strategies that can leverage the efficiency of the neural networks.
References in corpus (9)
- DGM: A deep learning algorithm for solving partial differential equations
- Turbulence Modeling in the Age of Data
- A Multi-Code Analysis Toolkit for Astrophysical Simulation Data
- Deep learning observables in computational fluid dynamics
- Three-dimensional Numerical Simulations of Rayleigh-Taylor Unstable Flames in Type Ia Supernovae
- MAESTRO: An Adaptive Low Mach Number Hydrodynamics Algorithm for Stellar Flows
- Direct Numerical Simulations of Type Ia Supernovae Flames II: The Rayleigh-Taylor Instability
- The Neural Network shifted-Proper Orthogonal Decomposition: a Machine Learning Approach for Non-linear Reduction of Hyperbolic Equations
- MAESTROeX: A Massively Parallel Low Mach Number Astrophysical Solver