opPINN: Physics-Informed Neural Network with operator learning to approximate solutions to the Fokker-Planck-Landau equation
arXiv:2207.01765 · doi:10.1016/j.jcp.2023.112031
Abstract
We propose a hybrid framework opPINN: physics-informed neural network (PINN) with operator learning for approximating the solution to the Fokker-Planck-Landau (FPL) equation. The opPINN framework is divided into two steps: Step 1 and Step 2. After the operator surrogate models are trained during Step 1, PINN can effectively approximate the solution to the FPL equation during Step 2 by using the pre-trained surrogate models. The operator surrogate models greatly reduce the computational cost and boost PINN by approximating the complex Landau collision integral in the FPL equation. The operator surrogate models can also be combined with the traditional numerical schemes. It provides a high efficiency in computational time when the number of velocity modes becomes larger. Using the opPINN framework, we provide the neural network solutions for the FPL equation under the various types of initial conditions, and interaction models in two and three dimensions. Furthermore, based on the theoretical properties of the FPL equation, we show that the approximated neural network solution converges to the a priori classical solution of the FPL equation as the pre-defined loss function is reduced.
arXiv comment28 pages, 12 figures
References in corpus (18)
- Artificial Neural Networks for Solving Ordinary and Partial Differential Equations
- DGM: A deep learning algorithm for solving partial differential equations
- Solving high-dimensional partial differential equations using deep learning
- Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
- Bayesian Deep Convolutional Encoder-Decoder Networks for Surrogate Modeling and Uncertainty Quantification
- Prediction of Aerodynamic Flow Fields Using Convolutional Neural Networks
- Solving parametric PDE problems with artificial neural networks
- Entropy dissipation estimates for the Landau equation in the Coulomb case and applications
- Uniqueness of bounded solutions for the homogeneous Landau equation with a Coulomb potential
- Trend to Equilibrium for the Kinetic Fokker-Planck Equation via the Neural Network Approach
- Using neural networks to accelerate the solution of the Boltzmann equation
- The Landau equation with the specular reflection boundary condition
- Estimates for radial solutions of the homogeneous Landau equation with Coulomb potential
- A Conservative Scheme for Vlasov Poisson Landau modeling collisional plasmas
- Random batch particle methods for the homogeneous Landau equation
- On the rate of convergence to equilibrium for the homogeneous Landau equation with soft potentials
- Hermite spectral method for Fokker-Planck-Landau equation modeling collisional plasma
- Approximation to Singular Quadratic Collision Model in Fokker-Planck-Landau Equation
Cited by in corpus (3)
- Separable Physics-informed Neural Networks for Solving the BGK Model of the Boltzmann Equation
- FourierSpecNet: Neural Collision Operator Approximation Inspired by the Fourier Spectral Method for Solving the Boltzmann Equation
- Learning collision operators from plasma phase space data using differentiable simulators