opPINN: Physics-Informed Neural Network with operator learning to approximate solutions to the Fokker-Planck-Landau equation
This work addresses computational challenges in solving complex kinetic equations for plasma physics or fluid dynamics, offering an incremental improvement by integrating operator learning into existing PINN methods.
The authors tackled the problem of approximating solutions to the Fokker-Planck-Landau equation by proposing opPINN, a hybrid framework combining physics-informed neural networks with operator learning, which reduces computational cost and provides neural network solutions for various conditions in 2D and 3D, showing convergence to classical solutions as the loss decreases.
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.