No Arabic abstract
The Landau form of the Fokker-Planck equation is the gold standard for plasmas dominated by small angle collisions, however its $Order{N^2}$ work complexity has limited its practicality. This paper extends previous work on a fully conservative finite element method for this Landau collision operator with adaptive mesh refinement, optimized for vector machines, by porting the algorithm to the Cuda programming model with implementations in Cuda and Kokkos, and by reporting results within a Vlasov-Maxwell-Landau model of a plasma thermal quench. With new optimizations of the Landau kernel and ports of this kernel, the sparse matrix assembly and algebraic solver to Cuda, the cost of a well resolved Landau collision time advance is shown to be practical for kinetic plasma applications. This fully implicit Landau time integrator and the plasma quench model is available in the PETSc (Portable, Extensible, Toolkit for Scientific computing) numerical library.
An encoder-decoder neural network has been used to examine the possibility for acceleration of a partial integro-differential equation, the Fokker-Planck-Landau collision operator. This is part of the governing equation in the massively parallel particle-in-cell code, XGC, which is used to study turbulence in fusion energy devices. The neural network emphasizes physics-inspired learning, where it is taught to respect physical conservation constraints of the collision operator by including them in the training loss, along with the L2 loss. In particular, network architectures used for the computer vision task of semantic segmentation have been used for training. A penalization method is used to enforce the soft constraints of the system and integrate error in the conservation properties into the loss function. During training, quantities representing the density, momentum, and energy for all species of the system is calculated at each configuration vertex, mirroring the procedure in XGC. This simple training has produced a median relative loss, across configuration space, on the order of 10E-04, which is low enough if the error is of random nature, but not if it is of drift nature in timesteps. The run time for the Picard iterative solver of the operator scales as order n squared, where n is the number of plasma species. As the XGC1 code begins to attack problems including a larger number of species, the collision operator will become expensive computationally, making the neural network solver even more important, since the training only scales as n. A wide enough range of collisionality is considered in the training data to ensure the full domain of collision physics is captured. An advanced technique to decrease the losses further will be discussed, which will be subject of a subsequent report. Eventual work will include expansion of the network to include multiple plasma species.
A Landau fluid model for a collisionless electron-proton magnetized plasma, that accurately reproduces the dispersion relation and the Landau damping rate of all the magnetohydrodynamic waves, is presented. It is obtained by an accurate closure of the hydrodynamic hierarchy at the level of the fourth order moments, based on linear kinetic theory. It retains non-gyrotropic corrections to the pressure and heat flux tensors up to the second order in the ratio between the considered frequencies and the ion cyclotron frequency.
A gyrokinetic Coulomb collision operator is derived, which is particularly useful to describe the plasma dynamics at the periphery region of magnetic confinement fusion devices. The derived operator is able to describe collisions occurring in distribution functions arbitrarily far from equilibrium with variations on spatial scales at and below the particle Larmor radius. A multipole expansion of the Rosenbluth potentials is used in order to derive the dependence of the full Coulomb collision operator on the particle gyroangle. The full Coulomb collision operator is then expressed in gyrocentre phase-space coordinates, and a closed formula for its gyroaverage in terms of the moments of the gyrocenter distribution function in a form ready to be numerically implemented is provided. Furthermore, the collision operator is projected onto a Hermite-Laguerre velocity space polynomial basis and expansions in the small electron-to-ion mass ratio are provided.
We study the collision frequencies of particles in the weakly and highly ionized plasmas with the power-law q-distributions in nonextensive statistics. We derive the average collision frequencies of neutral-neutral particle, electron-neutral particle, ion-neutral particle, electron-electron, ion-ion and electron-ion, respectively, in the q-distributed plasmas. We show that the average collision frequencies depend strongly on the q-parameter in a complex form and thus their properties are significantly different from that in Maxwell-distributed plasmas. These new average collision frequencies are important for us to study accurately the transport property in the complex plasmas with non-Maxwell/power-law velocity distributions.
The before described general principles and methodology of calculating electron wave propagation in homogeneous isotropic half-infinity slab of Maxwellian plasma with indefinite but in principal value sense taken integrals in characteristic equations, and the use of 2D Laplace transform method are applied to an evaluation of collision damping decrements of plane electron longitudinal and transverse waves. Damping decrement tends to infinity when the wave frequency tends to electron Langmuir frequency from above values. We considered recurrent relations for amplitudes of the overtones which form in their sum the all solution of the plasma wave non-linear equations including collision damping and quadratic (non-linear) terms. Collisionless damping at frequencies more the Langmuir one is possible only in non-Maxwellian plasmas.