Verification of turbulent simulations using PoPe: quantifying model precision and numerical error with data mining of simulation output

Verification of a 1D-1V kinetic code with the PoPe method [1] is presented. Investigation of the impact of reducing the precision of the numerical scheme is analysed by following 3 indicators of the physics solved by the code, namely the plasma response to an external high frequency electric field wave. The response of the distribution function in the vicinity of the particle-wave resonance is found to be most sensitive to the resolution. Consistently, a rapid growth of the error indicator determined with PoPe is observed. However, no critical value of this indicator allowing us to retain the physics in a situation of degraded precision could be observed. The response of the amplitude of the electric potential fluctuations is characterised by a transient growth followed by a plateau. It is found that the loss of this plateau is governed by the resolution in v-space, but due to the generation of a symmetry in the problem rather than to errors in the numerical scheme. The analysis of the transient indicates that the growth rate of the amplitude of the electric potential is very robust down to very low resolution, step in velocity of 2 thermal velocities. However, a transition prior to this resolution, with step 0.5 thermal velocity, can be identified corresponding to a PoPe indicator of order zero, namely for errors of order 100 %.