Please refer to journal paper from S.J.P.Pamela, titled "Neural-Parareal: Self-improving acceleration of fusion MHD simulations using time-parallelisation and neural operators" Available on ArXiV and on Comp.Phys.Comm.: https://doi.org/10.1016/j.cpc.2024.109391 Data produced by the JOREK code, https://jorek.eu All runs created using the electrostatic model, model-ID "model003" Data downsampled by saving every 10th timestep, on a regular 2D grid of 100x100. To reproduce full runs, use corresponding input files. Note: variables names are the same as in the JOREK code: u = electric potential omega = toroidal vorticity rho = density T = temperature The create_gif.py can be used to convert data into movies.