Equilibrium Reconstruction on the START Spherical Tokamak Using aNeural Network

The neural network post-shot reconstruction analysis, as implemented on the start spherical tokamak at culham,is described. this used a combination of magnetic and soft x-ray diagnostic inputs to evaluate selected plasmaparameters as a function of time throughout the shot. an in-built novelty detector was used to detect inadequatedatabase coverage associated with plasma configurations not represented in the database. the method is illustratedby results from the high beta campaign on start.