Neural network approximated Bayesian inference of edge electron density profiles at JET

Abstract

A neural network (NN) has been trained on the inference of the edge electron density profiles from measurements of the JET lithium beam emission spectroscopy (Li-BES) diagnostic. The novelty of the approach resides in the fact that the network has been trained to be a fast surrogate model of an existing Bayesian model of the diagnostic implemented within the Minerva framework. We build on previous work that showed a similar application to an X-ray imaging diagnostic at the W7-X experiment, and we show here that the approach is general and can be applied to a different physics system. What makes the approach so versatile is the common definition of different models within the same framework. The network is tested on data measured during several different pulses and the predictions compared to the results obtained with the full model Bayesian inference. The NN analysis only requires tens of microseconds on a GPU compared to the tens of minutes long full inference. Finally, we show how uncertainties in the network's prediction can be calculated using state-of-the-art deep learning technique based on a variational inference interpretation of the network training. This is particularly advantageous because it does not require extra computation time besides the conventional network evaluation time.