Determining 1D fast-ion velocity distribution functions from ion cyclotron emission data using deep neural networks.

The relationship between simulated ion cyclotron emission (ICE) signals s and the corresponding 1D velocity distribution function fv⊥ of the fast ions triggering the ICE is modeled using a two-layer deep neural network. The network architecture (number of layers and number of computational nodes in each layer) and hyperparameters (learning rate and number of learning iterations) are fine-tuned using a bottom-up approach based on cross-validation. Thus, the optimal mapping gs;θ of the neural network in terms of the number of nodes, the number of layers, and the values of the hyperparameters, where θ is the learned model parameters, is determined by comparing many different configurations of the network on the same training and test set and choosing the best one based on its average test error. The training and test sets are generated by computing random ICE velocity distribution functions f and their corresponding ICE signals s by modeling the relationship as the linear matrix equation Wf = s. The simulated ICE signals are modeled as edge ICE signals at LHD. The network predictions for f based on ICE signals s are on many simulated ICE signal examples closer to the true velocity distribution function than that obtained by 0th-order Tikhonov regularization, although there might be qualitative differences in which features one technique is better at predicting than the other. Additionally, the network computations are much faster. Adapted versions of the network can be applied to future experimental ICE data to infer fast-ion velocity distribution functions.

Fast-ion orbit sensitivity of neutron emission spectroscopy diagnostics.

Fast ions in fusion plasmas often leave characteristic signatures in the plasma neutron emission. Measurements of this emission are subject to the phase-space sensitivity of the diagnostic, which can be mapped using weight functions. In this paper, we present orbit weight functions for the TOFOR and NE213 neutron diagnostics at the Joint European Torus, mapping their phase-space sensitivity in 3D orbit space. Both diagnostics are highly sensitive to fast ions that spend a relatively large fraction of their orbit transit times inside the viewing cone of the diagnostic. For most neutron energies, TOFOR is found to be relatively sensitive to potato orbits and heavily localized counter-passing orbits, as well as trapped orbits whose "banana tips" are inside the viewing cone of TOFOR. For the NE213-scintillator, the sensitivity is found to be relatively high for stagnation orbits.