Reconstructing the Plasma Boundary with a Reduced Set of Diagnostics

TL;DR

This paper explores using neural networks with limited diagnostic data to accurately reconstruct the plasma boundary in a tokamak, which is crucial for fusion reactor operation.

Contribution

It demonstrates that neural networks can effectively reconstruct the plasma boundary using reduced diagnostic inputs, balancing accuracy and input complexity.

Findings

Neural network trained on coil currents achieved 0.04 m error.

Adding plasma current and loop voltage reduced error to 0.03 m.

Machine learning shows promise in data-limited fusion environments.

Abstract

This study investigates the feasibility of reconstructing the last closed flux surface (LCFS) in the DIII-D tokamak using neural network models trained on reduced input feature sets, addressing an ill-posed task. Two models are compared: one trained solely on coil currents and another incorporating coil currents, plasma current, and loop voltage. The model trained exclusively on coil currents achieved a mean point displacement of 0.04 m on a held-out test set, while the inclusion of plasma current and loop voltage reduced the error to 0.03 m. This comparison highlights the trade-offs between input feature complexity and reconstruction accuracy, demonstrating the potential of machine learning algorithms to perform effectively in data-limited environments, such as those expected in Fusion Power Plants (FPP) due to diagnostic constraints imposed by the presence of blankets and shielding.