Reconstruction of tokamak plasma safety factor profile using deep learning

Abstract The motional Stark effect (MSE) diagnostic has been a standard measurement for the magnetic field line pitch angle in tokamaks that are equipped with neutral beams. However, MSE data not always available due to experimental constraints, especially future devices without Here we develop deep-learning based model (SGTC-QR) can reconstruct safety factor profile mimic traditional equilibrium reconstruction constraint. demonstrates promising performance, and sub-millisecond inference time is compatible real-time plasma control system.