The developement of deep learning based surrogate model of GTC (SGTC)

We have developed the surrogate model of GTC based on deep learning methods. The trained surrogate models of GTC (SGTC) can be used as physics-based fast instability simulators that run on the order of milliseconds, which fits the requirement of the real-time plasma control system. We demonstrate the feasibility of this workflow by first creating a big database from GTC systematic linear global electromagnetic simulations of the current-driven kink instabilities in DIII-D plasmas, and then developing SGTC linear internal kink instability simulators through supervised training. SGTC linear internal kink simulators demonstrate predictive capabilities for the mode instability properties including the growth rate and mode structure. We have developed the q-profile reconstruction module (SGTC-QR) that can reconstruct the safety factor profile without the MSE diagnostic to mimic the traditional equilibrium reconstruction with the MSE constraint. The model demonstrates promising performance, and the sub-millisecond inference time is compatible with the real-time plasma control system. Recently, we have developed the 2-D equilibrium reconstruction model based on the Physics-Informed Neural Networks (PINN) to predict the flux surface shape and the self-consistent q-profile.