DKEKAN: A Single-Parameterized KAN Surrogate for Drift Kinetic Equation Toward Fast Neoclassical Toroidal Viscosity Torque Modeling in Tokamaks

This paper introduces DKEKAN, a Kolmogorov-Arnold Network based surrogate model for drift kinetic equation solving in tokamak plasma. The model specifically targets neoclassical toroidal viscosity (NTV) torque computation, which is critical for predicting plasma rotation and stability in fusion reactors. By reducing the parameter space to a single parameter, the approach aims to enable faster NTV calculations that can be self-consistently integrated into modern tokamak modeling frameworks.