Neural Network-Enhanced COTSIM: Advancing Predictive Capabilities for Fast DIII-D Simulations
K. Shabbir, T. Rafiq, E. Schuster
IEEE Transactions on Plasma Sciences, vol. 54, no. 6, pp. 2860-2866, June 2026
|
Abstract
|
|
Sustaining fusion reactions in tokamaks requires
heating plasma to thermonuclear temperatures while maintaining
confinement and stability. Neutral beam injection (NBI) pro-
vides heating, current drive, torque, and fueling, while electron
cyclotron (EC) waves are widely used for heating and current
drive; together, these actuators shape the plasma current, tem-
perature, and density profiles. The control-oriented tokamak
simulator (COTSIM), a predictive, control-oriented code, has
been enhanced with neural-network surrogates for transport
and sources. Turbulent transport is predicted by MMMnet—a
neural-network version of the updated multimode model (MMM
9.0.10)—with significantly reduced computation time relative to
MMM; neoclassical transport follows the Chang–Hinton model.
NUBEAMnet, a surrogate of the Monte Carlo NUBEAM module,
predicts beam-driven heating, current, and torque. EC heating
and current drive use a control-oriented, empirically scaled
source model; plasma resistivity follows the Spitzer formulation;
bootstrap current uses the Sauter model. Equilibrium is com-
puted using both prescribed and fixed-boundary solvers (FBSs),
and the pedestal structure is modeled with an empirical pedestal
model. For a representative DIII-D discharge, COTSIM predicts
electron and ion temperature and safety-factor profiles in close
agreement with TRANSP predictive and interpretive simulations
while extending predictions through the pedestal region to the
plasma edge (versus 80% of the minor radius in TRANSP). The
equivalent COTSIM simulation runs in under 3 min compared to
about 2 h for TRANSP, enabling rapid scenario planning, opti-
mization of tokamak operation, and between-pulse control design.