Answers are grounded in this paper and cite their sources.
Fusion plasma control requires real-time coordination of multiple actuators under partial observations and model uncertainty. Here we demonstrate predictive control of a fusion plasma on the Large Helical Device using an adaptive digital-twin system that combines data assimilation with physics-based integrated modeling. The digital twin was dynamically synchronized with experimental observations, while heating and fueling inputs were optimized from its predictions to drive the plasma toward target states. Real-time adaptation and control estimation were performed on a remote supercomputer located approximately 1,000 km from the experimental device, using up to 10,000 CPU cores. Multivariate control of electron density, electron temperature, and ion temperature was demonstrated in five representative target cases. These results establish a closed loop between an adaptive digital twin and a physical fusion plasma. They provide a route toward digital-twin-based control of fusion reactors and other partially observed complex systems.
No takes yet. Share an insight, caveat, or question.
Morishita et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: