Fusion Deep Learning
The Fusion Recurrent Neural Network
Deep Learning to Predict Disruptions in Tokamak Plasmas
Nuclear fusion power delivered by magnetic-confinement tokamak reactors holds the promise of sustainable and clean energy. The avoidance of large-scale plasma instabilities called disruptions within these reactors is one of the most pressing challenges because disruptions can halt power production and damage key components.
Nuclear fusion power delivered by magnetic-confinement tokamak reactors holds the promise of sustainable and clean energy. The avoidance of large-scale plasma instabilities called disruptions within these reactors is one of the most pressing challenges because disruptions can halt power production and damage key components.
Our deep learning method extends considerably the capabilities of previous strategies. In particular, it delivers reliable predictions for tokamaks other than the one on which it was trained. Our approach takes advantage of high-dimensional training data to boost predictive performance while engaging supercomputing resources at the largest scale to improve accuracy and speed. Trained on experimental data from the largest tokamaks, our method can be applied to specific tasks such as prediction with long warning times. This opens up the possibility of moving from passive disruption prediction to active reactor control and optimization. These initial results illustrate the potential for deep learning to accelerate progress in fusion-energy science and, more generally, to the understanding and prediction of complex physical systems.
Our deep learning method extends considerably the capabilities of previous strategies. In particular, it delivers reliable predictions for tokamaks other than the one on which it was trained. Our approach takes advantage of high-dimensional training data to boost predictive performance while engaging supercomputing resources at the largest scale to improve accuracy and speed. Trained on experimental data from the largest tokamaks, our method can be applied to specific tasks such as prediction with long warning times. This opens up the possibility of moving from passive disruption prediction to active reactor control and optimization. These initial results illustrate the potential for deep learning to accelerate progress in fusion-energy science and, more generally, to the understanding and prediction of complex physical systems.
Princeton Plasma Physics Laboratory
100 Stellarator Road
Princeton, New Jersey 08540