Hannover 2020 – scientific programme
The DPG Spring Meeting in Hannover had to be cancelled! Read more ...
Parts | Days | Selection | Search | Updates | Downloads | Help
P: Fachverband Plasmaphysik
P 21: Helmholtz Graduate School 5
P 21.4: Talk
Thursday, March 12, 2020, 15:20–15:45, b305
Classification of tokamak plasma confinement states with convolutional recurrent neural networks — •Francisco Matos1, Vlado Menkovski2, Federico Felici3, Alessandro Pau3, Frank Jenko1, The TCV Team4, and The Eurofusion MST1 Team5 — 1Max Planck Institute for Plasma Physics, Garching, Germany — 2Eindhoven University of Technology, Eindhoven, Netherlands — 3Ecole Polytechnique Federale de Laussane, Swiss Plasma Center, Switzerland — 4See author list of S. Coda et al 2019 Nucl. Fusion 59 112023 — 5See author list of B. Labit et al., 2019 Nucl. Fusion 59 086020
During a tokamak discharge, the plasma can vary between different confinement regimes: Low (L), High (H) and, in some cases, a temporary (intermediate state), called Dithering (D). In addition, while the plasma is in H mode, Edge Localized Modes (ELMs) can occur. The automatic detection of changes between these states, and of ELMs, is important for tokamak operation. Motivated by this, and by recent developments in Deep Learning (DL), we developed and compared two methods for automatic detection of the occurrence of L-D-H transitions and ELMs, applied on data from the TCV tokamak. These methods consist in a Convolutional Neural Network (CNN) and a Convolutional Long Short Term Memory Neural Network (Conv-LSTM). We measured our results with regards to ELMs using ROC curves and Youden's score index, and regarding state detection using Cohen's Kappa Index.