Automatic identification of tokamak plasma confinement states (L-mode, ELM-free H-mode, and ELMy H-mode) with multi-task learning neural network
Open Access
- 23 June 2025
- journal article
- Published by IOP Publishing in Nuclear Fusion
- Vol. 65 (7) , 076035
Abstract
The identification of plasma confinement states (L-mode, ELM-free H-mode, and ELMy H-mode) is carried out using a multi-task learning neural network (MTL-NN) in EAST. The identification process can be divided into two tasks: identifying the operational modes and detecting the edge localized modes (ELMs). D α and Mirnov coil measurements are selected as features for detecting the ELM. Parameters from scaling laws, which are related to thermal energy confinement time and heating threshold of L–H transition, are selected as features for identifying the operational modes. The data set used for supervised learning is collected from ELM control experiments in EAST. The MTL-NN comprises two task-specific layers and a shared layer. The multi-task learning framework allows for mutual error correction between tasks, resulting in higher accuracy and robustness compared to single-task models. Evaluation results demonstrate that the MTL-NN achieves an accuracy of 96.7% on the test set, representing a 3.6% improvement compared to single-task models.Keywords
Funding Information
- National Magnetic Confinement Fusion Program of China (2024YFE03010000)
- Hefei Institutes of Physical Science, Chinese Academy of Sciences (BJPY2022B05)
- Natural Science Foundation of Anhui Province (2208085J39)
- Chinese Academy of Sciences (No. XDB0790100)
- National Natural Science Foundation of China (12105323)
This publication has 46 references indexed in Scilit:
- Classification of the L-, H-mode, and plasma-free state: Convolutional neural networks and variational autoencoders on the edge reflectometer for KSTARReview of Scientific Instruments, 2024
- Real-time classification of L-H transition and ELM in KSTARFusion Engineering and Design, 2020
- Lower hybrid wave absorption study to improve the calculation of energy confinement time in EASTPhysics of Plasmas, 2018
- A brief review on multi-task learningMultimedia Tools and Applications, 2018
- Automatic detection of L-H transition in KSTAR by support vector machineFusion Engineering and Design, 2018
- Framewise phoneme classification with bidirectional LSTM and other neural network architecturesNeural Networks, 2005
- Multitask LearningMachine Learning, 1997
- H mode power threshold database for ITERNuclear Fusion, 1996
- ITER H mode confinement database updateNuclear Fusion, 1994
- The H-Mode of ASDEXNuclear Fusion, 1989