Disruption prediction and analysis through multimodal deep learning in KSTAR
Authors:
- Jinsu KimJKJinsu Kim
- Jeongwon LeeJLJeongwon Lee
- Jaemin SeoJSJaemin Seo
- Yeongsun LeeYLYeongsun Lee
- Yong-Su NaYNYong-Su Na
- 2 February 2024
- journal article
- research article
- Published by Elsevier in Fusion Engineering and Design
- Vol. 200
Abstract
No abstract availableKeywords
This publication has 19 references indexed in Scilit:
- Disruption prediction for future tokamaks using parameter-based transfer learningCommunications Physics, 2023
- Disruption event characterization and forecasting in tokamaksPhysics of Plasmas, 2023
- Magnetic control of tokamak plasmas through deep reinforcement learningNature, 2022
- Tokamak visible image sequence recognition using nonlocal spatio-temporal CNN for attention needed area localizationFusion Engineering and Design, 2021
- Deep convolutional neural networks for multi-scale time-series classification and application to tokamak disruption prediction using raw, high temporal resolution diagnostic dataPhysics of Plasmas, 2020
- Multivariate LSTM-FCNs for time series classificationNeural Networks, 2019
- Predicting disruptive instabilities in controlled fusion plasmas through deep learningNature, 2019
- Status of research toward the ITER disruption mitigation systemPhysics of Plasmas, 2014
- Understanding disruptions in tokamaksPhysics of Plasmas, 2012
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989