FusionPapers
図版検索トレンドwiki日本の研究
© 2026 FUSIONPAPERS
About法務情報
トップに戻る

Frontiers in data analysis methods: from causality detection to data driven experimental design

A Murari, E Peluso, T Craciunescu, S Dormido-Canto, M Lungaroni, R Rossi, L Spolladore, J Vega, M Gelfusa, JET Contributors2022年Plasma Physics and Controlled FusionIF 2.2出版社

On the route to the commercial reactor, the experiments in magnetical confinement nuclear fusion have become increasingly complex and they tend to produce huge amounts of data. New analysis tools have therefore become indispensable, to fully exploit the information generated by the most relevant devices, which are nowadays very expensive to both build and operate. The paper presents a series of innovative tools to cover the main aspects of any scientific investigation. Causality detection techniques can help identify the right causes of phenomena and can become very useful in the optimisation of synchronisation experiments, such as the pacing of sawteeth instabilities with ion cyclotron radiofrequency heating modulation. Data driven theory is meant to go beyond traditional machine learning tools, to provide interpretable and physically meaningful models. The application to very severe problems for the tokamak configuration, such as disruptions, could help not only in understanding the physics but also in extrapolating the solutions to the next generation of devices. A specific methodology has also been developed to support the design of new experiments, proving that the same progress in the derivation of empirical models could be achieved with a significantly reduced number of discharges.

日本語訳

商業炉への道のりにおいて、磁気閉じ込め核融合実験はますます複雑化し、膨大な量のデータを生成する傾向にある。したがって、現在では建設・運転に多大なコストを要する最先端の装置群から得られる情報を完全に活用するためには、新たな解析ツールが不可欠となっている。本論文は、あらゆる科学的調査の主要な側面を網羅する一連の革新的ツールを提示するものである。因果関係検出技術は、現象の真の原因を特定するのに役立ち、イオンサイクロトロン周波数加熱変調による鋸歯状不安定性のペーシングなどの同期実験の最適化において極めて有用となり得る。データ駆動型理論は、従来の機械学習ツールを超越し、解釈可能で物理的に意味のあるモデルを提供することを目的としている。トカマク配位におけるディスラプションなどの極めて困難な問題への適用は、物理の理解を深めるだけでなく、次世代装置への解決策の外挿にも寄与し得る。さらに、新規実験の設計を支援する具体的な方法論も開発されており、これにより、大幅に削減された放電回数で、経験的モデルの導出における同等の進展が達成可能であることが実証されている。

この論文にはまだAI要約がありません。

関連論文

A hybrid physics/data-driven logic to detect, classify, and predict anomalies and disruptions in tokamak plasmas

2024Nuclear Fusion

Near real-time streaming analysis of big fusion data

2022Plasma Physics and Controlled Fusion

Testing the consistency of multimachine databases for physical studies of regression

2020Nuclear Fusion

Summary report of the 3rd IAEA technical meeting on fusion data processing validation and analysis (FDPVA)

2020Nuclear Fusion

Development of a Bayesian method for the analysis of inertial confinement fusion experiments on the NIF

2013Nuclear Fusion

A comparison between ICRF theory and experiment

1988Plasma Physics and Controlled Fusion

Physics-guided machine learning approaches to predict the ideal stability properties of fusion plasmas

2020Nuclear Fusion

Conditional recurrence plots for the investigation of sawteeth pacing with RF modulation

2022Plasma Physics and Controlled Fusion

Overview of image processing tools to extract physical information from JET videos

2014Plasma Physics and Controlled Fusion

Application of dimensionless parameter scaling techniques to the design and interpretation of magnetic fusion experiments

2008Plasma Physics and Controlled Fusion