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

A self-organised partition of the high dimensional plasma parameter space for plasma disruption prediction

Enrico Aymerich, Alessandra Fanni, Fabio Pisano, Giuliana Sias, Barbara Cannas, JET Contributors, WPTE Team2024年10月Nuclear FusionIF 3出版社

This paper introduces a disruption predictor constructed through a fully unsupervised two-dimensional mapping of the high-dimensional JET operational space. The primary strength of this disruption predictor lies in its inherent self-organization capability. Diverging from both supervised disruption predictors and earlier approaches suggested by the same authors, which were based on unsupervised models such as Self-Organizing or Generative Topographic Maps, this predictor eliminates the need for labeling data of disruption terminated pulses during training. In prior methods, labels were indeed required post-mapping to inform the model about the presence or absence of disruption precursors at each time instant during the disrupted discharges. In contrast, our approach in this study involves no labeling of data from disruption-terminated experiments. The Self-Organizing Map, operating without any a priori information, adeptly identifies the regions characterizing the pre-disruptive phase. Moreover, SOM discovers non-trivial relationships and captures the complicated interplay of device diagnostics on the internal plasma states from the experimental data. The provided model is highly interpretable; it allows the visualization of high-dimensional data and facilitates easy interrogation of the model to understand the reasons behind its correlations. Hence, utilizing SOMs across various devices can prove invaluable in extracting rules and identifying common patterns, thereby facilitating extrapolation to ITER of the knowledge acquired from existing tokamaks.

日本語訳

本論文は、高次元のJET運転空間の完全に教師なしの2次元マッピングによって構築されたディスラプション予測器を紹介する。このディスラプション予測器の主な強みは、その本質的な自己組織化能力にある。教師ありディスラプション予測器や、同じ著者らが以前に提案した、自己組織化マッや生成的トポグラフィックマップなどの教師なしモデルに基づくアプローチの両方とは異なり、この予測器は、トレーニング中にディスラプションで終了したパルスのデーターにラベル付けする必要をなくす。以前の方法では、ディスラプションを起こした放電の各時点におけるディスラプション前駆体の有無をモデルに知らせるために、マッピング後にラベルが確かに必要であった。対照的に、本究研での我々のアプローチは、ディスラプションで終了した実験からのデータのラベル付けを一切行わない。自己組織化マップは、事前提報なしで動作し、プレディスラプション段階を特徴づける領域を巧みに識別する。さらに、SOMは非自明な関係を発見し、実検データから装置診断と内部プラズマ状態の間の複雑な相互作用を捉える。提供されるモデルは解釈可能性が非常に高い。高次元データの可視化を可能にし、モデルに容易に問い合せて、その相関関係の背後にある理理を理理解することを促促する。したがって、様々な装置にわたってSOMを利用することは、ルールの抽抽出と共通パターンの識別に非常に有用であり、既存のトカマクから得られた知認識のITERへの外挿を容易にすることができる。

装置

iter中精度(概要文一致)jet中精度(概要文一致)

wiki

Plasma disruptionDisruption prediction

AIによる論文要約

プラズマ崩壊予測のための高次元パラメータ空間の自己組織化分割
JAこのペーパーは、プラズマ物理、機械学習、データ解析に興味のある核融合研究者に有益です。特に、教師なし学習手法を活用してプラズマ現象を理解したい研究者に役立つでしょう。#PlasmaDisruptionPrediction #UnsupervisedLearning #SelfOrganizingMap #HighDimensionalDataAnalysis
LLM向け: {'Title': 'A self-organised partition of the high dimensional plasma parameter s…

この論文は、JETの高次元運転空間を2次元にマッピングすることで、完全に教師なしの方法でプラズマ崩壊予測モデルを構築しています。このモデルは、崩壊終了実験のラベル付けを必要とせず、自己組織化によって崩壊前兆の領域を特定します。このアプローチは解釈性が高く、デバイス診断の複雑な相互作用を理解するのに役立ちます。

A self-organised partition of the high dimensional plasma parameter space for plasma disruption prediction
ENThis paper will be of interest to fusion researchers, particularly those working on plasma disruption prediction and the development of interpretable machine learning models for fusion applications.#FusionResearch #PlasmaDisruption #MachineLearning #SelfOrganizingMaps #ITER
LLM向け: {'Title': 'A self-organised partition of the high dimensional plasma parameter s…

This paper presents a novel disruption predictor that uses a self-organizing map (SOM) to map high-dimensional plasma data without the need for labeled disruption data. The SOM identifies regions of the parameter space associated with pre-disruptive conditions, allowing for interpretable visualization and understanding of the complex relationships between plasma diagnostics. This approach can be valuable for extracting common patterns and rules across tokamaks, facilitating the extrapolation of knowledge to ITER.

関連論文

A machine learning approach based on generative topographic mapping for disruption prevention and avoidance at JET

2019Nuclear Fusion

A statistical approach for the automatic identification of the start of the chain of events leading to the disruptions at JET

2021Nuclear Fusion

Plasma state monitoring and disruption characterization using multimodal VAEs

2025Nuclear Fusion

Overview of manifold learning techniques for the investigation of disruptions on JET

2014Plasma Physics and Controlled Fusion

Manifold learning to interpret JET high-dimensional operational space

2013Plasma Physics and Controlled Fusion

Unbiased and non-supervised learning methods for disruption prediction at JET

2009Nuclear Fusion

Disruption predictor based on neural network and anomaly detection on J-TEXT

2020Plasma Physics and Controlled Fusion

Disruption prediction and model analysis using LightGBM on J-TEXT and HL-2A

2021Plasma Physics and Controlled Fusion

IDP-PGFE: an interpretable disruption predictor based on physics-guided feature extraction

2023Nuclear Fusion

Hybrid deep-learning architecture for general disruption prediction across multiple tokamaks

2021Nuclear Fusion