arXiv cs.AI· Nathaniel Chen, Alvin Garcia, Ricardo Shousha, Jalal Butt, Azarakhsh Jalalvand, Egemen Kolemen·· 12 小时前AI 评分18
Tokamak-SI：用带标注目录解读托卡马克放电
Tokamak-SI: Interpreting Tokamak Discharges with Labeled Catalogs
AI 导读
Tokamak-SI 将多项既有研究的标签与标注方法整合为单一可扩展、时间对齐的分类数据集，覆盖 DIII-D 托卡马克中约束、脱靶、AE、ELM、锯齿、撕裂模和电阻壁模等观测。基于该数据集训练的模型可将标签扩展到新炮次，在 AE、ELM 和 TM 检测上匹配或超越此前的检测器。该数据集旨在支持任务特定基准测试、物理可检索档案以及实验中关键事件的直接识别。
正文 · 原文
Abstract:Finding which phenomena occur in a tokamak discharge, and when, is often a manual task. Previous efforts at labeling events have been task-specific, each with its own corpus of data. We introduce Tokamak-SI, which combines the labels and labeling methods of many earlier studies into a single scalable, time-aligned, and categorical dataset covering observations from confinement, detachment, alfven eigenmodes (AE), edge localized modes (ELM), sawtooth, tearing modes (TM), and resistive wall modes in DIII-D tokamak. Models based on this, which can extend the labels to new shots, match or beat earlier detectors on its labels, including for AE, ELM, and TM detection. Tokamak-SI is intended to enable task-specific benchmarking, physics-searchable archives, and direct identification of key events during an experiment.
| Subjects: | Plasma Physics (physics.plasm-ph); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.32264 [physics.plasm-ph] |
| (or arXiv:2610.32264v1 [physics.plasm-ph] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32264 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Nathaniel Chen [view email]
[v1]
Fri, 23 Oct 2026 07:22:41 UTC (1,248 KB)
来源：arXiv cs.AI · arxiv.org