Skip to content
DraconiticResearch
Search Sources API
203,203 studies31 sourcesUpdated 2 min ago
PreprintCC BY 4.0arXiv

Tokamak-SI: Interpreting Tokamak Discharges with Labeled Catalogs

  • Nathaniel Chen
  • Alvin Garcia
  • Ricardo Shousha
  • Jalal Butt
  • Azarakhsh Jalalvand
  • Egemen Kolemen
Open at sourcePDFDOICite

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.

Related

  1. Modeling the HI-Halo Connection: Evolution, Scatter, and a Halo-based Prescription for 21-cm Mock Catalogs
    Mohd Kamran, Gabriella de Lucia, Marta Spinelli +3
    HALPreprintLicence not statedGeneral astronomyGeneral physicsHAL
  2. Sub-nanosecond time resolved light emission study for diffuse discharges in air under steep high voltage pulses
    P Tardiveau, Lionel Magne, Emmanuel Marode +3
    Plasma Sources Science and TechnologyPeer-reviewedPublisher termsFull text63 citedPlasma physicsHAL
  3. Enhancing dark siren cosmology via Gaussian process reconstruction of incomplete galaxy catalogs
    Matteo Tagliazucchi, Jonathan Gair, Riccardo Barbieri +1
    arXivPreprintCC BY 4.0Full textCosmologyGravitation & general relativityarXiv
  4. Not all those missing are lost: leveraging galaxy clustering in incomplete catalogs to unleash dark sirens cosmology
    Riccardo Barbieri, Marios Kalomenopoulos, Matteo Tagliazucchi +2
    arXivPreprintarXiv licenceFull textCosmologyGravitation & general relativityarXiv
  5. Weak Positive Discharges Leading to Lightning Initiation
    Victor P Pasko, Sebastien Celestin, Anne Bourdon
    Geophysical Research LettersPeer-reviewedCC BY 4.0Full textGeneral physicsHAL

Cite

BibTeXRIS
BibTeX
@misc{chen2026tokamaksi,
  title = {{Tokamak-SI: Interpreting Tokamak Discharges with Labeled Catalogs}},
  author = {Nathaniel Chen and Alvin Garcia and Ricardo Shousha and Jalal Butt and Azarakhsh Jalalvand and Egemen Kolemen},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.32264},
  eprint = {2610.32264},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.32264},
  note = {CC BY 4.0},
}
RIS
TY  - UNPB
TI  - Tokamak-SI: Interpreting Tokamak Discharges with Labeled Catalogs
AU  - Nathaniel Chen
AU  - Alvin Garcia
AU  - Ricardo Shousha
AU  - Jalal Butt
AU  - Azarakhsh Jalalvand
AU  - Egemen Kolemen
PY  - 2026
DA  - 2026/10/23
PB  - arXiv
DO  - 10.48550/arxiv.2610.32264
UR  - https://arxiv.org/abs/2610.32264
AB  - 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.
ER  -