Machine learning for classification, dimension reduction, clustering, and feature importance analysis of QH-mode plasma regimes
Abstract Edge-localized modes (ELMs) release bursts of energy and particles that threaten plasma-facing components in future tokamak reactors, making ELM-free operating regimes a priority for fusion research. Quiescent H-mode (QH), wide-pedestal QH-mode (WPQH), and broadband QH-mode (BBQH) form a family of ELM-free regimes at DIII-D whose boundaries and controlling parameters remain incompletely understood. This work aims to identify, from data, which measured quantities distinguish the three regimes, using a physics-labeled database of 482 high-confidence segments drawn from 323 DIII-D discharges, whose manual labeling was accelerated by the Data Fusion Labeler (dFL). An XGBoost classifier trained on 1 ms-resolution diagnostic data establishes that the manual labels are learnable: under leave-one-shot-out cross-validation it reproduces them for 87.3% of 1 ms samples (macro-F1 0.82). The same classifier underpins dFL's autolabeler for extending the database across the archive, at an estimated ~50× speedup over fully manual analysis. A supervised feature-importance analysis (classifiers evaluated on held-out discharges, with SHAP attribution), trained only on physics signals not used as labeling criteria, shows that the regimes are also distinguishable from independent physics quantities, and unsupervised dimension-reduction and clustering methods examine the same data without labels. The analysis recovers injected torque as the dominant actuator distinguishing the regimes. Within the rotation and E_r quantities considered, edge E×B shear carries the most information distinguishing the three regimes, while toroidal rotation also contributes strongly; this is a statistical association for this model and dataset, consistent with the critical-shear picture of edge harmonic oscillation onset. Where the supervised and unsupervised rankings appear to disagree, the disagreement reflects the correlation structure among related features rather than a substantive physics dispute. Together, these results identify key physical quantities associated with QH-mode regime boundaries and provide a reusable, interpretable workflow for machine-learning-based analysis of labeled databases in fusion research.
Authors
- Erik Olofsson (ORCID: https://orcid.org/0000-0001-9019-212X)
- R. A. Myers (ORCID: https://orcid.org/0000-0002-5376-6435)
- Andrew Oakleigh Nelson (ORCID: https://orcid.org/0000-0002-9612-1936)
- B. Sammuli (ORCID: https://orcid.org/0000-0002-3000-9327)
- T. Odstrčil (ORCID: https://orcid.org/0000-0003-4173-4230)
- Zeyu Li (ORCID: https://orcid.org/0000-0003-3932-9244)
- R. Nazikian (ORCID: https://orcid.org/0000-0001-6235-6692)
- Tapan Ganatma Nakkina (ORCID: https://orcid.org/0000-0002-2618-9038)
- David Orozco (ORCID: https://orcid.org/0000-0002-0610-2492)
- Craig Michoski (ORCID: https://orcid.org/0000-0002-6356-233X)
- Xi Chen (ORCID: https://orcid.org/0000-0002-8718-6877)
- Mitchell Clark
- Matthew Waller (ORCID: https://orcid.org/0009-0005-3062-6420)
Institutions
- Peking University (CN)
- Oak Ridge Institute for Science and Education (US)
- State Key Laboratory of Nuclear Physics and Technology (CN)
- General Atomics (United States) (US)
- Columbia University (US)
- The University of Texas at Austin (US)
Publication Details
- Journal
- Nuclear Fusion
- Published
- 2026-11-17
- DOI
- https://doi.org/10.1088/1741-4326/aec307
- Primary Topic
- Magnetic confinement fusion research
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- U.S. Department of Energy
- Office of Science
- Fusion Energy Sciences