U.S. Department of EnergyOffice of Scientific and Technical Information
Evolution patterns and parameter regimes in edge localized modes on the National Spherical Torus Experiment
Abstract
We implement unsupervised machine learning techniques to identify characteristic evolution patterns and associated parameter regimes in edge localized mode (ELM) events observed on the National Spherical Torus Experiment. Multi-channel, localized measurements spanning the pedestal region capture the complex evolution patterns of ELM events on Alfven timescales. Some ELM events are active for less than 100~microsec, but others persist for up to 1~ms. Also, some ELM events exhibit a single dominant perturbation, but others are oscillatory. Clustering calculations with time-series similarity metrics indicate the ELM database contains at least two and possibly three groups of ELMs with similar evolution patterns. The identified ELM groups trigger similar stored energy loss, but the groups occupy distinct parameter regimes for ELM-relevant quantities like plasma current, triangularity, and pedestal height. Notably, the pedestal electron pressure gradient is not an effective parameter for distinguishing the ELM groups, but the ELM groups segregate in terms of electron density gradient and electron temperature gradient. The ELM evolution patterns and corresponding parameter regimes can shape the formulation or validation of nonlinear ELM models. Finally, the techniques and results demonstrate an application of unsupervised machine learning at a data-rich fusion facility.
- Authors:
-
- Princeton Plasma Physics Lab. (PPPL), Princeton, NJ (United States)
- Publication Date:
- DOE Contract Number:
- AC02-09CH11466
- Research Org.:
- Princeton Plasma Physics Lab. (PPPL), Princeton, NJ (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC), Fusion Energy Sciences (FES)
- Subject:
- 70 PLASMA PHYSICS AND FUSION TECHNOLOGY; Edge Localized Modes National Spherical Torus Experiment Time series evolution patterns Unsupervised machine learning
- Keywords:
- Edge Localized Modes National Spherical Torus Experiment Time series evolution patterns Unsupervised machine learning
- OSTI Identifier:
- 1366473
- DOI:
- https://doi.org/10.11578/1366473
Citation Formats
Smith, D. R., Bell, R. E., Podesta, M., Smith, D. R., Fonck, R. J., McKee, G. R., Diallo, A., Kaye, S. M., LeBlanc, B. P., and Sabbagh, S. A. Evolution patterns and parameter regimes in edge localized modes on the National Spherical Torus Experiment. United States: N. p., 2015.
Web. doi:10.11578/1366473.
Smith, D. R., Bell, R. E., Podesta, M., Smith, D. R., Fonck, R. J., McKee, G. R., Diallo, A., Kaye, S. M., LeBlanc, B. P., & Sabbagh, S. A. Evolution patterns and parameter regimes in edge localized modes on the National Spherical Torus Experiment. United States. doi:https://doi.org/10.11578/1366473
Smith, D. R., Bell, R. E., Podesta, M., Smith, D. R., Fonck, R. J., McKee, G. R., Diallo, A., Kaye, S. M., LeBlanc, B. P., and Sabbagh, S. A. 2015.
"Evolution patterns and parameter regimes in edge localized modes on the National Spherical Torus Experiment". United States. doi:https://doi.org/10.11578/1366473. https://www.osti.gov/servlets/purl/1366473. Pub date:Tue Sep 01 00:00:00 EDT 2015
@article{osti_1366473,
title = {Evolution patterns and parameter regimes in edge localized modes on the National Spherical Torus Experiment},
author = {Smith, D. R. and Bell, R. E. and Podesta, M. and Smith, D. R. and Fonck, R. J. and McKee, G. R. and Diallo, A. and Kaye, S. M. and LeBlanc, B. P. and Sabbagh, S. A.},
abstractNote = {We implement unsupervised machine learning techniques to identify characteristic evolution patterns and associated parameter regimes in edge localized mode (ELM) events observed on the National Spherical Torus Experiment. Multi-channel, localized measurements spanning the pedestal region capture the complex evolution patterns of ELM events on Alfven timescales. Some ELM events are active for less than 100~microsec, but others persist for up to 1~ms. Also, some ELM events exhibit a single dominant perturbation, but others are oscillatory. Clustering calculations with time-series similarity metrics indicate the ELM database contains at least two and possibly three groups of ELMs with similar evolution patterns. The identified ELM groups trigger similar stored energy loss, but the groups occupy distinct parameter regimes for ELM-relevant quantities like plasma current, triangularity, and pedestal height. Notably, the pedestal electron pressure gradient is not an effective parameter for distinguishing the ELM groups, but the ELM groups segregate in terms of electron density gradient and electron temperature gradient. The ELM evolution patterns and corresponding parameter regimes can shape the formulation or validation of nonlinear ELM models. Finally, the techniques and results demonstrate an application of unsupervised machine learning at a data-rich fusion facility.},
doi = {10.11578/1366473},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Tue Sep 01 00:00:00 EDT 2015},
month = {Tue Sep 01 00:00:00 EDT 2015}
}