U.S. Department of EnergyOffice of Scientific and Technical Information
Towards Fast and Accurate Predictions of Radio Frequency Power Deposition and Current Profile via Data-driven Modeling
Abstract
Three machine learning techniques (multilayer perceptron, random forest, and Gaussian process) provide fast surrogate models for lower hybrid current drive (LHCD) simulations. A single GENRAY/CQL3D simulation without radial diffusion of fast electrons requires several minutes of wall-clock time to complete, which is acceptable for many purposes, but too slow for integrated modeling and real-time control applications. The machine learning models use a database of 16,000+ GENRAY/CQL3D simulations for training, validation, and testing. Latin hypercube sampling methods ensure that the database covers the range of 9 input parameters ($$n_{e0}$$, $$T_{e0}$$, $$I_p$$, $$B_t$$, $$R_0$$, $$n_{||}$$, $$Z_{eff}$$, $$V_{loop}$$, $$P_{LHCD}$$) with sufficient density in all regions of parameter space. The surrogate models reduce the inference time from minutes to ~ms with high accuracy across the input parameter space.
- Authors:
-
- OSTI
- Publication Date:
- DOE Contract Number:
- SC0021202
- Research Org.:
- Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States). Plasma Science and Fusion Center
- Sponsoring Org.:
- USDOE Office of Science (SC), Fusion Energy Sciences (FES)
- Subject:
- 70 PLASMA PHYSICS AND FUSION TECHNOLOGY
- OSTI Identifier:
- 1887948
- DOI:
- https://doi.org/10.7910/DVN/5YY6PE
Citation Formats
Wallace, G. M., Bai, Z., Bertelli, N., Bethel, E. W., Perciano, T., Sadre, R., Shiraiwa, S., and Wright, J. C. Towards Fast and Accurate Predictions of Radio Frequency Power Deposition and Current Profile via Data-driven Modeling. United States: N. p., 2022.
Web. doi:10.7910/DVN/5YY6PE.
Wallace, G. M., Bai, Z., Bertelli, N., Bethel, E. W., Perciano, T., Sadre, R., Shiraiwa, S., & Wright, J. C. Towards Fast and Accurate Predictions of Radio Frequency Power Deposition and Current Profile via Data-driven Modeling. United States. doi:https://doi.org/10.7910/DVN/5YY6PE
Wallace, G. M., Bai, Z., Bertelli, N., Bethel, E. W., Perciano, T., Sadre, R., Shiraiwa, S., and Wright, J. C. 2022.
"Towards Fast and Accurate Predictions of Radio Frequency Power Deposition and Current Profile via Data-driven Modeling". United States. doi:https://doi.org/10.7910/DVN/5YY6PE. https://www.osti.gov/servlets/purl/1887948. Pub date:Fri Apr 15 04:00:00 UTC 2022
@article{osti_1887948,
title = {Towards Fast and Accurate Predictions of Radio Frequency Power Deposition and Current Profile via Data-driven Modeling},
author = {Wallace, G. M. and Bai, Z. and Bertelli, N. and Bethel, E. W. and Perciano, T. and Sadre, R. and Shiraiwa, S. and Wright, J. C.},
abstractNote = {Three machine learning techniques (multilayer perceptron, random forest, and Gaussian process) provide fast surrogate models for lower hybrid current drive (LHCD) simulations. A single GENRAY/CQL3D simulation without radial diffusion of fast electrons requires several minutes of wall-clock time to complete, which is acceptable for many purposes, but too slow for integrated modeling and real-time control applications. The machine learning models use a database of 16,000+ GENRAY/CQL3D simulations for training, validation, and testing. Latin hypercube sampling methods ensure that the database covers the range of 9 input parameters ($n_{e0}$, $T_{e0}$, $I_p$, $B_t$, $R_0$, $n_{||}$, $Z_{eff}$, $V_{loop}$, $P_{LHCD}$) with sufficient density in all regions of parameter space. The surrogate models reduce the inference time from minutes to ~ms with high accuracy across the input parameter space.},
doi = {10.7910/DVN/5YY6PE},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Fri Apr 15 04:00:00 UTC 2022},
month = {Fri Apr 15 04:00:00 UTC 2022}
}