Towards fast, accurate predictions of RF simulations via data-driven modeling: Forward and lateral models
Name
090008_1_5.0162422.pdf
Description
Published version
Size
3.11 MB
Format
Adobe PDF
Checksum (MD5)
7ec7eccd8e386a6819645bc78693ca23
Author(s)
Wallace, GM
Bai, Z
Bertelli, N
Bethel, EW
Perciano, T
Shiraiwa, S
Wright, JC
Date Issued
August 18, 2023
Journal
AIP Conference Proceedings
Publisher
AIP Publishing
Citation
G. M. Wallace, Z. Bai, N. Bertelli, E. W. Bethel, T. Perciano, S. Shiraiwa, J. C. Wright; Towards fast, accurate predictions of RF simulations via data-driven modeling: Forward and lateral models. AIP Conf. Proc. 18 August 2023; 2984 (1): 090008.
Version
Final published version
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. More accurate simulations with fast electron diffusion are even slower, requiring multiple hours of run time with parallel processing. The machine learning models use a database of 16,000+ GEN-RAY/CQL3D simulations for training, validation, and testing. Latin hypercube sampling methods implemented in πScope ensure that the database covers the range of 9 input parameters (ne0, Te0, Ip, Bt, R0, n∥︀, Ze f f, Vloop, PLHCD) with sufficient density in all regions of parameter space. The surrogate models reduce the computation time from minutes-hours to ms with high accuracy across the input parameter space. Data-driven surrogate models also allow for solving inverse and “lateral” problems. A surrogate model for the inverse problem maps from a desired current drive or power deposition profile to a set of input parameters that would result in such a profile, while a surrogate model for the lateral problem maps from a measured experimental quantity such as hard x-ray emission to a current drive or power deposition profile. The πScope database creation workflow is flexible and applicable to other RF simulation codes such as TORIC.
MIT Department
Massachusetts Institute of Technology. Plasma Science and Fusion Center
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1063/5.0162422
