A neural network-based method for input parameter optimization of edge transport modeling utilizing experimental diagnostics

A neural network-based method for input parameter optimization of edge transport modeling utilizing experimental diagnostics

A neural network-based method is developed to fast optimize EMC3-EIRENE input parameters, enabling EMC3-EIRENE to produce synthetic data that closely match experimental measurements on Wendelstein 7-X. Initially, an EMC3-EIRENE simulation database covering a range of key input parameters is generate...

Full description

Saved in:
Bibliographic Details
Main Authors: Y. Luo, S. Xu, Y. Liang, E. Wang, J. Cai, Y. Feng, D. Reiter, A. Knieps, S. Brezinsek, D. Harting, M. Krychowiak, D. Gradic, P. Ren, D. Zhang, Y. Gao, G. Fuchert, A. Pandey, M. Jakubowski, the W7-X Team
Format: Article
Language:English
Published: IOP Publishing 2025-01-01
Series:Nuclear Fusion
Subjects:
machine learning
Bayesian inference
EMC3-EIRENE
Wendelstein 7-X
Online Access:https://doi.org/10.1088/1741-4326/adf75f
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A neural network-based method is developed to fast optimize EMC3-EIRENE input parameters, enabling EMC3-EIRENE to produce synthetic data that closely match experimental measurements on Wendelstein 7-X. Initially, an EMC3-EIRENE simulation database covering a range of key input parameters is generated. Trained on this database, a feed-forward neural network (FNN) surrogate model efficiently maps EMC3-EIRENE input parameters to synthetic signals corresponding to experimentally observed physical quantities. Subsequently, the trained surrogate model is incorporated into a Bayesian inference framework with Dynamic Nested Sampling to infer posterior distributions of the EMC3-EIRENE input parameters. In this step, the FNN-predicted synthetic data are compared with the experimental data, and the likelihood function explicitly accounts for the measurement uncertainties of the selected diagnostics. EMC3-EIRENE simulations using the maximum a posteriori estimates derived from these posterior distributions reproduce experimental measurements with satisfactory accuracy. This neural network-based method significantly reduces computational costs and the need for manual parameter tuning, and it can be generalized to other similar modeling codes.
ISSN:0029-5515

Similar Items