A fast neural network surrogate model for the eigenvalues of QuaLiKiz
Artikel i vetenskaplig tidskrift, 2023

We introduce a neural network surrogate model that predicts the eigenvalues for the turbulent microinstabilities, based on the gyrokinetic eigenvalue solver in QuaLiKiz. The model quickly provides information about the dominant instability for specific plasma conditions, and in addition, the eigenvalues offer a pathway for extrapolating transport fluxes. The model is trained on a 5 × 106 data points large dataset based on experimental data from discharges at the joint European torus, where each data point represents a QuaLiKiz simulation. The most accurate model was obtained when the task was split into a classification task to decide if the imaginary part of eigenvalues were stable ( ≤ 0 ) or not, and a regression model to calculate the eigenvalues once the classifier predicted the unstable class.

Författare

Emil Fransson

Chalmers, Rymd-, geo- och miljövetenskap, Astronomi och plasmafysik

Andreas Gillgren

Chalmers, Rymd-, geo- och miljövetenskap, Astronomi och plasmafysik

A. Ho

Dutch Institute for Fundamental Energy Research (DIFFER)

J. Borsander

Student vid Chalmers

O. Lindberg

Student vid Chalmers

W. Rieck

Student vid Chalmers

M. Åqvist

Student vid Chalmers

Pär Strand

Chalmers, Rymd-, geo- och miljövetenskap, Astronomi och plasmafysik

Physics of Plasmas

1070-664X (ISSN) 1089-7674 (eISSN)

Vol. 30 12 123904

Borderline: utveckling av en prediktiv kapacitet för kanteffekter i fusionsreaktorsrelevanta plasmor

Vetenskapsrådet (VR) (2020-05465), 2021-01-01 -- 2024-12-28.

Ämneskategorier

Subatomär fysik

Beräkningsmatematik

DOI

10.1063/5.0174643

Mer information

Senast uppdaterat

2024-01-10