A machine learning framework for developing quasilinear saturation rules of turbulent transport from linear gyrokinetic data

TL;DR

This paper introduces SAT3-NN, a neural network model that predicts nonlinear saturated potential magnitudes from linear gyrokinetic data, improving flux predictions in turbulent transport modeling.

Contribution

The paper presents a novel neural network framework, SAT3-NN, that enhances the accuracy of quasilinear saturation rules derived from linear gyrokinetic data.

Findings

SAT3-NN outperforms previous models in predicting saturated potentials.

Flux predictions from SAT3-NN have smaller deviations from nonlinear simulation data.

The model reproduces the anti-gyroBohm scaling in TEM-dominated cases.

Abstract

A new neural network model for a quasilinear saturation rule has been developed to map linear gyrokinetic data to nonlinear saturated potential magnitudes to predict the total energy and particle fluxes. The training dataset is taken from the high resolution simulation database generated from nonlinear gyrokinetic turbulence simulations with the CGYRO code for developing the SAT3 model. This new model, named SAT3-NN, overall is able to capture the 1D saturated potential magnitudes of the dataset more accurately than SAT3, as depicted by lower percentage errors in the peak locations and peak values of the 1D saturated potentials. The resulting fluxes also had smaller deviations from the nonlinear CGYRO data as compared to previous saturation models such as SAT0 - SAT2. Consistent with SAT3, SAT3-NN is able to recreate the anti-gyroBohm scaling of fluxes seen for the TEM-dominated cases considered.