Advanced surrogate model for electron-scale turbulence in tokamak pedestals

TL;DR

This paper introduces an advanced surrogate model for predicting electron-scale turbulence in tokamak pedestals, utilizing sensitivity-driven sparse grid interpolation to incorporate key parameters and validate predictions across diverse conditions.

Contribution

The paper develops a novel surrogate model based on a sensitivity-driven sparse grid approach, capturing additional influential parameters for ETG-driven turbulence prediction.

Findings

Model accurately predicts electron heat flux influenced by multiple parameters.

Prediction intervals confirm model reliability beyond training data.

Model outperforms existing scaling laws in validation tests.

Abstract

We derive an advanced surrogate model for predicting turbulent transport at the edge of tokamaks driven by electron temperature gradient (ETG) modes.Our derivation is based on a recently developed sensitivity-driven sparse grid interpolation approach for uncertainty quantification and sensitivity analysis at scale, which informs the set of parameters that define the surrogate model as a scaling law.Our model reveals that ETG-driven electron heat flux is influenced by the safety factor $q$, electron beta $\beta_e$, and normalized electron Debye length $\lambda_D$, in addition to well-established parameters such as the electron temperature and density gradients. To assess the trustworthiness of our model's predictions beyond training, we compute prediction intervals using bootstrapping. The surrogate model's predictive power is tested across a wide range of parameter values, including within-distribution testing parameters (to verify our model) as well as out-of-bounds and out-of-distribution testing (to validate the proposed model). Overall, validation efforts show that our model competes well with, or can even outperform, existing scaling laws in predicting ETG-driven transport.