Efficient dataset construction using active learning and uncertainty-aware neural networks for plasma turbulent transport surrogate models

Abstract

This work demonstrates a proof-of-principle for using uncertainty-aware architectures, in combination with active learning techniques and an in-the-loop physics simulation code as a data labeller, to construct efficient datasets for data-driven surrogate model generation. Building off of a previous proof-of-principle successfully demonstrating training set reduction on static pre-labelled datasets, using the ADEPT framework, this strategy was applied again to the plasma turbulent transport problem within tokamak fusion plasmas, specifically the QuaLiKiz quasilinear electrostatic gyrokinetic turbulent transport code. While QuaLiKiz provides relatively fast evaluations, this study specifically targeted small datasets to serve as a proxy for more expensive codes, such as CGYRO or GENE. The newly implemented algorithm uses the SNGP architecture for the classification component of the problem and the BNN-NCP architecture for the regression component, training models for all turbulent modes (ITG, TEM, ETG) and all transport fluxes ($Q_e$, $Q_i$, ${\Gamma }_e$, ${\Gamma }_i$, and ${\Pi }_i$) described by the general QuaLiKiz output. With 45 active learning iterations, moving from a small initial training set of $10^2$ to a final set of $10^4$, the resulting models reached a $F_1$ classification performance of ~0.8 and a $R^2$ regression performance of ~0.75 on an independent test set across all outputs. This extrapolates to reaching the same performance and efficiency as the previous ADEPT pipeline, although on a problem with 1 extra input dimension. While the improvement rate achieved in this implementation diminishes faster than expected, the overall technique is formulated with components that can be upgraded and generalized to many surrogate modeling applications beyond plasma turbulent transport predictions.

References in corpus (12)

• Deep Learning in Neural Networks: An Overview
• Fast modeling of turbulent transport in fusion plasmas using neural networks
• Tractable flux-driven temperature, density, and rotation profile evolution with the quasilinear gyrokinetic transport model QuaLiKiz
• Active Learning and Bayesian Optimization: a Unified Perspective to Learn with a Goal
• Application of Gaussian process regression to plasma turbulent transport model validation via integrated modelling
• Self-consistent simulation of plasma scenarios for ITER using a combination of 1.5D transport codes and free-boundary equilibrium codes
• Neural network surrogate of QuaLiKiz using JET experimental data to populate training space
• First-principles-based multiple-isotope particle transport modelling at JET
• Multiple-isotope pellet cycles captured by turbulent transport modelling in the JET tokamak
• On Closed-Form Expressions for the Fisher-Rao Distance
• Fast transport simulations with higher-fidelity surrogate models for ITER
• EuroPED-NN: Uncertainty aware surrogate model