Efficient training sets for surrogate models of tokamak turbulence with Active Deep Ensembles

TL;DR

This paper introduces ADEPT, a physics-informed active learning approach that significantly reduces the data requirements for training surrogate models of tokamak turbulence, enabling faster and more efficient plasma simulations.

Contribution

The work presents a novel active learning strategy that improves data efficiency for surrogate modeling of plasma turbulence, validated on existing models and real JET scenarios.

Findings

Up to 20-fold reduction in training data needed.

Surrogates recover QuaLiKiz performance within 10%.

Two orders of magnitude fewer data points required.

Abstract

Model-based plasma scenario development lies at the heart of the design and operation of future fusion powerplants. Including turbulent transport in integrated models is essential for delivering a successful roadmap towards operation of ITER and the design of DEMO-class devices. Given the highly iterative nature of integrated models, fast machine-learning-based surrogates of turbulent transport are fundamental to fulfil the pressing need for faster simulations opening up pulse design, optimization, and flight simulator applications. A significant bottleneck is the generation of suitably large training datasets covering a large volume in parameter space, which can be prohibitively expensive to obtain for higher fidelity codes. In this work, we propose ADEPT (Active Deep Ensembles for Plasma Turbulence), a physics-informed, two-stage Active Learning strategy to ease this challenge. Active Learning queries a given model by means of an acquisition function that identifies regions where additional data would improve the surrogate model. We provide a benchmark study using available data from the literature for the QuaLiKiz quasilinear transport model. We demonstrate quantitatively that the physics-informed nature of the proposed workflow reduces the need to perform simulations in stable regions of the parameter space, resulting in significantly improved data efficiency. We show an up to a factor of 20 reduction in training dataset size needed to achieve the same performance as random sampling. We then validate the surrogates on multichannel integrated modelling of ITG-dominated JET scenarios and demonstrate that they recover the performance of QuaLiKiz to better than 10\%. This matches the performance obtained in previous work, but with two orders of magnitude fewer training data points.