Cheap training sets for surrogate models of gyrokinetic turbulence
Model-based plasma scenario development lies at the heart of the design and operation of future fusion powerplants. Including gyrokinetic turbulence 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 gyrokinetic turbulence 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. We provide a benchmark study using available data from the literature for the QuaLiKiz quasilinear model. We demonstrate quantitatively that the physics-informed nature of the workflow proposed reduces the need to perform simulations in stable regions of the parameter space, resulting in significantly improved data efficiency compared to non-physics informed approaches which consider a regression problem over the whole domain. 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 surrogate on multichannel integrated modelling of ITG-dominated JET scenarios.