EuroPED-NN: Uncertainty aware surrogate model
This work addresses the need for robust and reliable surrogate models in plasma physics, specifically for the EuroPED model, by providing uncertainty quantification, which is incremental as it applies an existing BNN-NCP technique to this domain.
The authors tackled the problem of creating an uncertainty-aware surrogate model for the EuroPED plasma pedestal model using a Bayesian neural network with noise contrastive prior (BNN-NCP), resulting in a model that matches regular neural network outputs while providing confidence estimates and highlighting out-of-distribution regions, validated on JET-ILW and AUG data.
This work successfully generates an uncertainty-aware surrogate model of the EuroPED plasma pedestal model using the Bayesian neural network with noise contrastive prior (BNN-NCP) technique. This model is trained using data from the JET-ILW pedestal database and subsequent model evaluations, conforming to EuroPED-NN. The BNN-NCP technique has been proven to be a suitable method for generating uncertainty-aware surrogate models. It matches the output results of a regular neural network while providing confidence estimates for predictions as uncertainties. Additionally, it highlights out-of-distribution (OOD) regions using surrogate model uncertainties. This provides critical insights into model robustness and reliability. EuroPED-NN has been physically validated, first, analyzing electron density $n_e\!\left(ψ_{\text{pol}}=0.94\right)$ with respect to increasing plasma current, $I_p$, and second, validating the $Δ-β_{p,ped}$ relation associated with the EuroPED model. This affirms the robustness of the underlying physics learned by the surrogate model. On top of that, the method was used to develop a EuroPED-like model fed with experimental data, i.e. an uncertainty aware experimental model, which is functional in JET database. Both models have been also tested in $\sim 50$ AUG shots.