This work successfully generates uncertainty aware surrogate models, via the
Bayesian neural network with noise contrastive prior (BNN-NCP) technique, of
the EuroPED plasma pedestal model using data from the JET-ILW pedestal database
and subsequent model evaluations. All this conform EuroPED-NN. The BNN-NCP
technique is proven to be a good fit for uncertainty aware surrogate models,
matching the output results as a regular neural network, providing prediction's
confidence as uncertainties, and highlighting the 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
$n_e\!\left(\psi_{\text{pol}}=0.94\right)$ with respect to increasing plasma
current, $I_p$, and second, validating the $\Delta-\beta_{p,ped}$ relation
associated with the EuroPED model. Affirming the robustness of the underlying
physics learned by the surrogate model.

通过使用 Bayesian 神经网络与噪声对比优先（BNN-NCP）技术，利用 JET-ILW 基座数据库和后续模型评估的数据成功生成了对 EuroPED 等离子体基座模型的不确定性感知代理模型。EuroPED-NN 通过提供模型的不确定性作为预测的置信度，以及利用代理模型的不确定性突出显示分布外区域，为模型的稳健性和可靠性提供关键见解。代理模型所学习到的基本物理性质的稳健性得到验证。