Within integrated tokamak plasma modeling, turbulent transport codes are typically the computational bottleneck limiting their routine use outside of post-discharge analysis. Neural network (NN) surrogates have been used to accelerate these calculations while retaining the desired accuracy of the physics-based models. This paper extends a previous NN model, known as QLKNN-hyper-10D, by incorporating the impact of impurities, plasma rotation, and magnetic equilibrium effects. This is achieved by adding a light impurity fractional density ($n_{\text{imp},\text{light}}/n_e$) and its normalized gradient, the normalized pressure gradient (α), the toroidal Mach number ($M_{\text{tor}}$), and the normalized toroidal flow velocity gradient. The input space was sampled based on experimental data from the JET tokamak to avoid the curse of dimensionality. The resulting networks, named QLKNN-jetexp-15D, show good agreement with the original QuaLiKiz model, both by comparing individual transport quantity predictions and by comparing its impact within the integrated model, JINTRAC. The profile-averaged RMS of the integrated modeling simulations is <10% for each of the five scenarios tested. This is non-trivial given the potential numerical instabilities present within the highly nonlinear system of equations governing plasma transport, especially considering the novel addition of momentum flux predictions to the model proposed here. An evaluation of all 25 NN output quantities at one radial location takes ∼0.1 ms, 10⁴ times faster than the original QuaLiKiz model. Within the JINTRAC integrated modeling tests performed in this study, using QLKNN-jetexp-15D resulted in a speed increase of only 60–100 as other physics modules outside of turbulent transport become the bottleneck.

中文翻译：

---

使用JET实验数据来填充训练空间的QuaLiKiz的神经网络替代

在集成的托卡马克等离子体建模中，湍流传输代码通常是计算瓶颈，限制了它们在放电后分析之外的常规使用。神经网络（NN）替代物已用于加速这些计算，同时保留了基于物理模型的所需精度。本文通过合并杂质，等离子体旋转和磁平衡效应的影响，扩展了先前的NN模型（称为QLKNN-hyper-10D）。这是通过添加轻杂质分数密度（${ñ}_{\text{小鬼}，\text{光}}/{ñ}_{Ë}$）及其归一化梯度，归一化压力梯度（α），环形马赫数（${\mathrm{中号}}_{\text{r}}$），以及归一化的环流速度梯度。输入空间是根据来自JET Tokamak的实验数据进行采样的，以避免维数的诅咒。所得的网络名为QLKNN-jetexp-15D，通过比较各个运输量预测并比较其在集成模型JINTRAC中的影响，显示出与原始QuaLiKiz模型的良好一致性。对于所测试的五个场景中的每一个，集成建模仿真的轮廓平均RMS <10％。考虑到在控制等离子体传输的高度非线性方程组中存在潜在的数值不稳定性，这是不平凡的，特别是考虑到此处提出的模型对动量通量预测的新颖添加。在一个径向位置上对所有25个NN输出量的评估大约需要0.1 ms，10 ms比原始QuaLiKiz模型快⁴倍。在这项研究中进行的JINTRAC集成建模测试中，使用QLKNN-jetexp-15D导致速度仅增加了60-100，这是湍流传输之外的其他物理模块成为了瓶颈。