Towards Fast and Accurate Predictions of Radio Frequency Power Deposition and Current Profile via Data-driven Modeling

Three machine learning techniques (multilayer perceptron, random forest, and Gaussian process) provide fast surrogate models for lower hybrid current drive (LHCD) simulations. A single GENRAY/CQL3D simulation without radial diffusion of fast electrons requires several minutes of wall-clock time to complete, which is acceptable for many purposes, but too slow for integrated modeling and real-time control applications. The machine learning models use a database of 16,000+ GENRAY/CQL3D simulations for training, validation, and testing. Latin hypercube sampling methods ensure that the database covers the range of 9 input parameters ($n_{e0}$, $T_{e0}$, $I_p$, $B_t$, $R_0$, $n_{||}$, $Z_{eff}$, $V_{loop}$, $P_{LHCD}$) with sufficient density in all regions of parameter space. The surrogate models reduce the inference time from minutes to ~ms with high accuracy across the input parameter space.

三种机器学习技术——多层感知机（multilayer perceptron）、随机森林（random forest）与高斯过程（Gaussian process）——可用于构建低混杂电流驱动（lower hybrid current drive, LHCD）模拟的快速替代模型。单次不包含快电子径向扩散的GENRAY/CQL3D模拟需耗时数分钟的墙钟时间，虽可满足多数应用场景的需求，但对于集成建模与实时控制类应用而言仍过于缓慢。该类机器学习模型依托包含16000余条GENRAY/CQL3D模拟结果的数据库开展训练、验证与测试。研究采用拉丁超立方采样（Latin hypercube sampling）方法构建该数据库，确保其覆盖9项输入参数（$n_{e0}$、$T_{e0}$、$I_p$、$B_t$、$R_0$、$n_{||}$、$Z_{eff}$、$V_{loop}$、$P_{LHCD}$）的全范围，且在参数空间的所有区域均具备足够的采样密度。上述替代模型可将推理时间从数分钟缩短至约毫秒级，且在全输入参数空间内均保持较高的预测精度。