Machine learning enhanced predictions of ICRF heating: Overcoming numerical limitations via data curation

In this work we present the development of robust surrogate models for Ion Cyclotron Range of Frequencies (ICRF) and High-Harmonic Fast Wave (HHFW) heating predictions in fusion plasmas. Building upon our previous efforts to achieve real-time capable models, we identify the cause of the outliers found using TORIC in certain HHFW heating scenarios. The outliers are observed to be spurious ion Bernstein wave (IBW)- like modes caused by a wavelength control algorithm designed to address challenging scenarios with high perpendicular wavenumbers. The effect arises from the modulation in the perpendicular susceptibility, which can induce sign reversal and IBW-like propagation for scenarios featuring normalized ion Larmor radius lambda_i >> 1. We use TORIC with this algorithm disabled to generate a novel HHFW-NSTX database that is free of outliers. Surrogate models trained on this database, including Random Forest Regressors (RFR), Multi- Layer Perceptrons (MLP), and Gaussian Process Regressors (GPR), demonstrate the ability to accurately predict HHFW heating profiles, with regression scores of R^2 = [0.93−0.99]. Additionally we demonstrate that it is possible to generalize predictions beyond training data by the use of both RFR and GPR models, enabling the prediction of scenarios previously limited to the original model. GPR models also provide uncertainty quantification, offering insights into model confidence. This work introduces a comprehensive Verification, Validation, and Uncertainty Quantification (VVUQ) methodology for surrogate modeling, applicable not only to ICRF heating but also to other RF heating challenges and fusion physics problems. Beyond accelerated inference, these models show performant extrapolation capabilities, providing an alternative for addressing numerical challenges.本研究开发了适用于聚变等离子体中离子回旋频段（Ion Cyclotron Range of Frequencies, ICRF）与高谐波快波（High-Harmonic Fast Wave, HHFW）加热预测的鲁棒代理模型。本研究此前已开展具备实时推理能力模型的相关工作，在此基础上，我们定位了在特定HHFW加热场景中通过TORIC模拟得到的结果中出现异常值的成因。经观测，该类异常值为伪离子伯恩斯坦波（spurious ion Bernstein wave, IBW）类模态，其产生原因是为解决高垂直波数复杂场景而设计的波长控制算法。该效应源于垂直磁化率的调制，当场景满足归一化离子拉莫尔半径λ_i远大于1时，这种调制会引发符号反转与类IBW的传播行为。本研究通过禁用该算法的TORIC模拟，构建了无异常值的新型HHFW-NSTX数据库。基于该数据库训练的代理模型，包括随机森林回归器（Random Forest Regressors, RFR）、多层感知机（Multi-Layer Perceptrons, MLP）与高斯过程回归器（Gaussian Process Regressors, GPR），均可精准预测HHFW加热剖面，其回归决定系数R²介于0.93至0.99之间。此外，本研究证明，通过随机森林回归器与高斯过程回归器模型，可实现对训练数据分布外场景的泛化预测，能够对原有模型无法覆盖的场景进行预测。高斯过程回归器还可提供不确定性量化结果，为模型置信度评估提供参考依据。本研究提出了一套完整的代理模型验证、确认与不确定性量化（Verification, Validation, and Uncertainty Quantification, VVUQ）方法论，该方法不仅适用于ICRF加热场景，还可推广至其他射频加热相关挑战与聚变物理问题。除了加速推理之外，这些模型还展现出优异的外推能力，为解决数值模拟难题提供了新的替代方案。