Plasma Confinement State Classification via FPP Relevant Microwave Diagnostics

TL;DR

The paper tackles real-time confinement-state identification in fusion power plants under strict diagnostic constraints by using only electron cyclotron emission to classify L-mode versus H-mode. It embeds the electron temperature profile $T_e(R,t)$ into seven radial basis function weights and trains a HistGradientBoostingClassifier to achieve an average test accuracy of $96\%$ and an F1 score of $95\%$, with demonstrated robustness to channel loss and density-limit effects. The approach emphasizes reactor-readiness by leveraging boundary-safe diagnostics (ECE, CO2 interferometer, and magnetic measurements) and a transparent, physics-informed feature space. This minimalist yet reliable framework supports resilient plasma control architectures for future FPPs, and the authors outline paths to extend the method with additional reactor-relevant diagnostics as fallbacks.

Abstract

We present a parsimonious and robust machine learning approach for identifying plasma confinement states in fusion power plants (FPPs) where reliable identification of the low-confinement (L-mode) and high-confinement (H-mode) regimes is critical for safe and efficient operation. Unlike research-oriented devices, FPPs must operate with a severely constrained set of diagnostics. To address this challenge, we demonstrate that a minimalist model, using only electron cyclotron emission (ECE) signals, can deliver accurate and reliable state classification. ECE provides electron temperature profiles without the engineering or survivability issues of in-vessel probes, making it a primary candidate for FPP-relevant diagnostics. Our framework employs ECE as input, extracts features with radial basis functions, and applies a gradient boosting classifier, achieving high accuracy with test accuracy averaging 96\% correct predictions. Robustness analysis and feature importance study confirm the reliability of the approach. These results demonstrate that state-of-the-art performance is attainable from a restricted diagnostic set, paving the way for minimalist yet resilient plasma control architectures for FPPs.

Figures (12)

• Figure 1: This figure shows the breakdown of L-mode and H-mode data points in the data unprocessed 40 chord data set. The t-SNE algorithm was utilized to visualize the ECE data space and how it naturally separates out the L mode and H mode.
• Figure 2: This figure shows the same t-SNE plot as in figure \ref{['LH_TSNSE']}, but with a color bar indicating the different shot number values. This plot illustrates that the ECE data space is well sampled by the fact that repetitive ECE behavior is seen by overlapping points of data that occurred weeks or months apart during different physics experiments.
• Figure 3: A histogram of plasma parameters, power inputs, and shape parameters from the labeled dataset are presented here to quantify the data space. Each data point was taken from the shot at the time of training/testing (if available). The term, drsep, refers to the outboard radial distance to the second separatrix; negative values of drsep describe Lower Single Null (LSN), positive values describe Upper Single Null (USN), and values near zero describe a Double Null configurations.
• Figure 4: ECE data from L-mode shot 203047 at time 4500 ms and H-mode shot 203191 at time 2400 ms are each interpolated with 7 Gaussian RBFs and plotted. The 7 centers from the RBFs were placed equally distant apart, one at each end and 5 equally spaced within.
• Figure 5: An ROC Curve of each of the 7 center weight pairings is made using a simple decision stump classifier that was carefully scaled across the data set. These curves illustrate which regions of the profile provide the most discriminative information for mode classification.