Machine Learning Characterization of Alfvénic and Sub-Alfvénic Chirping and Correlation With Fast-Ion Loss at NSTX.

Abrupt large events in the Alfvénic and sub-Alfvénic frequency bands in tokamaks are typically correlated with increased fast-ion loss. Here, machine learning is used to speed up the laborious process of characterizing the behavior of magnetic perturbations from corresponding frequency spectrograms that are typically identified by humans. The analysis allows for comparison between different mode character (such as quiescent, fixed frequency, chirping, and avalanching) and plasma parameters obtained from the TRANSP code, such as the ratio of the neutral beam injection (NBI) velocity and the Alfvén velocity ($v_{\textrm {inj.}}/v_{A}$), the $q$ -profile, and the ratio of the neutral beam beta and the total plasma beta ($\beta _{\textrm {beam},i}/\beta $). In agreement with the previous work by Fredrickson et al., we find a correlation between $\beta _{\textrm {beam},i}$ and mode character. In addition, previously unknown correlations are found between moments of the spectrograms and mode character. Character transition from quiescent to nonquiescent behavior for magnetic fluctuations in the 50–200 kHz frequency band is observed along the boundary $v_{\varphi } \lessapprox ({1}/{4})(v_{\textrm {inj.}} - 3v_{A})$ , where $v_{\varphi }$ is the rotation velocity. [ABSTRACT FROM AUTHOR]