Machine learning characterisation of Alfv\'{e}nic and sub-Alfv\'{e}nic chirping and correlation with fast ion loss at NSTX

• Published in: arXiv.org 2020-01
• Main Authors: Woods, Benjamin J Q, Duarte, Vinícius N, Fredrickson, Eric D, Gorelenkov, Nikolai N, Podestà, Mario, Vann, Roddy G L
• Format: Article
• Language: English
• Subjects: Artificial intelligence; Beam injection; Correlation; Frequencies; Machine learning; Magnetic variations; Neutral beams; Spectrograms; Tokamak devices; Velocity
• ISSN: 2331-8422

Abrupt large events in the Alfv\'{e}nic and sub-Alfv\'{e}nic 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 behaviour of magnetic perturbations from corresponding frequency spectrograms that are typically identified by humans. Analysis allows for comparison between different mode character (such as quiescent, fixed-frequency, chirping, avalanching) and plasma parameters obtained from the TRANSP code such as the ratio of the neutral beam injection (NBI) velocity and the Alfv\'{e}n velocity (\(v_{\textrm{inj.}}/v_{\textrm{A}}\)), the \(q\)-profile, and the ratio of the neutral beam beta and the total plasma beta (\(\beta_{\textrm{beam},i}/\beta\)). In agreement with previous work by Fredrickson et al. [Nucl. Fusion 2014, 54 093007], we find 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 non-quiescent behaviour for magnetic fluctuations in the 50 - 200 kHz frequency band is observed along the boundary \(v_{\varphi} \lessapprox \frac{1}{4}(v_{\textrm{inj.}} - 3v_{\textrm{A}})\) where \(v_{\varphi}\) is the rotation velocity.