English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

One of the most pressing challenges facing the fusion community is adequatelymitigating or, even better, avoiding disruptions of tokamak plasmas. However,before this can be done, disruptions must first be predicted with sufficientwarning time to actuate a response. The established field of survival analysisprovides a convenient statistical framework for time-to-event (i.e.time-to-disruption) studies. This paper demonstrates the integration of anexisting disruption prediction machine learning algorithm with the Kaplan-Meierestimator of survival probability. Specifically discussed are the impliedwarning times from binary classification of disruption databases and theinterpretation of output signals from Random Forest algorithms trained andtested on these databases. This survival analysis approach is applied to bothsmooth and noisy test data to highlight important features of the survival andhazard functions. In addition, this method is applied to three Alcator C-Modplasma discharges and compared to a threshold-based scheme for triggeringalarms. In one case, both techniques successfully predict the disruption;although, in another, neither warns of the impending disruption with enoughtime to mitigate. For the final discharge, the survival analysis approach couldavoid the false alarm triggered by the threshold method. Limitations of thisanalysis and opportunities for future work are also presented.

An application of survival analysis to disruption prediction via Random Forests