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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Disruption in tokamak plasmas, stemming from various instabilities, poses acritical challenge, resulting in detrimental effects on the associated devices.Consequently, the proactive prediction of disruptions to maintain stabilityemerges as a paramount concern for future fusion reactors. While data-drivenmethodologies have exhibited notable success in disruption prediction,conventional neural networks within a frequentist approach cannot adequatelyquantify the uncertainty associated with their predictions, leading tooverconfidence. To address this limit, we utilize Bayesian deep probabilisticlearning to encompass uncertainty and mitigate false alarms, thereby enhancingthe precision of disruption prediction. Leveraging 0D plasma parameters fromEFIT and diagnostic data, a Temporal Convolutional Network adept at handlingmulti-time scale data was utilized. The proposed framework demonstratesproficiency in predicting disruptions, substantiating its effectiveness throughsuccessful applications to KSTAR experimental data.

Enhancing Disruption Prediction through Bayesian Neural Network in KSTAR