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

While fusion reactors known as tokamaks hold promise as a firm energy source,advances in plasma control, and handling of events where control of plasmas islost, are needed for them to be economical. A significant bottleneck towardsapplying more advanced control algorithms is the need for better plasmasimulation, where both physics-based and data-driven approaches currently fallshort. The former is bottle-necked by both computational cost and thedifficulty of modelling plasmas, and the latter is bottle-necked by therelative paucity of data. To address this issue, this work applies the neuralordinary differential equations (ODE) framework to the problem of predicting asubset of plasma dynamics, namely the coupled plasma current and internalinductance dynamics. As the neural ODE framework allows for the naturalinclusion of physics-based inductive biases, we train both physics-based andneural network models on data from the Alcator C-Mod fusion reactor and findthat a model that combines physics-based equations with a neural ODE performsbetter than both existing physics-motivated ODEs and a pure neural ODE model.

Hybridizing Physics and Neural ODEs for Predicting Plasma Inductance Dynamics in Tokamak Fusion Reactors