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

Particle accelerators are enabling tools for scientific exploration anddiscovery in various disciplines. Finding optimized operation points for thesecomplex machines is a challenging task, however, due to the large number ofparameters involved and the underlying non-linear dynamics. Here, we introducetwo families of data-driven surrogate models, based on deep and invertibleneural networks, that can replace the expensive physics computer models. Thesemodels are employed in multi-objective optimisations to find Pareto optimaloperation points for two fundamentally different types of particleaccelerators. Our approach reduces the time-to-solution for a multi-objectiveaccelerator optimisation up to a factor of 640 and the computational cost up to98%. The framework established here should pave the way for future on-line andreal-time multi-objective optimisation of particle accelerators.

Fast, efficient and flexible particle accelerator optimisation using densely connected and invertible neural networks