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

Nanophotonics finds ever broadening applications requiring complex componentdesigns with a large number of parameters to be simultaneously optimized.Recent methodologies employing optimization algorithms commonly focus on asingle design objective, provide isolated designs, and do not describe how thedesign parameters influence the device behaviour. Here we propose anddemonstrate a machine-learning-based approach to map and characterize themulti-parameter design space of nanophotonic components. Pattern recognition isused to reveal the relationship between an initial sparse set of optimizeddesigns through a significant reduction in the number of characterizingparameters. This defines a design sub-space of lower dimensionality that can bemapped faster by orders of magnitude than the original design space. As aresult, multiple performance criteria are clearly visualized, revealing theinterplay of the design parameters, highlighting performance and structurallimitations, and inspiring new design ideas. This global perspective onhigh-dimensional design problems represents a major shift in how modernnanophotonic design is approached and provides a powerful tool to explorecomplexity in next-generation devices.

Mapping the global design space of nanophotonic components using machine learning pattern recognition