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

Understanding the time evolution of physical systems is crucial to revealingfundamental characteristics that are hidden in frequency domain. In opticalscience, high-quality resonance cavities and enhanced interactions with mattersare at the heart of modern quantum technologies. However, capturing their timedynamics in real-world scenarios suffers from long data acquisition and lowanalysis accuracy due to slow convergence and limited time window. Here, wereport a physics-guided and physics-explainable recurrent neural network toprecisely forecast the time-domain response of resonance features with theshortest acquired input sequence being 7\% of full length, and to infercorresponding resonance frequencies. The model is trained in a two-stepmulti-fidelity framework for high-accuracy forecast, where the first step isbased on a large amount of low-fidelity physical-model-generated synthetic dataand second step involves a small set of high-fidelity application-orientedobservational data. Through both simulations and experiments, we demonstratethat the model is universally applicable to a wide range of resonances,including dielectric metasurfaces, graphene plasmonics, and ultrastronglycoupled Landau polaritons, where our model accurately captures small signalfeatures and learns essential physical quantities. The demonstrated machinelearning algorithm offers a new way to accelerate the exploration of physicalphenomena and the design of devices under resonance-enhanced light-matterinteraction.

Physics-Guided and Physics-Explainable Recurrent Neural Network for Time Dynamics in Optical Resonances