Abstract
Advances in plasmonic materials and devices have given rise to a variety of applications in photocatalysis, microscopy, nanophotonics, and metastructures. With the advent of computing power and artificial neural networks, the characterization and design process of plasmonic nanostructures can be significantly accelerated using machine learning as opposed to conventional FDTD simulations. The machine learning (ML) based methods can not only perform with high accuracy and return optical spectra and optimal design parameters, but also maintain a stable high computing efficiency without being affected by the structural complexity. This work reviews the prominent ML methods involved in forward simulation and inverse design of plasmonic nanomaterials, such as Convolutional Neural Networks, Generative Adversarial Networks, Genetic Algorithms and Encoder–Decoder Networks. Moreover, we acknowledge the current limitations of ML methods in the context of plasmonics and provide perspectives on future research directions.
Highlights
Introduction to Plasmons and Plasmonic StructuresMetallic elements and compounds contain a sea of mobile charge carriers.Collective and coherent oscillations of the electron plasma can be excited through resonant interactions with light or electron beams
The exponential growth of computational power and computable data in different fields of science has provided an ideal environment for the application of diverse machine learning algorithms
We have discussed various algorithms applied in simulation tasks, solving PDEs involved in electromagnetic equations, imaging data analysis, and inverse design problems
Summary
Metallic elements and compounds contain a sea (or plasma) of mobile charge carriers. Collective and coherent oscillations of the electron plasma can be excited through resonant interactions with light or electron beams. Bulk plasmons are longitudinal oscillations in the interior of metallic structures (i.e., not close to the surface) and cannot be directly excited by light, which is a transverse electromagnetic wave [3,4]. The phenomenon related to the resulting plasma oscillations at the surface of the metallic nanoparticles is called localized since the associated electromagnetic plasmon resonancesurface (LSPR)plasmon since theresonance associated(LSPR). Surface plasmons enable the information carried by light waves to be squeezed into tiny volumes dramatically smaller in size than the wavelength of the corresponding coupled photons [15] This property is being actively studied to achieve generation intrachip optical interconnects to overcome the signal propagation delays in presently used copper interconnect technology [16]. Machine learning is becoming an increasingly important tool to create libraries of structure–property relationships and uncover hidden relationships between design variables and functional properties
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
