Abstract
The substitution of time- and labor-intensive empirical research as well as slow finite difference time domain (FDTD) simulations with revolutionary techniques such as artificial neural network (ANN)-based predictive modeling is the next trend in the field of nanophotonics. In this work, we demonstrated that neural networks with proper architectures can rapidly predict the far-field optical response of core–shell plasmonic metastructures. The results obtained with artificial neural networks are comparable with FDTD simulations in accuracy but the speed of obtaining them is between 100–1000 times faster than FDTD simulations. Further, we have proven that ANNs does not have problems associated with FDTD simulations such as dependency of the speed of convergence on the size of the structure. The other trend in photonics is the inverse design problem, where the far-field optical response of a spherical core–shell metastructure can be linked to the design parameters such as type of the material(s), core radius, and shell thickness using a neural network. The findings of this paper provide evidence that machine learning (ML) techniques such as artificial neural networks can potentially replace time-consuming finite domain methods in the future.
Highlights
The substitution of time- and labor-intensive empirical research as well as slow finite difference time domain (FDTD) simulations with revolutionary techniques such as artificial neural network (ANN)-based predictive modeling is the trend in the field of nanophotonics
The validation loss function exhibited the same trend as the number of epochs increased and reached stable values in the range of 10−4, 10−4 and 10−6 for the absorption prediction network (APN), extinction prediction network (EPN) and scattering prediction network (SPN), respectively
In light of the fact that, on average, 20% of these data has never been used in the training or validation data sets, these results show an extremely acceptable agreement between FDTD simulation target spectra and the ANN predicted spectra
Summary
The substitution of time- and labor-intensive empirical research as well as slow finite difference time domain (FDTD) simulations with revolutionary techniques such as artificial neural network (ANN)-based predictive modeling is the trend in the field of nanophotonics. The other trend in photonics is the inverse design problem, where the far-field optical response of a spherical core–shell metastructure can be linked to the design parameters such as type of the material(s), core radius, and shell thickness using a neural network. A variety of plasmonic metals with different shapes such as spheres, cubes, stars, octahedra and triangles with different optical properties have been synthesized [6,7]. Amongst all these shapes, spheres are the easiest to fabricate while simultaneously achieving a monodisperse size distribution and preventing aggregation. Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
