Browse by author
Lookup NU author(s): Dr Sneha Verma
This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).
Nanophotonics exploits the best of photonics and nanotechnology which has transformed opticsin recent years by allowing subwavelength structures to enhance light‑matter interactions. Despitethese breakthroughs, design, fabrication, and characterization of such exotic devices have remainedthrough iterative processes which are often computationally costly, memory‑intensive, and time‑consuming. In contrast, deep learning approaches have recently shown excellent performance aspractical computational tools, providing an alternate avenue for speeding up such nanophotonicssimulations. This study presents a DNN framework for transmission, reflection, and absorption spectrapredictions by grasping the hidden correlation between the independent nanostructure properties andtheir corresponding optical responses. The proposed DNN framework is shown to require a sufficientamount of training data to achieve an accurate approximation of the optical performance derived fromcomputational models. The fully trained framework can outperform a traditional EM solution usingon the COMSOL Multiphysics approach in terms of computational cost by three orders of magnitude.Furthermore, employing deep learning methodologies, the proposed DNN framework makes aneffort to optimise design elements that influence the geometrical dimensions of the nanostructure,offering insight into the universal transmission, reflection, and absorption spectra predictions at thenanoscale. This paradigm improves the viability of complicated nanostructure design and analysis, andit has a lot of potential applications involving exotic light‑matter interactions between nanostructuresand electromagnetic fields. In terms of computational times, the designed algorithm is more than 700times faster as compared to conventional FEM method (when manual meshing is used). Hence, thisapproach paves the way for fast yet universal methods for the characterization and analysis of theoptical response of nanophotonic systems
Author(s): Verma Sneha, Chugh Sunny, Gosh Souvik, Rahman BMA
Publication type: Article
Publication status: Published
Journal: Scientific Reports
Year: 2023
Volume: 13
Online publication date: 20/01/2023
Acceptance date: 12/01/2023
Date deposited: 19/09/2024
ISSN (electronic): 2045-2322
Publisher: Nature
URL: https://doi.org/10.1038/s41598-023-28076-3
DOI: 10.1038/s41598-023-28076-3
Data Access Statement: All data generated or analysed during this study are included in the supplementary information in the graphical form. The raw datasets and computational models used and/or analysed during the current study available from the corresponding author on reasonable request.
Altmetrics provided by Altmetric
