Deep Learning Enabled Nanophotonics

Huang, Lujun; Xu, Lei; Miroshnichenko, Andrey E.

doi:10.5772/intechopen.93289

Cited by 12 publications

(7 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several review articles have been published recently, which categorize in great detail the latest developments of deep learning applications in photonics and nano-optics. For an exhaustive overview we therefore invite the reader to consult these articles [29][30][31][32][33]. Also a few thematically more distantly related review articles have been published recently, which we want to indicate to the interested reader.…”

Section: This Work and Its Positioning With Respect To Other Reviewsmentioning

confidence: 99%

Deep learning in nano-photonics: inverse design and beyond

et al. 2021

View full text Add to dashboard Cite

Deep learning in the context of nano-photonics is mostly discussed in terms of its potential for inverse design of photonic devices or nanostructures. Many of the recent works on machine-learning inverse design are highly specific, and the drawbacks of the respective approaches are often not immediately clear. In this review we want therefore to provide a critical review on the capabilities of deep learning for inverse design and the progress which has been made so far. We classify the different deep learning-based inverse design approaches at a higher level as well as by the context of their respective applications and critically discuss their strengths and weaknesses. While a significant part of the community's attention lies on nano-photonic inverse design, deep learning has evolved as a tool for a large variety of applications. The second part of the review will focus therefore on machine learning research in nano-photonics "beyond inverse design". This spans from physics informed neural networks for tremendous acceleration of photonics simulations, over sparse data reconstruction, imaging and "knowledge discovery" to experimental applications. http://dx.doi.org/XX.XXXX/XX.XX.XXXXXX CONTENTS C Deep learning for interpretation of photonics experiments 11 4 Conclusions and perspectives 13

show abstract

Section: This Work and Its Positioning With Respect To Other Reviewsmentioning

confidence: 99%

Deep learning in nano-photonics: inverse design and beyond

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Due to the decrease of the total volume size of the Si nanoresonators after the air hole is introduced, one sees that the resonant positions for the transmission valley and peak have shifted together towards the shorter wavelength direction as compared to Figure 1. For an inverse design of the large number of filters with various central wavelengths, it is worth noting that the machine learning approach can be applied, which can introduce the remarkable design flexibility, that can exceed performance of the conventional optimisation methods for such types of the inverse design problems in nanophotonics [53][54][55][56] . Circular displacement currents are excited inside the Si nanodisk, as depicted by the electric near-field images shown in Figure 3(b-d), indicating the excitation of the longitudinal MD resonance.…”

Section: Design Of Metasurfacesmentioning

confidence: 99%

Planar narrow bandpass filter based on Si resonant metasurface

Zheng

Komar

Kamali

et al. 2021

Journal of Applied Physics

Self Cite

View full text Add to dashboard Cite

Optically resonant dielectric metasurfaces offer unique capability to fully control the wavefront, polarisation, intensity or spectral content of light based on the excitation and interference of different electric and magnetic Mie multipolar resonances. Recent advances of the wide accessibility in nanofabrication and nanotechnologies have led to a surge in the research field of high-quality functional optical metasurfaces which can potentially replace or even outperform conventional optical components with ultra-thin features. Replacing conventional optical filtering components with metasurface technology offers remarkable advantages including lower integration cost, ultra-thin compact configuration, easy combination with multiple functions and less restriction on materials. Here we propose and experimentally demonstrate a planar narrow band-pass filter based on the optical dielectric metasurface composed of Si nanoresonators in array. A broadband transmission spectral valley (around 200 nm) has been realised by combining electric and magnetic dipole resonances adjacent to each other. Meanwhile, we obtain a narrow-band transmission peak by exciting a high-quality leaky mode which is formed by partially breaking a bound state in the continuum generated by the collective longitudinal magnetic dipole resonances in the metasurface. Owing to the in-plane inversion symmetry of our nanostructure, the radiation of this antisymmetric mode is inhibited at far field, manifesting itself a sharp Fano-shape peak in the spectrum. Our proposed metasurface-based filter shows a stable performance for oblique light incidence with small angles (within 10 deg). Our work imply many potential applications of nanoscale photonics devices such as displays, spectroscopy, etc.

show abstract

“…A DL-assisted inverse design technique was reported for PCM-based tunable metasurfaces. 54 All of these reports, however, consider a single material throughout the study. Kiarashinejad et al 55 reported the inverse design of 1D metagratings using GST to achieve reconfigurable reflectivity.…”

Section: Introductionmentioning

confidence: 99%

Deep learning aids simultaneous structure–material design discovery: a case study on designing phase change material metasurfaces

et al. 2023

View full text Add to dashboard Cite

.The capabilities of modern precision nanofabrication and the wide choice of materials [plasmonic metals, high-index dielectrics, phase change materials (PCM), and 2D materials] make the inverse design of nanophotonic structures such as metasurfaces increasingly difficult. Deep learning is becoming increasingly relevant for nanophotonics inverse design. Although deep learning design methodologies are becoming increasingly sophisticated, the problem of the simultaneous inverse design of structure and material has not received much attention. In this contribution, we propose a deep learning-based inverse design methodology for simultaneous material choice and device geometry optimization. To demonstrate the utility of the proposed method, we consider the topical problem of active metasurface design using PCMs. We consider a set of four commonly used PCMs in both fully amorphous and crystalline material phases for the material choice and an arbitrarily specifiable polygonal meta-atom shape for the geometry part, which leads to a vast structure/material design space. We find that a suitably designed deep neural network can achieve good optical spectrum prediction capability in an ample design space. Furthermore, we show that this forward model has a sufficiently high predictive ability to be used in a surrogate-optimization setup resulting in the inverse design of active metasurfaces of switchable functionality.

show abstract

Deep Learning Enabled Nanophotonics

Cited by 12 publications

References 31 publications

Deep learning in nano-photonics: inverse design and beyond

Deep learning in nano-photonics: inverse design and beyond

Planar narrow bandpass filter based on Si resonant metasurface

Deep learning aids simultaneous structure–material design discovery: a case study on designing phase change material metasurfaces

Contact Info

Product

Resources

About