Metasurface‐Based Molecular Biosensing Aided by Artificial Intelligence

Tittl, Andreas; John‐Herpin, Aurelian; Leitis, Aleksandrs; Arvelo, Eduardo; Altug, Hatice

doi:10.1002/anie.201901443

Cited by 107 publications

(92 citation statements)

References 92 publications

(158 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Metasurfaces have emerged as one of the most exciting research directions in optics, where light scattering properties of materials can be controlled at will by designing subwavelength structures (“meta‐units”) that strongly interact with the incident light. [ 1–8 ] While originally only enabling static functionality, [ 9 ] these concepts have recently been extended towards active optical devices by employing tunable metasurfaces for sensing and light focusing applications, where the optical response can be controlled using light inclination, [ 10–12 ] stretchable substrates, [ 13 ] electrostatic biasing of two‐dimensional (2D) materials such as graphene, [ 14,15 ] and phase change materials. [ 16–18 ]…”

Section: Introductionmentioning

confidence: 99%

All‐Dielectric Programmable Huygens' Metasurfaces

Leitis

Heßler

Wahl

et al. 2020

Adv Funct Materials

Self Cite

187

151

View full text Add to dashboard Cite

Low-loss nanostructured dielectric metasurfaces have emerged as a breakthrough platform for ultrathin optics and cutting-edge photonic applications, including beam shaping, focusing, and holography. However, the static nature of their constituent materials has traditionally limited them to fixed functionalities. Tunable all-dielectric infrared Huygens' metasurfaces consisting of multi-layer Ge disk meta-units with strategically incorporated non-volatile phase change material Ge 3 Sb 2 Te 6 are introduced. Switching the phase-change material between its amorphous and crystalline structural state enables nearly full dynamic light phase control with high transmittance in the mid-IR spectrum. The metasurface is realized experimentally, showing postfabrication tuning of the light phase within a range of 81% of the full 2π phase shift. Additionally, the versatility of the tunable Huygen's metasurfaces is demonstrated by optically programming the spatial light phase distribution of the metasurface with single meta-unit precision and retrieving high-resolution phase-encoded images using hyperspectral measurements. The programmable metasurface concept overcomes the static limitations of previous dielectric metasurfaces, paving the way for "universal" metasurfaces and highly efficient, ultracompact active optical elements like tunable lenses, dynamic holograms, and spatial light modulators.

show abstract

Section: Introductionmentioning

confidence: 99%

All‐Dielectric Programmable Huygens' Metasurfaces

Leitis

Heßler

Wahl

et al. 2020

Adv Funct Materials

Self Cite

187

151

View full text Add to dashboard Cite

show abstract

“…gaining popularity. Several developments in ML over the past few years has motivated the researchers to explore its potential in the field of photonics, including multimode fibers [5], power splitter [6], plasmonics [7], grating coupler [8], photonic crystals [9], [10], metamaterials [11], photonic modes fields distribution [12], label-free cell classification [13], molecular biosensing [14], optical communications [15], [16] and networking [17], [18].…”

mentioning

confidence: 99%

Machine Learning Regression Approach to the Nanophotonic Waveguide Analyses

Chugh

Ghosh

Gulistan

et al. 2019

J. Lightwave Technol.

View full text Add to dashboard Cite

Machine learning is an application of artificial intelligence that focuses on the development of computer algorithms which learn automatically by extracting patterns from the data provided. Machine learning techniques can be efficiently used for a problem with a large number of parameters to be optimized and also where it is infeasible to develop an algorithm of specific instructions for performing the task. Here, we combine the finite element simulations and machine learning techniques for the prediction of mode effective indices, power confinement and coupling length of different integrated photonics devices. Initially, we prepare a dataset using COMSOL Multiphysics and then this data is used for training while optimizing various parameters of the machine learning model. Waveguide width, height, operating wavelength, and other device dimensions are varied to record different modal solution parameters. A detailed study has been carried out for a slot waveguide structure to evaluate different machine learning model parameters including number of layers, number of nodes, choice of activation functions, and others. After training, this model is used to predict the outputs for new input device specifications. This method predicts the output for different device parameters faster than direct numerical simulation techniques. Absolute percentage error of less than 5% in predicting an output has been obtained for slot, strip and directional waveguide coupler designs. This study pave the step towards using machine learning based optimization techniques for integrated silicon photonics devices. Index Terms-Machine learning, neural networks, regression, multilayer perceptron, silicon photonics. I. INTRODUCTION M ACHINE learning (ML) technology is being extensively used in many aspects of modern society: web searches, social networking, smartphones, bioinformatics, robotics, chatbots, and self-driving cars [1]. ML techniques are used to classify or detect objects in images, speech to text conversion, pattern recognition, natural language processing, sentiment analysis and recommendations of products/movies for users based on their search preferences. ML algorithms can be trained to perform exceptionally well when it is difficult to analyze the underlying physics and mathematics of the problem [2]. ML algorithms extract patterns from the raw data provided during the training without being explicitly programmed. The learned patterns can be used to make predictions on some other data of interest. ML systems can be trained more efficiently when massive amount of data is present [3], [4]. Recently, research on the application of ML techniques for optical communication systems and nanophotonic devices is

show abstract

“…In addition, AI techniques have also been employed for the inverse design of nanophotonic devices. After being trained with random initial populations of nanostructure geometries and their known spectra, the deep neural networks (DNNs) are able to predict the spectral response of new nanostructure designs, as well as design new nanostructures based on the wanted spectral response [254,255].…”

Section: Discussionmentioning

confidence: 99%

Progress of infrared guided-wave nanophotonic sensors and devices

Dong

Lee

2020

Nano Convergence

View full text Add to dashboard Cite

Nanophotonics, manipulating light-matter interactions at the nanoscale, is an appealing technology for diversified biochemical and physical sensing applications. Guided-wave nanophotonics paves the way to miniaturize the sensors and realize on-chip integration of various photonic components, so as to realize chip-scale sensing systems for the future realization of the Internet of Things which requires the deployment of numerous sensor nodes. Starting from the popular CMOS-compatible silicon nanophotonics in the infrared, many infrared guided-wave nanophotonic sensors have been developed, showing the advantages of high sensitivity, low limit of detection, low crosstalk, strong detection multiplexing capability, immunity to electromagnetic interference, small footprint and low cost. In this review, we provide an overview of the recent progress of research on infrared guided-wave nanophotonic sensors. The sensor configurations, sensing mechanisms, sensing performances, performance improvement strategies, and system integrations are described. Future development directions are also proposed to overcome current technological obstacles toward industrialization.

show abstract

Metasurface‐Based Molecular Biosensing Aided by Artificial Intelligence

Cited by 107 publications

References 92 publications

All‐Dielectric Programmable Huygens' Metasurfaces

All‐Dielectric Programmable Huygens' Metasurfaces

Machine Learning Regression Approach to the Nanophotonic Waveguide Analyses

Progress of infrared guided-wave nanophotonic sensors and devices

Contact Info

Product

Resources

About