Smart inverse design of graphene-based photonic metamaterials by an adaptive artificial neural network

Meta-Attention Deep Learning for Smart Development of Metasurface Sensors

Optical metasurfaces with pronounced spectral characteristics are promising for sensor applications. Currently, deep learning (DL) offers a rapid manner to design various metasurfaces. However, conventional DL models are usually assumed as black boxes, which is difficult to explain how a DL model learns physical features, and they usually predict optical responses of metasurfaces in a fuzzy way. This makes them incapable of capturing critical spectral features precisely, such as high quality (Q) resonances, and hinders their use in designing metasurface sensors. Here, a transformer-based explainable DL model named Metaformer for the high-intelligence design, which adopts a spectrum-splitting scheme to elevate 99% prediction accuracy through reducing 99% training parameters, is established. Based on the Metaformer, all-dielectric metasurfaces based on quasi-bound states in the continuum (Q-BIC) for high-performance metasensing are designed, and fabrication experiments are guided potently. The explainable learning relies on spectral position encoding and multi-head attention of meta-optics features, which overwhelms traditional black-box models dramatically. The meta-attention mechanism provides deep physics insights on metasurface sensors, and will inspire more powerful DL design applications on other optical devices.

Deep neural network-enabled dual-functional wideband absorbers

The increasing interest in switchable and tunable wideband perfect absorbers for applications such as modulation, energy harvesting, and spectroscopy has significantly driven research efforts. In this study, we present a dual-function terahertz (THz) metamaterial absorber supported by deep neural networks (DNN). This absorber achieves dual-wideband perfect absorption through the use of graphene and vanadium dioxide (VO₂), enabling both switching and tuning functionalities. Simulation results show that, in the insulating phase of VO₂, a high-frequency wideband absorption ranging from 9.31 to 9.77 THz is achieved, with an absorption rate exceeding 90%. In contrast, in the metallic phase of VO₂, a full-band wideband absorption above 90% is observed from 8.44 to 9.75 THz. The corresponding fractional bandwidths are 61.3% and 174.6%, respectively. Additionally, electrical tuning of graphene's Fermi level from 0.01 to 1 eV enables continuous modulation of absorption intensity between 48 and 100%. The absorber also exhibits polarization insensitivity to TE and TM waves due to its symmetric design and broad incidence angle. This design holds significant potential for various THz applications, including switching, electromagnetic shielding, stealth technology, filtering, and sensing.

Deep learning-driven forward and inverse design of nanophotonic nanohole arrays: streamlining design for tailored optical functionalities and enhancing accessibility

In nanophotonics, nanohole arrays (NHAs) are periodic arrangements of nanoscale apertures in thin films that provide diverse optical functionalities essential for various applications. Fully studying NHAs' optical properties and optimizing performance demands understanding both materials and geometric parameters, which presents a computational challenge due to numerous potential combinations. Efficient computational modeling is critical for overcoming this challenge and optimizing NHA-based device performance. Traditional approaches rely on time-consuming numerical simulation processes for device design and optimization. However, using a deep learning approach offers an efficient solution for NHAs design. In this work, a deep neural network within the forward modeling framework accurately predicts the optical properties of NHAs by using device structure data such as periodicity and hole radius as model inputs. We also compare three deep learning-based inverse modeling approaches-fully connected neural network, convolutional neural network, and tandem neural network-to provide approximate solutions for NHA structures based on their optical responses. Once trained, the DNN accurately predicts the desired result in milliseconds, enabling repeated use without wasting computational resources. The models are trained using over 6000 samples from a dataset obtained by finite-difference time-domain (FDTD) simulations. The forward model accurately predicts transmission spectra, while the inverse model reliably infers material attributes, lattice geometries, and structural parameters from the spectra. The forward model accurately predicts transmission spectra, with an average Mean Squared Error (MSE) of 2.44 × 10-4. In most cases, the inverse design demonstrates high accuracy with deviations of less than 1.5 nm for critical geometrical parameters. For experimental verification, gold nanohole arrays are fabricated using deep UV lithography. Validation against experimental data demonstrates the models' robustness and precision. These findings show that the trained DNN models offer accurate predictions about the optical behavior of NHAs.

Deep neural network-enabled multifunctional switchable terahertz metamaterial devices

Under the support of deep neural networks (DNN), a multifunctional switchable terahertz metamaterial (THz MMs) device is designed and optimized. This device not only achieves ideal ultra-wideband (UWB) absorption in the THz frequency range but enables dual-functional polarization transformation over UWB. When vanadium dioxide (VO2) is in the metallic state, the device as a UWB absorber with an absorption rate exceeding 90% in the 2.43-10 THz range, with a relative bandwidth (RBW) of 145.2%, and its wideband absorption performance is insensitive to polarization. When VO2 is in the insulating state, the device can switch to a polarization converter, achieving conversions from linear to cross polarization and from linear to circular polarization in the ranges of 4.58-10 THz and 4.16-4.43 THz, respectively. Within the 4.58-10 THz range, the polarization conversion ratio approaches 100% with an RBW of 74.3%, the polarization rotation angle is near 90°. Within the 4.16-4.43 THz range, the RBW is 6.29% and the ellipticity ratio approaches 1, Moreover, the effects of incident angle and polarization angle on the operational characteristics are studied. This THz MMs due to its advantages of wide angle, broad bandwidth, and high efficiency, provides valuable references for the research of new multifunctional THz devices. It has great application potential in short-range wireless THz communication, ultrafast optical switches, high-temperature resistant switches, transient spectroscopy, and optical polarization control devices.

Chiral Metasurface Multifocal Lens in the Terahertz Band Based on Deep Learning

Chiral metasurfaces have garnered significant interest as an emerging field of metamaterials, primarily due to their exceptional capability to manipulate phase distributions at interfaces. However, the on-demand design of chiral metasurface structures remains a challenging task. To address this challenge, this paper introduces a deep learning-based network model for rapid calculation of chiral metasurface structure parameters. The network achieves a mean absolute error (MAE) of 0.025 and enables the design of chiral metasurface structures with a circular dichroism (CD) of 0.41 at a frequency of 1.169 THz. By changing the phase of the chiral metasurface, it is possible to produce not only a monofocal lens but also a multifocal lens. Well-designed chiral metasurface lenses allow us to control the number and position of focal points of the light field. This chiral metasurface, designed using deep learning, demonstrates great multifocal focus characteristics and holds great potential for a wide range of applications in sensing and holography.

Broadband Solar Metamaterial Absorbers Empowered by Transformer-Based Deep Learning

The research of metamaterial shows great potential in the field of solar energy harvesting. In the past decade, the design of broadband solar metamaterial absorber (SMA) has attracted a surge of interest. The conventional design typically requires brute-force optimizations with a huge sampling space of structure parameters. Very recently, deep learning (DL) has provided a promising way in metamaterial design, but its application on SMA development is barely reported due to the complicated features of broadband spectrum. Here, this work develops the DL model based on metamaterial spectrum transformer (MST) for the powerful design of high-performance SMAs. The MST divides the optical spectrum of metamaterial into N patches, which overcomes the severe problem of overfitting in traditional DL and boosts the learning capability significantly. A flexible design tool based on free customer definition is developed to facilitate the real-time on-demand design of metamaterials with various optical functions. The scheme is applied to the design and fabrication of SMAs with graded-refractive-index nanostructures. They demonstrate the high average absorptance of 94% in a broad solar spectrum and exhibit exceptional advantages over many state-of-the-art counterparts. The outdoor testing implies the high-efficiency energy collection of about 1061 kW h m^-2 from solar radiation annually. This work paves a way for the rapid smart design of SMA, and will also provide a real-time developing tool for many other metamaterials and metadevices.

Recent advances in density functional theory approach for optoelectronics properties of graphene

Graphene has received tremendous attention among diverse 2D materials because of its remarkable properties. Its emergence over the last two decades gave a new and distinct dynamic to the study of materials, with several research projects focusing on exploiting its intrinsic properties for optoelectronic devices. This review provides a comprehensive overview of several published articles based on density functional theory and recently introduced machine learning approaches applied to study the electronic and optical properties of graphene. A comprehensive catalogue of the bond lengths, band gaps, and formation energies of various doped graphene systems that determine thermodynamic stability was reported in the literature. In these studies, the peculiarity of the obtained results reported is consequent on the nature and type of the dopants, the choice of the XC functionals, the basis set, and the wrong input parameters. The different density functional theory models, as well as the strengths and uncertainties of the ML potentials employed in the machine learning approach to enhance the prediction models for graphene, were elucidated. Lastly, the thermal properties, modelling of graphene heterostructures, the superconducting behaviour of graphene, and optimization of the DFT models are grey areas that future studies should explore in enhancing its unique potential. Therefore, the identified future trends and knowledge gaps have a prospect in both academia and industry to design future and reliable optoelectronic devices.

Machine learning-augmented surface-enhanced spectroscopy toward next-generation molecular diagnostics

The world today is witnessing the significant role and huge demand for molecular detection and screening in healthcare and medical diagnosis, especially during the outbreak of COVID-19. Surface-enhanced spectroscopy techniques, including Surface-Enhanced Raman Scattering (SERS) and Infrared Absorption (SEIRA), provide lattice and molecular vibrational fingerprint information which is directly linked to the molecular constituents, chemical bonds, and configuration. These properties make them an unambiguous, nondestructive, and label-free toolkit for molecular diagnostics and screening. However, new issues in molecular diagnostics, such as increasing molecular species, faster spread of viruses, and higher requirements for detection accuracy and sensitivity, have brought great challenges to detection technology. Advancements in artificial intelligence and machine learning (ML) techniques show promising potential in empowering SERS and SEIRA with rapid analysis and automatic data processing to jointly tackle the challenge. This review introduces the combination of ML and SERS/SEIRA by investigating how ML algorithms can be beneficial to SERS/SEIRA, discussing the general process of combining ML and SEIRA/SERS, highlighting the molecular diagnostics and screening applications based on ML-combined SEIRA/SERS, and providing perspectives on the future development of ML-integrated SEIRA/SERS. In general, this review offers comprehensive knowledge about the recent advances and the future outlook regarding ML-integrated SEIRA/SERS for molecular diagnostics and screening.

Lightweight Machine-Learning Model for Efficient Design of Graphene-Based Microwave Metasurfaces for Versatile Absorption Performance

Graphene, as a widely used nanomaterial, has shown great flexibility in designing optically transparent microwave metasurfaces with broadband absorption. However, the design of graphene-based microwave metasurfaces relies on cumbersome parameter sweeping as well as the expertise of researchers. In this paper, we propose a machine-learning network which enables the forward prediction of reflection spectra and inverse design of versatile microwave absorbers. Techniques such as the normalization of input and transposed convolution layers are introduced in the machine-learning network to make the model lightweight and efficient. Particularly, the tunable conductivity of graphene enables a new degree in the intelligent design of metasurfaces. The inverse design system based on the optimization method is proposed for the versatile design of microwave absorbers. Representative cases are demonstrated, showing very promising performances on satisfying various absorption requirements. The proposed machine-learning network has significant potential for the intelligent design of graphene-based metasurfaces for various microwave applications.

Fabrication of graphene-based sensor for exposure to different chemicals

Opto-chemical sensors are the most significant type of sensors that are widely used to detect a variety of volatile organic compounds and chemicals. This research work demonstrates the fabrication and characterization of an opto-chemical sensor based on a graphene thin film. A 300 nm graphene thin film was deposited on clean glass with the help of RF magnetron sputtering. The structure, surface and quality of the graphene thin film were characterized using XRD, SEM and Raman spectroscopy. For optical characterization, the thin film was exposed to IPA, acetone and toluene (separately) for five, ten and fifteen minutes. The optical transmission was then observed via UV-NIR spectroscopy in the near-infrared range (900 to 1450 nm). The thin film of graphene has expressed a sharp response time and recovery time with high sensitivity for each chemical. However, by comparing the output of the graphene thin film in response to each chemical, it was observed that graphene thin film has a better transmission and sensing rate for exposure to toluene.

Optimization of metamaterials and metamaterial-microcavity based on deep neural networks

Computational inverse-design and forward prediction approaches provide promising pathways for on-demand nanophotonics. Here, we use a deep-learning method to optimize the design of split-ring metamaterials and metamaterial-microcavities. Once the deep neural network is trained, it can predict the optical response of the split-ring metamaterial in a second which is much faster than conventional simulation methods. The pretrained neural network can also be used for the inverse design of split-ring metamaterials and metamaterial-microcavities. We use this method for the design of the metamaterial-microcavity with the absorptance peak at 1310 nm. Experimental results verified that the deep-learning method is a fast, robust, and accurate method for designing metamaterials with complex nanostructures.

Synthesis of multi-band reflective polarizing metasurfaces using a generative adversarial network

Electromagnetic linear-to-circular polarization converters with wide- and multi-band capabilities can simplify antenna systems where circular polarization is required. Multi-band solutions are attractive in satellite communication systems, which commonly have the additional requirement that the sense of polarization is reversed between adjacent bands. However, the design of these structures using conventional ad hoc methods relies heavily on empirical methods. Here, we employ a data-driven approach integrated with a generative adversarial network to explore the design space of the polarizer meta-atom thoroughly. Dual-band and triple-band reflective polarizers with stable performance over incident angles up to and including 30°, corresponding to typical reflector antenna system requirements, are synthesized using the proposed method. The feasibility and performance of the designed polarizer is validated through measurements of a fabricated prototype.

Machine Learning in Interpolation and Extrapolation for Nanophotonic Inverse Design

The algorithmic design of nanophotonic structures promises to significantly improve the efficiency of nanophotonic components due to the strong dependence of electromagnetic function on geometry and the unintuitive connection between structure and response. Such approaches, however, can be highly computationally intensive and do not ensure a globally optimal solution. Recent theoretical results suggest that machine learning techniques could address these issues as they are capable of modeling the response of nanophotonic structures at orders of magnitude lower time per result. In this work, we explore the utilization of artificial neural network (ANN) techniques to improve the algorithmic design of simple absorbing nanophotonic structures. We show that different approaches show various aptitudes in interpolation versus extrapolation, as well as peak performances versus consistency. Combining ANNs with classical machine learning techniques can outperform some standard ANN techniques for forward design, both in terms of training speed and accuracy in interpolation, but extrapolative performance can suffer. Networks pretrained on general image classification perform well in predicting optical responses of both interpolative and extrapolative structures, with very little additional training time required. Furthermore, we show that traditional deep neural networks are able to perform significantly better in extrapolation than more complicated architectures using convolutional or autoencoder layers. Finally, we show that such networks are able to perform extrapolation tasks in structure generation to produce structures with spectral responses significantly outside those of the structures on which they are trained.

Fabrication and Characterization of a Highly Sensitive and Flexible Tactile Sensor Based on Indium Zinc Oxide (IZO) with Imprecise Data Analysis

Tactile sensors are widely used in the electronic industry. In the following research work, we proposed a tactile sensor based on indium zinc oxide (IZO) electrodes and used neutrosophic statistics to analyze the capacitance and resistance of the tactile sensor. The tactile sensor was fabricated by depositing the IZO electrodes on a polycarbonate substrate (a thin layer). The IZO was characterized through X-ray diffraction (XRD), field emission scanning electron microscopy (FESEM), and ultraviolet-visible (UV-vis) spectroscopy techniques. The sensor's electrical properties were characterized using an LCR meter, i.e., capacitance and resistance were measured in intervals with respect to changes in the applied force on the sensor at 1 kHz operational frequency. The sensor expressed high sensitivity with quick response and recovery times. The sensor also expressed long-term stability. For the analysis of capacitance and resistance, two statistical approaches, i.e., classical and neutrosophic approaches, were applied, and the better analysis approach for the sensor was found.

Inverse Design for Coating Parameters in Nano-Film Growth Based on Deep Learning Neural Network and Particle Swarm Optimization Algorithm

The NN (neural network)-PSO (particle swarm optimization) method is demonstrated to be able to inversely extract the coating parameters for the multilayer nano-films through a simulation case and two experimental cases to verify its accuracy and robustness. In the simulation case, the relative error (RE) between the average layer values and the original one was less than 3.45% for 50 inverse designs. In the experimental anti-reflection (AR) coating case, the mean thickness values of the inverse design results had a RE of around 5.05%, and in the Bragg reflector case, the RE was less than 1.03% for the repeated inverse simulations. The method can also be used to solve the single-solution problem of a tandem neural network in the inverse process.

Deep learning in light-matter interactions

The deep-learning revolution is providing enticing new opportunities to manipulate and harness light at all scales. By building models of light-matter interactions from large experimental or simulated datasets, deep learning has already improved the design of nanophotonic devices and the acquisition and analysis of experimental data, even in situations where the underlying theory is not sufficiently established or too complex to be of practical use. Beyond these early success stories, deep learning also poses several challenges. Most importantly, deep learning works as a black box, making it difficult to understand and interpret its results and reliability, especially when training on incomplete datasets or dealing with data generated by adversarial approaches. Here, after an overview of how deep learning is currently employed in photonics, we discuss the emerging opportunities and challenges, shining light on how deep learning advances photonics.

Artificial Intelligence in Meta-optics

Recent years have witnessed promising artificial intelligence (AI) applications in many disciplines, including optics, engineering, medicine, economics, and education. In particular, the synergy of AI and meta-optics has greatly benefited both fields. Meta-optics are advanced flat optics with novel functions and light-manipulation abilities. The optical properties can be engineered with a unique design to meet various optical demands. This review offers comprehensive coverage of meta-optics and artificial intelligence in synergy. After providing an overview of AI and meta-optics, we categorize and discuss the recent developments integrated by these two topics, namely AI for meta-optics and meta-optics for AI. The former describes how to apply AI to the research of meta-optics for design, simulation, optical information analysis, and application. The latter reports the development of the optical Al system and computation via meta-optics. This review will also provide an in-depth discussion of the challenges of this interdisciplinary field and indicate future directions. We expect that this review will inspire researchers in these fields and benefit the next generation of intelligent optical device design.

Machine-learning reinforcement for optimizing multilayered thin films: applications in designing broadband antireflection coatings

The design and fabrication of nanoscale multilayered thin films play an essential role in regulating the operation efficiency of sensitive optical sensors and filters. In this paper, we introduce a packaged tool that employs flexible electromagnetic calculation software with machine learning in order to find the optimized double-band antireflection coatings in intervals of wavelength from 3 to 5 µm and 8 to 12 µm. Instead of computing or modeling an extremely enormous set of thin film structures, this tool enhanced with machine learning can swiftly predict the optical properties of a given structure with >99.7% accuracy and a substantial reduction in computation costs. Furthermore, the tool includes two learning methods that can infer a global optimal structure or suitable local optimal ones. Specifically, these well-trained models provide the highest accurate double-band average transmission coefficient combined with the lowest number of layers or the thinnest total thickness starting from a reference multilayered structure. Finally, the more sophisticated enhancement method, called the double deep Q-learning network, exhibited the best performance in finding optimal antireflective multilayered structures with the highest double-band average transmission coefficient of about 98.95%.

Smart and Rapid Design of Nanophotonic Structures by an Adaptive and Regularized Deep Neural Network

The design of nanophotonic structures based on deep learning is emerging rapidly in the research community. Design methods using Deep Neural Networks (DNN) are outperforming conventional physics-based simulations performed iteratively by human experts. Here, a self-adaptive and regularized DNN based on Convolutional Neural Networks (CNNs) for the smart and fast characterization of nanophotonic structures in high-dimensional design parameter space is presented. This proposed CNN model, named LRS-RCNN, utilizes dynamic learning rate scheduling and L2 regularization techniques to overcome overfitting and speed up training convergence and is shown to surpass the performance of all previous algorithms, with the exception of two metrics where it achieves a comparable level relative to prior works. We applied the model to two challenging types of photonic structures: 2D photonic crystals (e.g., L3 nanocavity) and 1D photonic crystals (e.g., nanobeam) and results show that LRS-RCNN achieves record-high prediction accuracies, strong generalizibility, and substantially faster convergence speed compared to prior works. Although still a proof-of-concept model, the proposed smart LRS-RCNN has been proven to greatly accelerate the design of photonic crystal structures as a state-of-the-art predictor for both Q-factor and V. It can also be modified and generalized to predict any type of optical properties for designing a wide range of different nanophotonic structures. The complete dataset and code will be released to aid the development of related research endeavors.

Inverse deep learning methods and benchmarks for artificial electromagnetic material design

In this work we investigate the use of deep inverse models (DIMs) for designing artificial electromagnetic materials (AEMs) - such as metamaterials, photonic crystals, and plasmonics - to achieve some desired scattering properties (e.g., transmission or reflection spectrum). DIMs are deep neural networks (i.e., deep learning models) that are specially-designed to solve ill-posed inverse problems. There has recently been tremendous growth in the use of DIMs for solving AEM design problems however there has been little comparison of these approaches to examine their absolute and relative performance capabilities. In this work we compare eight state-of-the-art DIMs on three unique AEM design problems, including two models that are novel to the AEM community. Our results indicate that DIMs can rapidly produce accurate designs to achieve a custom desired scattering on all three problems. Although no single model always performs best, the Neural-Adjoint approach achieves the best overall performance across all problem settings. As a final contribution we show that not all AEM design problems are ill-posed, and in such cases a conventional deep neural network can perform better than DIMs. We recommend that a deep neural network is always employed as a simple baseline approach when addressing AEM design problems. We publish python code for our AEM simulators and our DIMs to enable easy replication of our results, and benchmarking of new DIMs by the AEM community.

A learning based approach for designing extended unit cell metagratings

The possibility of arbitrary spatial control of incident wavefronts with the subwavelength resolution has driven research into dielectric optical metasurfaces in the last decade. The unit-cell based metasurface design approach that relies on a library of single element responses is known to result in reduced efficiency attributed to the inadequate accounting of the coupling effects between meta-atoms. Metasurfaces with extended unit-cells containing multiple resonators can improve design outcomes but their design requires extensive numerical computing and optimizations. We report a deep learning based design methodology for the inverse design of extended unit-cell metagratings. In contrast to previous reports, our approach learns the metagrating spectral response across its reflected and transmitted orders. Through systematic exploration, we discover network architectures and training dataset sampling strategies that allow such learning without requiring extensive ground-truth generation. The one-time investment of model creation can then be used to significantly accelerate numerical optimization of multiple functionalities as demonstrated by considering the inverse design of various spectral and polarization dependent splitters and filters. The proposed methodology is not limited to these proof-of-concept demonstrations and can be broadly applied to meta-atom-based nanophotonic system design and in realising the next generation of metasurface functionalities with improved performance.

Computational Discovery of New 2D Materials Using Deep Learning Generative Models

Two-dimensional (2D) materials have emerged as promising functional materials with many applications such as semiconductors and photovoltaics because of their unique optoelectronic properties. Although several thousand 2D materials have been screened in existing materials databases, discovering new 2D materials remains challenging. Herein, we propose a deep learning generative model for composition generation combined with a random forest-based 2D materials classifier to discover new hypothetical 2D materials. Furthermore, a template-based element substitution structure prediction approach is developed to predict the crystal structures of a subset of the newly predicted hypothetical formulas, which allows us to confirm their structure stability using DFT calculations. So far, we have discovered 267 489 new potential 2D materials compositions, where 1485 probability scores are more then 0.95. Among them, we have predicted 101 crystal structures and confirmed 92 2D/layered materials by DFT formation energy calculation. Our results show that generative machine learning models provide an effective way to explore the vast chemical design space for new 2D materials discovery.

Machine learning-based leaky momentum prediction of plasmonic random nanosubstrate

In this work, we explore the use of machine learning for constructing the leakage radiation characteristics of the bright-field images of nanoislands from surface plasmon polariton based on the plasmonic random nanosubstrate. The leakage radiation refers to a leaky wave of surface plasmon polariton (SPP) modes through a dielectric substrate which has drawn interest due to its possibility of direct visualization and analysis of SPP propagation. A fast-learning two-layer neural network has been deployed to learn and predict the relationship between the leakage radiation characteristics and the bright-field images of nanoislands utilizing a limited number of training samples. The proposed learning framework is expected to significantly simplify the process of leaky radiation image construction without the need of sophisticated equipment. Moreover, a wide range of application extensions can be anticipated for the proposed image-to-image prediction.

Biomolecular interactions of ultrasmall metallic nanoparticles and nanoclusters

The use of nanoparticles (NPs) in biomedicine has made a gradual transition from proof-of-concept to clinical applications, with several NP types meeting regulatory approval or undergoing clinical trials. A new type of metallic nanostructures called ultrasmall nanoparticles (usNPs) and nanoclusters (NCs), while retaining essential properties of the larger (classical) NPs, have features common to bioactive proteins. This combination expands the potential use of usNPs and NCs to areas of diagnosis and therapy traditionally reserved for small-molecule medicine. Their distinctive physicochemical properties can lead to unique in vivo behaviors, including improved renal clearance and tumor distribution. Both the beneficial and potentially deleterious outcomes (cytotoxicity, inflammation) can, in principle, be controlled through a judicious choice of the nanocore shape and size, as well as the chemical ligands attached to the surface. At present, the ability to control the behavior of usNPs is limited, partly because advances are still needed in nanoengineering and chemical synthesis to manufacture and characterize ultrasmall nanostructures and partly because our understanding of their interactions in biological environments is incomplete. This review addresses the second limitation. We review experimental and computational methods currently available to understand molecular mechanisms, with particular attention to usNP-protein complexation, and highlight areas where further progress is needed. We discuss approaches that we find most promising to provide relevant molecular-level insight for designing usNPs with specific behaviors and pave the way to translational applications.

Deep-learning-enabled inverse engineering of multi-wavelength invisibility-to-superscattering switching with phase-change materials

Inverse design of nanoparticles for desired scattering spectra and dynamic switching between the two opposite scattering anomalies, i.e. superscattering and invisibility, is important in realizing cloaking, sensing and functional devices. However, traditionally the design process is quite complicated, which involves complex structures with many choices of synthetic constituents and dispersions. Here, we demonstrate that a well-trained deep-learning neural network can handle these issues efficiently, which can not only forwardly predict scattering spectra of multilayer nanoparticles with high precision, but also inversely design the required structural and material parameters efficiently. Moreover, we show that the neural network is capable of finding out multi-wavelength invisibility-to-superscattering switching points at the desired wavelengths in multilayer nanoparticles composed of metals and phase-change materials. Our work provides a useful solution of deep learning for inverse design of nanoparticles with dynamic scattering spectra by using phase-change materials.

Artificial neural networks for the inverse design of nanoparticles with preferential nano-bio behaviors

Safe and efficient use of ultrasmall nanoparticles (NPs) in biomedicine requires numerous independent conditions to be met, including colloidal stability, selectivity for proteins and membranes, binding specificity, and low affinity for plasma proteins. The ability of a NP to satisfy one or more of these requirements depends on its physicochemical characteristics, such as size, shape, and surface chemistry. Multiscale and pattern recognition techniques are here integrated to guide the design of NPs with preferential nano-bio behaviors. Data systematically collected from simulations (or experiments, if available) are first used to train one or more artificial neural networks, each optimized for a specific kind of nano-bio interaction; the trained networks are then interconnected in suitable arrays to obtain the NP core morphology and layer composition that best satisfy all the nano-bio interactions underlying more complex behaviors. This reverse engineering approach is illustrated in the case of NP-membrane interactions, using binding modes and affinities and early stage membrane penetrations as training data. Adaptations for designing NPs with preferential nano-protein interactions and for optimizing solution conditions in the test tube are discussed.

Artificial intelligence for photonics and photonic materials

Artificial intelligence (AI) is the most important new methodology in scientific research since the adoption of quantum mechanics and it is providing exciting results in numerous fields of science and technology. In this review we summarize research and discuss future opportunities for AI in the domains of photonics, nanophotonics, plasmonics and photonic materials discovery, including metamaterials.

Switchable multifunctional modulator realized by the stacked graphene-based hyperbolic metamaterial unit cells

A tunable multifunctional modulator of the stacked graphene-based hyperbolic metamaterial (HM) cells is proposed. The dielectric constant and group index of HM are theoretically investigated. The calculated results show that, for the cell structure, a transmission window in the reflection zone (TWRZ) can be obtained at the normal incidence, but all reflections are converted to the transmission when the incident angle is near 82°. Concurrently, a single frequency absorption in the transmission zone (SFATZ) is realized, which can be adjusted by the chemical potential of graphene. For the whole structure composed of cell structures with different chemical potentials, the ultra-wideband absorption and transmission window in the absorption zone (TWAZ) can be achieved, which can work in different frequency bands if the given structural parameters can be tailored. Those computed results can apply for switchable frequency-dependent and angle-dependent reflection-transmission modulations, single frequency and ultra-wideband absorbers, and a logic switch based on the TWAZ.

Tunable broadband terahertz absorber based on plasmon hybridization in monolayer graphene ring arrays

Graphene as a new two-dimensional material can be utilized to design tunable optical devices owing to its exceptional physical properties, such as high mobility and tunable conductivity. In this paper, we present the design and analysis of a tunable broadband terahertz absorber based on periodic graphene ring arrays. Due to plasmon hybridization modes excited in the graphene ring, the proposed structure achieves a broad absorption bandwidth with more than 90% absorption in the frequency range of 0.88-2.10 THz under normal incidence, and its relative absorption bandwidth is about 81.88%. Meanwhile, it exhibits polarization-insensitive behavior and maintains high absorption over 80% when the incident angle is up to 45° for both TE and TM polarizations. Additionally, the peak absorption rate of the absorber can be tuned from 21% to nearly 100% by increasing the graphene's chemical potential from 0 to 0.9 eV. Such a design can have some potential applications in various terahertz devices, such as modulators, detectors, and spatial filters.

Broadband absorption using all-graphene grating-coupled nanoparticles on a reflector

In this paper, the hybridized localized surface plasmon resonances (LSPRs) of a periodic assembly of graphene-wrapped nanoparticles are used to design a nanoparticle assisted optical absorber. Bandwidth enhancement of this structure via providing multiple types of plasmonic resonances in the associated unit cell using two densely packed crossly stacked graphene strips is proposed. The designed graphene strips support fundamental propagating surface plasmons on the ribbons, and gap plasmons in the cavity constructed by the adjacent sections. Graphene strips exhibit a hyperbolic dispersion region in the operating spectrum and assist in the bandwidth enhancement. Moreover, since the nanoparticles are deposited on the top strips, real-time biasing of them can be easily conducted by exciting the surface plasmons of the strip without the necessity to electrically connect the adjacent nanoparticles. The overall dynamic bandwidth of the structure, using a two-state biasing scheme, covers the frequencies of 18.16–40.47 THz with 90% efficiency. Due to the symmetry of the structure, the device performs similarly for both transverse electric (TE) and transverse magnetic (TM) waves and it has a high broadband absorption rate regarding different incident angles up to 40°. Due to the presence of 2D graphene material and also using hollow spherical particles, our proposed absorber is also lightweight and it is suitable for novel compact optoelectronic devices due to its sub-wavelength dimensions.

Machine learning and evolutionary algorithm studies of graphene metamaterials for optimized plasmon-induced transparency

Machine learning and optimization algorithms have been widely applied in the design and optimization for photonics devices. We briefly review recent progress of this field of research and show data-driven applications, including spectrum prediction, inverse design and performance optimization, for novel graphene metamaterials (GMs). The structure of the GMs is well-designed to achieve the wideband plasmon induced transparency (PIT) effect, which can be theoretically demonstrated by using the transfer matrix method. Some traditional machine learning algorithms, including k nearest neighbour, decision tree, random forest and artificial neural networks, are utilized to equivalently substitute the numerical simulation in the forward spectrum prediction and complete the inverse design for the GMs. The calculated results demonstrate that all algorithms are effective and the random forest has advantages in terms of accuracy and training speed. Moreover, evolutionary algorithms, including single-objective (genetic algorithm) and multi-objective optimization (NSGA-II), are used to achieve the steep transmission characteristics of PIT effect by synthetically taking many different performance metrics into consideration. The maximum difference between the transmission peaks and dips in the optimized transmission spectrum reaches 0.97. In comparison to previous works, we provide a guidance for intelligent design of photonics devices based on machine learning and evolutionary algorithms and a reference for the selection of machine learning algorithms for simple inverse design problems.

Prediction Network of Metamaterial with Split Ring Resonator Based on Deep Learning

The introduction of "metamaterials" has had a profound impact on several fields, including electromagnetics. Designing a metamaterial's structure on demand, however, is still an extremely time-consuming process. As an efficient machine learning method, deep learning has been widely used for data classification and regression in recent years and in fact shown good generalization performance. We have built a deep neural network for on-demand design. With the required reflectance as input, the parameters of the structure are automatically calculated and then output to achieve the purpose of designing on demand. Our network has achieved low mean square errors (MSE), with MSE of 0.005 on both the training and test sets. The results indicate that using deep learning to train the data, the trained model can more accurately guide the design of the structure, thereby speeding up the design process. Compared with the traditional design process, using deep learning to guide the design of metamaterials can achieve faster, more accurate, and more convenient purposes.

Deep learning: a new tool for photonic nanostructure design

Early results have shown the potential of Deep Learning (DL) to disrupt the fields of optical inverse-design, particularly, the inverse design of nanostructures. In the last three years, the complexity of the optical nanostructure being designed and the sophistication of the employed DL methodology have steadily increased. This topical review comprehensively surveys DL based design examples from the nanophotonics literature. Notwithstanding the early success of this approach, its limitations, range of validity and its place among established design techniques remain to be assessed. The review also provides a perspective on the limitations of this approach and emerging research directions. It is hoped that this topical review may help readers to identify unaddressed problems, to choose an initial setup for a specific problem, and, to identify means to improve the performance of existing DL based workflows.

Deep Learning Meets Nanophotonics: A Generalized Accurate Predictor for Near Fields and Far Fields of Arbitrary 3D Nanostructures

Deep artificial neural networks are powerful tools with many possible applications in nanophotonics. Here, we demonstrate how a deep neural network can be used as a fast, general purpose predictor of the full near-field and far-field response of plasmonic and dielectric nanostructures. A trained neural network is shown to infer the internal fields of arbitrary three-dimensional nanostructures many orders of magnitude faster compared to conventional numerical simulations. Secondary physical quantities are derived from the deep learning predictions and faithfully reproduce a wide variety of physical effects without requiring specific training. We discuss the strengths and limitations of the neural network approach using a number of model studies of single particles and their near-field interactions. Our approach paves the way for fast, yet universal, methods for design and analysis of nanophotonic systems.

A Bidirectional Deep Neural Network for Accurate Silicon Color Design

Silicon nanostructure color has achieved unprecedented high printing resolution and larger color gamut than sRGB. The exact color is determined by localized magnetic and electric dipole resonance of nanostructures, which are sensitive to their geometric changes. Usually, the design of specific colors and iterative optimization of geometric parameters are computationally costly, and obtaining millions of different structural colors is challenging. Here, a deep neural network is trained, which can accurately predict the color generated by random silicon nanostructures in the forward modeling process and solve the nonuniqueness problem in the inverse design process that can accurately output the device geometries for at least one million different colors. The key results suggest deep learning is a powerful tool to minimize the computation cost and maximize the design efficiency for nanophotonics, which can guide silicon color manufacturing with high accuracy.

Giant enhancement of tunable asymmetric transmission for circularly polarized waves in a double-layer graphene chiral metasurface

In this letter, we propose a structure based on double-layer graphene-based planar chiral metasurface with a J-shaped pattern to generate asymmetric transmission for circularly polarized waves in the mid-infrared region. Asymmetric transmission of the double-layer structure can reach to 16.64%, which is much larger than that of the monolayer. The mechanism of asymmetric transmission is attributed to enantiomerically sensitive graphene's surface plasmons. Besides, asymmetric transmission can be dynamically tuned by changing the Fermi energy and is affected by intrinsic relaxation time. All simulations are conducted by the finite element method. Our findings provide a feasibility of realizing photonic devices in tunable polarization-dependent operation, such as asymmetric wave splitters and circulators.