Deep Learning: A Rapid and Efficient Route to Automatic Metasurface Design

Physics-driven unsupervised deep learning network for programmable metasurface-based beamforming

Programmable metasurfaces have garnered significant attention for their capacity to dynamically manipulate electromagnetic (EM) waves. In particular, the programmable metasurfaces offer to generate a wide range of EM beams when the appropriate digital coding patterns are designed. Traditionally, optimizing the coding patterns involves time-consuming nonlinear optimization algorithms due to the high computational complexity. In this study, we propose a physics-assisted deep learning (DL) model that can calculate the coding pattern in milliseconds, requiring only a simple depiction of the desired beam. An extended version of the macroscopic model for digital coding metasurface is introduced as the physics-driven component, which can compute the radiation pattern rapidly based on the provided coding pattern. The integration of the macroscopic model ensures to generate the physics-compliant coding designs. We validate the proposed method experimentally by measuring several coding patterns for both single-beam and dual-beam scenarios, which demonstrate good performance of beamforming.

Harnessing the Missing Spectral Correlation for Metasurface Inverse Design

A long-held tenet in computer science asserts that the training of deep learning is analogous to an alchemical furnace, and its "black box" signature brings forth inexplicability. For electromagnetic metasurfaces, the related intelligent applications also get stuck into such a dilemma. Although the past 5 years have witnessed a proliferation of deep learning-based works across complex photonic scenarios, they neglect the already existing but untapped physical laws. Here, the intrinsic correlation between the real and imaginary parts of the spectra are revealed using Kramers-Kronig relations, which is then mimicked by bidirectional information flow in neural network space. Such consideration harnesses the missing spectral connection to extract crucial features effectively. The bidirectional recurrent neural network is benchmarked in metasurface inverse design and compare it with a fully-connected neural network, unidirectional recurrent neural network, and attention-based transformer. Beyond the improved accuracy, the study examines the intermediate information products and physically explains why different network structures yield different performances. The work offers explicable perspectives to utilize physical information in the deep learning field and facilitates many data-intensive research endeavors.

A surrogate-assisted extended generative adversarial network for parameter optimization in free-form metasurface design

Metasurfaces have widespread applications in fifth-generation (5G) microwave communication. Among the metasurface family, free-form metasurfaces excel in achieving intricate spectral responses compared to regular-shape counterparts. However, conventional numerical methods for free-form metasurfaces are time-consuming and demand specialized expertise. Alternatively, recent studies demonstrate that deep learning has great potential to accelerate and refine metasurface designs. Here, we present XGAN, an extended generative adversarial network (GAN) with a surrogate for high-quality free-form metasurface designs. The proposed surrogate provides a physical constraint to XGAN so that XGAN can accurately generate metasurfaces monolithically from input spectral responses. In comparative experiments involving 20000 free-form metasurface designs, XGAN achieves 0.9734 average accuracy and is 500 times faster than the conventional methodology. This method facilitates the metasurface library building for specific spectral responses and can be extended to various inverse design problems, including optical metamaterials, nanophotonic devices, and drug discovery.

Specific wavelength peak emulation with amorphous metastructures

The conventional design process for metasurfaces is time-consuming and computationally expensive. To address this challenge, we utilize a deep convolutional generative adversarial network (DCGAN) to generate new nanohole metastructure designs that match a desired transmittance spectrum in the visible range. The trained DCGAN model demonstrates an exceptional performance in generating diverse and manufacturable metastructure designs that closely resemble the target optical properties. The proposed method provides several advantages over existing approaches. These include its capability to generate new designs without prior knowledge or assumptions regarding the relationship between metastructure geometries and optical properties, its high efficiency, and its generalizability to other types of metamaterials. The successful fabrication and experimental characterization of the predicted metastructures further validate the accuracy and effectiveness of our proposed method.

A novel artificial intelligence network to assess the prognosis of gastrointestinal cancer to immunotherapy based on genetic mutation features

Background

Immune checkpoint inhibitors (ICIs) have revolutionized gastrointestinal cancer treatment, yet the absence of reliable biomarkers hampers precise patient response prediction.

Methods

We developed and validated a genomic mutation signature (GMS) employing a novel artificial intelligence network to forecast the prognosis of gastrointestinal cancer patients undergoing ICIs therapy. Subsequently, we explored the underlying immune landscapes across different subtypes using multiomics data. Finally, UMI-77 was pinpointed through the analysis of drug sensitization data from the Genomics of Drug Sensitivity in Cancer (GDSC) database. The sensitivity of UMI-77 to the AGS and MKN45 cell lines was evaluated using the cell counting kit-8 (CCK8) assay and the plate clone formation assay.

Results

Using the artificial intelligence network, we developed the GMS that independently predicts the prognosis of gastrointestinal cancer patients. The GMS demonstrated consistent performance across three public cohorts and exhibited high sensitivity and specificity for 6, 12, and 24-month overall survival (OS) in receiver operating characteristic (ROC) curve analysis. It outperformed conventional clinical and molecular features. Low-risk samples showed a higher presence of cytolytic immune cells and enhanced immunogenic potential compared to high-risk samples. Additionally, we identified the small molecule compound UMI-77. The half-maximal inhibitory concentration (IC50) of UMI-77 was inversely related to the GMS. Notably, the AGS cell line, classified as high-risk, displayed greater sensitivity to UMI-77, whereas the MKN45 cell line, classified as low-risk, showed less sensitivity.

Conclusion

The GMS developed here can reliably predict survival benefit for gastrointestinal cancer patients on ICIs therapy.

Vision-driven metasurfaces for perception enhancement

Metasurfaces have exhibited unprecedented degree of freedom in manipulating electromagnetic (EM) waves and thus provide fantastic front-end interfaces for smart systems. Here we show a framework for perception enhancement based on vision-driven metasurface. Human's eye movements are matched with microwave radiations to extend the humans' perception spectrum. By this means, our eyes can "sense" visual information and invisible microwave information. Several experimental demonstrations are given for specific implementations, including a physiological-signal-monitoring system, an "X-ray-glasses" system, a "glimpse-and-forget" tracking system and a speech reception system for deaf people. Both the simulation and experiment results verify evident advantages in perception enhancement effects and improving information acquisition efficiency. This framework can be readily integrated into healthcare systems to monitor physiological signals and to offer assistance for people with disabilities. This work provides an alternative framework for perception enhancement and may find wide applications in healthcare, wearable devices, search-and-rescue and others.

Data-Driven Design for Metamaterials and Multiscale Systems: A Review

Metamaterials are artificial materials designed to exhibit effective material parameters that go beyond those found in nature. Composed of unit cells with rich designability that are assembled into multiscale systems, they hold great promise for realizing next-generation devices with exceptional, often exotic, functionalities. However, the vast design space and intricate structure-property relationships pose significant challenges in their design. A compelling paradigm that could bring the full potential of metamaterials to fruition is emerging: data-driven design. This review provides a holistic overview of this rapidly evolving field, emphasizing the general methodology instead of specific domains and deployment contexts. Existing research is organized into data-driven modules, encompassing data acquisition, machine learning-based unit cell design, and data-driven multiscale optimization. The approaches are further categorized within each module based on shared principles, analyze and compare strengths and applicability, explore connections between different modules, and identify open research questions and opportunities.

Flexible Metasurfaces for Multifunctional Interfaces

Optical metasurfaces, capable of manipulating the properties of light with a thickness at the subwavelength scale, have been the subject of extensive investigation in recent decades. This research has been mainly driven by their potential to overcome the limitations of traditional, bulky optical devices. However, most existing optical metasurfaces are confined to planar and rigid designs, functions, and technologies, which greatly impede their evolution toward practical applications that often involve complex surfaces. The disconnect between two-dimensional (2D) planar structures and three-dimensional (3D) curved surfaces is becoming increasingly pronounced. In the past two decades, the emergence of flexible electronics has ushered in an emerging era for metasurfaces. This review delves into this cutting-edge field, with a focus on both flexible and conformal design and fabrication techniques. Initially, we reflect on the milestones and trajectories in modern research of optical metasurfaces, complemented by a brief overview of their theoretical underpinnings and primary classifications. We then showcase four advanced applications of optical metasurfaces, emphasizing their promising prospects and relevance in areas such as imaging, biosensing, cloaking, and multifunctionality. Subsequently, we explore three key trends in optical metasurfaces, including mechanically reconfigurable metasurfaces, digitally controlled metasurfaces, and conformal metasurfaces. Finally, we summarize our insights on the ongoing challenges and opportunities in this field.

Inverse design of metasurfaces with customized transmission characteristics of frequency band based on generative adversarial networks

In recent years, deep learning (DL) has demonstrated significant potential in the inverse design of metasurfaces, and the generation of metasurfaces with customized transmission characteristics of frequency band remains a challenging and underexplored area. In this study, we propose a DL-assisted method for the inverse design of transmissive metasurfaces. The method consists of a generative adversarial network (GAN)-based graph generator, an electromagnetic response predictor, and a genetic algorithm optimizer. By integrating these components, we can obtain customized metasurfaces with desired transmission characteristics of frequency band. We demonstrate the effectiveness of the proposed method through examples of inverse-designed three-layer cascaded transmissive metasurfaces with wideband, dual-band, and stopband responses in the 8∼12 GHz frequency range. Specifically, we realize three different types of dual-band metasurfaces, namely double-wide, front-wide and rear-narrow, and front-narrow and rear-wide configurations. Additionally, we analyze the accuracy and reliability of the inverse design method by employing data from the training dataset, self-defined objectives, and bandwidth-reduced target responses scaled from the wideband type as design inputs. Quantitative evaluation is performed using metrics such as mean absolute error and average precision. The proposed method successfully achieves the desired effect as intended.

Deep-Learning-Assisted Simultaneous Target Sensing and Super-Resolution Imaging

Metasurfaces have recently experienced revolutionary progress in sensing and super-resolution imaging fields, mainly due to their manipulation of electromagnetic waves on subwavelength scales. However, on the one hand, the addition of metasurfaces can multiply the complexity of retrieving target information from detected electromagnetic fields. On the other hand, many existing studies utilize deep learning methods to provide compelling tools for electromagnetic problems but mainly concentrate on resolving one single function, limiting their versatilities. In this work, a multifunctional deep learning network is demonstrated to reconstruct diverse target information in a metasurface-target interactive system. First, a preliminary experiment verifies that the metasurface-involved scenario can tolerate the system noises. Then, the captured electric field distributions are fed into the multifunctional network, which can not only accurately sense the quantity and relative permittivity of targets but also generate super-resolution images precisely. The deep learning network, thus, paves an alternative way to recover the targets' information in metasurface-target interactive systems, accelerating the progression of target sensing and superimaging areas. Besides, another new network that allows forward electromagnetic prediction is also proposed and demonstrated. To sum up, the deep learning methodology may hold promise for inverse reconstructions or forward predictions in many electromagnetic scenarios.

Diverse ranking metamaterial inverse design based on contrastive and transfer learning

Metamaterials, thoughtfully designed, have demonstrated remarkable success in the manipulation of electromagnetic waves. More recently, deep learning can advance the performance in the field of metamaterial inverse design. However, existing inverse design methods based on deep learning often overlook potential trade-offs of optimal design and outcome diversity. To address this issue, in this work we introduce contrastive learning to implement a simple but effective global ranking inverse design framework. Viewing inverse design as spectrum-guided ranking of the candidate structures, our method creates a resemblance relationship of the optical response and metamaterials, enabling the prediction of diverse structures of metamaterials based on the global ranking. Furthermore, we have combined transfer learning to enrich our framework, not limited in prediction of single metamaterial representation. Our work can offer inverse design evaluation and diverse outcomes. The proposed method may shrink the gap between flexibility and accuracy of on-demand design.

Correlating metasurface spectra with a generation-elimination framework

Inferring optical response from other correlated optical response is highly demanded for vast applications such as biological imaging, material analysis, and optical characterization. This is distinguished from widely-studied forward and inverse designs, as it is boiled down to another different category, namely, spectra-to-spectra design. Whereas forward and inverse designs have been substantially explored across various physical scenarios, the spectra-to-spectra design remains elusive and challenging as it involves intractable many-to-many correspondences. Here, we first dabble in this uncharted area and propose a generation-elimination framework that can self-orient to the best output candidate. Such a framework has a strong built-in stochastically sampling capability that automatically generate diverse nominations and eliminate inferior nominations. As an example, we study terahertz metasurfaces to correlate the reflection spectra from low to high frequencies, where the inaccessible spectra are precisely forecasted without consulting structural information, reaching an accuracy of 98.77%. Moreover, an innovative dimensionality reduction approach is executed to visualize the distribution of the abstract correlated spectra data encoded in latent spaces. These results provide explicable perspectives for deep learning to parse complex physical processes, rather than "brute-force" black box, and facilitate versatile applications involving cross-wavelength information correlation.

Deep learning-based inverse design optimization of efficient multilayer thermal emitters in the near-infrared broad spectrum

This study proposes a deep learning architecture for automatic modeling and optimization of multilayer thin film structures to address the need for specific spectral emitters and achieve rapid design of geometric parameters for an ideal spectral response. Multilayer film structures are ideal thermal emitter structures for thermophotovoltaic application systems because they combine the advantages of large area preparation and controllable costs. However, achieving good spectral response performance requires stacking more layers, which makes it more difficult to achieve fine spectral inverse design using forward calculation of the dimensional parameters of each layer of the structure. Deep learning is the main method for solving complex data-driven problems in artificial intelligence and provides an efficient solution for the inverse design of structural parameters for a target waveband. In this study, an eight-layer thin film structure composed of SiO₂/Ti and SiO₂/W is rapidly reverse engineered using a deep learning method to achieve a structural design with an emissivity better than 0.8 in the near-infrared band. Additionally, an eight-layer thin film structure composed of 3 × 3 cm SiO₂/Ti is experimentally measured using magnetron sputtering, and the emissivity in the 1-4 µm band was better than 0.68. This research provides implications for the design and application of micro-nano structures, can be widely used in the fields of thermal imaging and thermal regulation, and will contribute to developing a new paradigm for optical nanophotonic structures with a fast target-oriented inverse design of structural parameters, such as required spectral emissivity, phase, and polarization.

Exploring the limits of metasurface polarization multiplexing capability based on deep learning

Metasurfaces provide a new approach for planar optics and thus have realized multifunctional meta-devices with different multiplexing strategies, among which polarization multiplexing has received much attention due to its convenience. At present, a variety of design methods of polarization multiplexed metasurfaces have been developed based on different meta-atoms. However, as the number of polarization states increases, the response space of meta-atoms becomes more and more complex, and it is difficult for these methods to explore the limit of polarization multiplexing. Deep learning is one of the important routes to solve this problem because it can realize the effective exploration of huge data space. In this work, a design scheme for polarization multiplexed metasurfaces based on deep learning is proposed. The scheme uses a conditional variational autoencoder as an inverse network to generate structural designs and combines a forward network that can predict meta-atoms' responses to improve the accuracy of designs. The cross-shaped structure is used to establish a complicated response space containing different polarization state combinations of incident and outgoing light. The multiplexing effects of the combinations with different numbers of polarization states are tested by utilizing the proposed scheme to design nanoprinting and holographic images. The polarization multiplexing capability limit of four channels (a nanoprinting image and three holographic images) is determined. The proposed scheme lays the foundation for exploring the limits of metasurface polarization multiplexing capability.

Rapid deep-learning-assisted design method for 2-bit coding metasurfaces

This paper proposes a deep-learning-assisted design method for 2-bit coding metasurfaces. This method uses a skip connection module and the idea of an attention mechanism in squeeze-and-excitation networks based on a fully connected network and a convolutional neural network. The accuracy limit of the basic model is further improved. The convergence ability of the model increased nearly 10 times, and the mean-square error loss function converges to 0.000168. The forward prediction accuracy of the deep-learning-assisted model is 98%, and the accuracy of inverse design results is 97%. This approach offers the advantages of an automatic design process, high efficiency, and low computational cost. It can serve users who lack metasurface design experience.

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.

Deep-learning based broadband reflection reduction metasurface

Reflection reduction metasurface (RRM) has been drawing much attention due to its potential application in stealth technology. However, the traditional RRM is designed mainly based on trial-and-error approaches, which is time-consuming and leads to inefficiency. Here, we report the design of a broadband RRM based on deep-learning methodology. On one hand, we construct a forward prediction network that can forecast the polarization conversion ratio (PCR) of the metasurface in a millisecond, demonstrating a higher efficiency than traditional simulation tools. On the other hand, we construct an inverse network to immediately derive the structure parameters once a target PCR spectrum is given. Thus, an intelligent design methodology of broadband polarization converters has been established. When the polarization conversion units are arranged in chessboard layout with 0/1 form, a broadband RRM is achieved. The experimental results show that the relative bandwidth reaches 116% (reflection<-10 dB) and 107.4% (reflection<-15 dB), which demonstrates a great advantage in bandwidth compared with the previous designs.

Chiral Metasurface for Near-Field Imaging and Far-Field Holography Based on Deep Learning

Chiral metasurfaces have great influence on the development of holography. Nonetheless, it is still challenging to design chiral metasurface structures on demand. As a machine learning method, deep learning has been applied to design metasurface in recent years. This work uses a deep neural network with a mean absolute error (MAE) of 0.03 to inverse design chiral metasurface. With the help of this approach, a chiral metasurface with circular dichroism (CD) values higher than 0.4 is designed. The static chirality of the metasurface and the hologram with an image distance of 3000 μm are characterized. The imaging results are clearly visible and demonstrate the feasibility of our inverse design approach.

Metasurface design with a complex residual neural network

In recent years, researchers have made great progress in solving complex electromagnetic field computing problems by using deep learning methods. However, the approaches found in literature were devoted to solving the real-number problem of electromagnetic field calculations. For the complex number problem, there was no good solution. Here, we proposed an advanced computation method for metasurfaces based on a complex residual neural network (CRNN). We predicted the scattering (S)₂₁ parameters of a cylindrical structure in the range of 1.2 to 1.7 µm wavelengths. By providing a set of cylindrical structure parameters, we could quickly predict the S ₂₁ parameters with CRNN and design a metalens, which proved the ability of the proposed method. In addition, our method can also be extended to the calculation of electromagnetic fields where the speed of the calculation of the complex number of metasurfaces should be accelerated.

Developing a carpet cloak operating for a wide range of incident angles using a deep neural network and PSO algorithm

Designing invisibility cloaks has always been one of the most fascinating fields of research; in this regard, metasurface-based carpet cloaks have drawn researchers' attention due to their inherent tenuousness, resulting in a lower loss and easier fabrication. However, their performances are dependent on the incident angle of the coming wave; as a result, designing a carpet cloak capable of rendering objects under it invisible for a wide range of angles requires advanced methods. In this paper, using the Particle Swarm Optimization (PSO) algorithm, along with a trained neural network, a metasurface-based carpet cloak is developed capable to operate for a wide range of incident angles. The deep neural network is trained and used in order to accelerate the process of calculation of reflection phases provided by different unit cell designs. The resultant carpet cloak is numerically analyzed, and its response is presented and discussed. Both near-field and far-field results show that the designed carpet cloak operates very well for all incident angles in the range of 0 to 65 degrees.

Long-term spatial variation of algal blooms extracted using the U-net model from 10 years of GOCI imagery in the East China Sea

Long-term satellite missions could help to provide insights into spatial and temporal variations in algal blooms. However, the traditional reflectance-based method has limitations in regards to determining the available threshold for algal bloom detection among the time-varying observation conditions. In terms of extracting useful information from long-term data series precisely and efficiently, the deep learning method has shown its superiority over traditional algorithms in batch data processing. In this study, a U-net model for algal bloom extraction along the coast of the East China Sea was developed using GOCI images. The U-net model was trained with two different datasets that were constructed with six-band channels (all visible bands from GOCI imagery) and RGB-band channels (bands of 443, 555, and 680 nm from GOCI imagery). The quantitative assessment from the U-net models suggests that the U-net model trained with the six-band channel datasets outperformed the RGB-band channel datasets, with increases of 23.6%, 18.1%, and 12.5% in terms of accuracy, precision, and F-score, respectively. The validation map derived from the U-net model trained with six-band channel datasets also showed considerable matching with the ground-truth maps. By using the U-net model, the occurrence of algal blooms was automatically extracted from GOCI images. A 10-year time series of GOCI data collected between 2011 and 2020 was derived using an output-trained U-net model to explore spatial variation along the coast of the ECS. It was found that the most affected areas of the algal blooms varied by year, but were mainly located in the Zhoushan and Zhejiang coasts. Additionally, by performing principal component analysis on the daily meteorological data during April and August 2011-2020, factors related to algal bloom occurrence were discussed.

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.

The accelerated design of the nanoantenna arrays by deep learning

Nanoantenna fusion photonics and nanotechnology can manipulate light through the ultra-thin structure composed of sub-wavelength antennas, and meet the important requirements for miniaturized optical components, completely changing the field of optics. However, the device design process is still time-consuming and consumes computing resources. Besides, the professional knowledge requirements of engineers are also high. Relying on the algorithm's inference ability and excellent computing ability, artificial intelligence has great potential in the fields of material design, material screening, and device performance prediction. However, the deep learning (DL) requires a mass of data. Therefore, this article proposes a method for the forward and inverse design of nanoantenna based on DL. Compared with the previous work, the network uses a two-dimensional matrix as input, which has a simple structure and is more suitable for the advantages of deep netural network. Simultaneously, the small datasets can be used to achieve higher accuracy. In the forward prediction, 100% of the data error is less than 0.007; in the inverse prediction, the data with error less than 0.05 accounted for 90%, 99.8% and 100% of the length, height, and width's datasets. It demonstrates that the method can improve the automation of the design process and reduce the consumption of computer resources.

Light-driven single-cell rotational adhesion frequency assay

The interaction between cell surface receptors and extracellular ligands is highly related to many physiological processes in living systems. Many techniques have been developed to measure the ligand-receptor binding kinetics at the single-cell level. However, few techniques can measure the physiologically relevant shear binding affinity over a single cell in the clinical environment. Here, we develop a new optical technique, termed single-cell rotational adhesion frequency assay (scRAFA), that mimics in vivo cell adhesion to achieve label-free determination of both homogeneous and heterogeneous binding kinetics of targeted cells at the subcellular level. Moreover, the scRAFA is also applicable to analyze the binding affinities on a single cell in native human biofluids. With its superior performance and general applicability, scRAFA is expected to find applications in study of the spatial organization of cell surface receptors and diagnosis of infectious diseases.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1186/s43593-022-00020-4.

Low-Loss Dual-Band Transparency Metamaterial with Toroidal Dipole

In this paper, a low-loss toroidal dipole metamaterial composed of four metal split ring resonators is proposed and verified at microwave range. Dual-band Fano resonances could be excited by normal incident electromagnetic waves at 6 GHz and 7.23 GHz. Analysis of the current distribution at the resonance frequency and the scattered power of multipoles shows that both Fano resonances derive from the predominant novel toroidal dipole. The simulation results exhibit that the sensitivity to refractive index of the analyte is 1.56 GHz/RIU and 1.8 GHz/RIU. Meanwhile, the group delay at two Fano peaks can reach to 11.38 ns and 12.85 ns, which means the presented toroidal metamaterial has significant slow light effects. The proposed dual-band toroidal dipole metamaterial may offer a new path for designing ultra-sensitive sensors, filters, modulators, slow light devices, and so on.

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.

An Inverse Design Framework for Isotropic Metasurfaces Based on Representation Learning

A hybrid framework for solving the non-uniqueness problem in the inverse design of isomorphic metasurfaces is proposed. The framework consists of a representation learning (RL) module and a variational autoencoder-particle swarm optimization (VAE-PSO) algorithm module. The RL module is used to reduce the complex high-dimensional space into a low-dimensional space with obvious features, with the purpose of eliminating the many-to-one relationship between the original design space and response space. The VAE-PSO algorithm first encodes all meta-atoms into a continuous latent space through VAE and then applies PSO to search for an optimized latent vector whose corresponding metasurface fulfills the target response. This framework gives the solution paradigm of the ideal non-uniqueness situation, simplifies the complexity of the network, improves the running speed of the PSO algorithm, and obtains the global optimal solution with 94% accuracy on the test set.

Industry 4.0 and Digitalisation in Healthcare

Industry 4.0 in healthcare involves use of a wide range of modern technologies including digitisation, artificial intelligence, user response data (ergonomics), human psychology, the Internet of Things, machine learning, big data mining, and augmented reality to name a few. The healthcare industry is undergoing a paradigm shift thanks to Industry 4.0, which provides better user comfort through proactive intervention in early detection and treatment of various diseases. The sector is now ready to make its next move towards Industry 5.0, but certain aspects that motivated this review paper need further consideration. As a fruitful outcome of this review, we surveyed modern trends in this arena of research and summarised the intricacies of new features to guide and prepare the sector for an Industry 5.0-ready healthcare system.

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.

Metamaterial Reverse Multiple Prediction Method Based on Deep Learning

Metamaterials and their related research have had a profound impact on many fields, including optics, but designing metamaterial structures on demand is still a challenging task. In recent years, deep learning has been widely used to guide the design of metamaterials, and has achieved outstanding performance. In this work, a metamaterial structure reverse multiple prediction method based on semisupervised learning was proposed, named the partially Conditional Generative Adversarial Network (pCGAN). It could reversely predict multiple sets of metamaterial structures that can meet the needs by inputting the required target spectrum. This model could reach a mean average error (MAE) of 0.03 and showed good generality. Compared with the previous metamaterial design methods, this method could realize reverse design and multiple design at the same time, which opens up a new method for the design of new metamaterials.

A deep learning approach to automate whole-genome prediction of diverse epigenomic modifications in plants

Epigenetic modifications function in gene transcription, RNA metabolism, and other biological processes. However, multiple factors currently limit the scientific utility of epigenomic datasets generated for plants. Here, using deep-learning approaches, we developed a Smart Model for Epigenetics in Plants (SMEP) to predict six types of epigenomic modifications: DNA 5-methylcytosine (5mC) and N6-methyladenosine (6mA) methylation, RNA N6-methyladenosine (m⁶ A) methylation, and three types of histone modification. Using the datasets from the japonica rice Nipponbare, SMEP achieved 95% prediction accuracy for 6mA, and also achieved around 80% for 5mC, m⁶ A, and the three types of histone modification based on the 10-fold cross-validation. Additionally, > 95% of the 6mA peaks detected after a heat-shock treatment were predicted. We also successfully applied the SMEP for examining epigenomic modifications in indica rice 93-11 and even the B73 maize line. Taken together, we show that the deep-learning-enabled SMEP can reliably mine epigenomic datasets from diverse plants to yield actionable insights about epigenomic sites. Thus, our work opens new avenues for the application of predictive tools to facilitate functional research, and will almost certainly increase the efficiency of genome engineering efforts.

Temperature-dependent circular conversion dichroism from chiral metasurfaces patterned in Dirac semimetal Cd3As2

Chiral metasurfaces patterned with L-shaped holes in a thin film of Dirac semimetal Cd3As2 are designed. The impact of temperature T on circular conversion dichroism, mainly characterized by circular polarization differential transmittance (CPDT), is studied by rigorous coupled-wave analysis. The results show that decreasing T will give rise to the appearance of much more narrow CPDT peaks and dips, and the maximum differential transmittance between two opposite circularly polarized light can reach above 0.60 by optimizing the structural parameters at 80 K. As the T increases, the differential transmittance gradually decreases, and the CPDT peak and dip values exhibit variation tendencies of 'Z' and 'S' types, respectively. Two simple formulae of CPDT extreme values with respect to T are derived, predicting that the decreasing tendency will reach saturation when T ≥ 500 K. Differing from the wavelength-independent variation trend of differential transmittance, CPDT extremum positions mainly show a blueshift (redshift) tendency at the wavelength λ > 10 μm (λ < 5 μm) as the T increases. Moreover, evolutions of CPDT with various factors including the thickness of Cd3As2, incident and azimuth angles are also clearly unveiled.

Comparison of multi-criteria and artificial intelligence models for land-subsidence susceptibility zonation

Land subsidence (LS) in arid and semi-arid areas, such as Iran, is a significant threat to sustainable land management. The purpose of this study is to predict the LS distribution by generating land subsidence susceptibility models (LSSMs) for the Shahroud plain in Iran using three different multi-criteria decision making (MCDM) and five different artificial intelligence (AI) models. The MCDM models we used are the VlseKriterijumska Optimizacija IKompromisno Resenje (VIKOR), Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) and Complex Proportional Assessment (COPRAS), and the AI models are the extreme gradient boosting (XGBoost), Cubist, Elasticnet, Bayesian multivariate adaptive regression spline (BMARS) and conditional random forest (Cforest) methods. We used the Receiver Operating Characteristic (ROC) curve, Area Under Curve (AUC) and different statistical indices,i.e. accuracy, sensitivity, specificity, F score, Kappa, Mean Absolute Error (MAE) and Nash-Sutcliffe Criteria (NSC)to validate and evaluate the methods. Based on the different validation techniques, the Cforest method yielded the best results with minimum and maximum values of 0.04 and 0.99, respectively. According to the Cforest model, 30.55% of the study area is extremely vulnerable to land subsidence. The results of our research will be of great help to planners and policy makers in the identification of the most vulnerable regions and the implementation of appropriate development strategies in this area.

Radiation Pattern Prediction for Metasurfaces: A Neural Network-Based Approach

As the current standardization for the 5G networks nears completion, work towards understanding the potential technologies for the 6G wireless networks is already underway. One of these potential technologies for the 6G networks is reconfigurable intelligent surfaces. They offer unprecedented degrees of freedom towards engineering the wireless channel, i.e., the ability to modify the characteristics of the channel whenever and however required. Nevertheless, such properties demand that the response of the associated metasurface is well understood under all possible operational conditions. While an understanding of the radiation pattern characteristics can be obtained through either analytical models or full-wave simulations, they suffer from inaccuracy and extremely high computational complexity, respectively. Hence, in this paper, we propose a neural network-based approach that enables a fast and accurate characterization of the metasurface response. We analyze multiple scenarios and demonstrate the capabilities and utility of the proposed methodology. Concretely, we show that this method can learn and predict the parameters governing the reflected wave radiation pattern with an accuracy of a full-wave simulation (98.8–99.8%) and the time and computational complexity of an analytical model. The aforementioned result and methodology will be of specific importance for the design, fault tolerance, and maintenance of the thousands of reconfigurable intelligent surfaces that will be deployed in the 6G network environment.

Thermodynamic stability, structural and electronic properties for the C20-nAln heterofullerenes (n = 1-5): a DFT study

DFT calculations are utilized to compare and contrast the substituted aluminum-heterofullerenes, C_20-nAl_n (with n = 1-5) from thermodynamically view point, at density functional theory (DFT). Vibrational frequency analysis confirms that apart from C₁₅Al₅, all studied species are true minima. Considering the optimized geometries shows that all heterofullerenes are isolated-pentagon cage and none collapse to open deformed as segregated structure. The highest binding energy (5.56 eV/atom) and absolute heat of atomization (3323.68 kcal mol^-1) reveals open-shell C₁₉Al₁ as the most stable thermodynamic heterofullerene. The most NICS (0) (isotropic and anisotropic parameters, -49.58 and - 46.47 ppm, respectively) introduces closed-shell C₁₈Al_2-2 as the most aromatic structure. Also, closed-shell C₁₆Al_4-1 heterofullerene emerges with the most polarizability (307.71 a.u.) and hence activity to interact with the surrounding polar species. The lowest and the highest charge transfer on the surfaces of C₂₀ and C₁₆Al_4-2 without weak Al-Al bond, as the worst and the best candidate, respectively, provokes further investigation on impossible and possible application for hydrogen storage, respectively. We wish that the present survey will stimulate new experiments.

Vision-Based Pavement Marking Detection and Condition Assessment—A Case Study

Pavement markings constitute an effective way of conveying regulations and guidance to drivers. They constitute the most fundamental way to communicate with road users, thus, greatly contributing to ensuring safety and order on roads. However, due to the increasingly extensive traffic demand, pavement markings are subject to a series of deterioration issues (e.g., wear and tear). Markings in poor condition typically manifest as being blurred or even missing in certain places. The need for proper maintenance strategies on roadway markings, such as repainting, can only be determined based on a comprehensive understanding of their as-is worn condition. Given the fact that an efficient, automated and accurate approach to collect such condition information is lacking in practice, this study proposes a vision-based framework for pavement marking detection and condition assessment. A hybrid feature detector and a threshold-based method were used for line marking identification and classification. For each identified line marking, its worn/blurred severity level was then quantified in terms of worn percentage at a pixel level. The damage estimation results were compared to manual measurements for evaluation, indicating that the proposed method is capable of providing indicative knowledge about the as-is condition of pavement markings. This paper demonstrates the promising potential of computer vision in the infrastructure sector, in terms of implementing a wider range of managerial operations for roadway management.

Deep neural network-based automatic metasurface design with a wide frequency range

Beyond the scope of conventional metasurface, which necessitates plenty of computational resources and time, an inverse design approach using machine learning algorithms promises an effective way for metasurface design. In this paper, benefiting from Deep Neural Network (DNN), an inverse design procedure of a metasurface in an ultra-wide working frequency band is presented in which the output unit cell structure can be directly computed by a specified design target. To reach the highest working frequency for training the DNN, we consider 8 ring-shaped patterns to generate resonant notches at a wide range of working frequencies from 4 to 45 GHz. We propose two network architectures. In one architecture, we restrict the output of the DNN, so the network can only generate the metasurface structure from the input of 8 ring-shaped patterns. This approach drastically reduces the computational time, while keeping the network’s accuracy above 91%. We show that our model based on DNN can satisfactorily generate the output metasurface structure with an average accuracy of over 90% in both network architectures. Determination of the metasurface structure directly without time-consuming optimization procedures, an ultra-wide working frequency, and high average accuracy equip an inspiring platform for engineering projects without the need for complex electromagnetic theory.

Suggesting a Stochastic Fractal Search Paradigm in Combination with Artificial Neural Network for Early Prediction of Cooling Load in Residential Buildings

Early prediction of thermal loads plays an essential role in analyzing energy-efficient buildings’ energy performance. On the other hand, stochastic algorithms have recently shown high proficiency in dealing with this issue. These are the reasons that this study is dedicated to evaluating an innovative hybrid method for predicting the cooling load (CL) in buildings with residential usage. The proposed model is a combination of artificial neural networks and stochastic fractal search (SFS–ANNs). Two benchmark algorithms, namely the grasshopper optimization algorithm (GOA) and firefly algorithm (FA) are also considered to be compared with the SFS. The non-linear effect of eight independent factors on the CL is analyzed using each model’s optimal structure. Evaluation of the results outlined that all three metaheuristic algorithms (with more than 90% correlation) can adequately optimize the ANN. In this regard, this tool’s prediction error declined by nearly 23%, 18%, and 36% by applying the GOA, FA, and SFS techniques. Moreover, all used accuracy criteria indicated the superiority of the SFS over the benchmark schemes. Therefore, it is inferred that utilizing the SFS along with ANN provides a reliable hybrid model for the early prediction of CL.

Synthesizing Multi-Layer Perceptron Network with Ant Lion Biogeography-Based Dragonfly Algorithm Evolutionary Strategy Invasive Weed and League Champion Optimization Hybrid Algorithms in Predicting Heating Load in Residential Buildings

The significance of accurate heating load (HL) approximation is the primary motivation of this research to distinguish the most efficient predictive model among several neural-metaheuristic models. The proposed models are formulated through synthesizing a multi-layer perceptron network (MLP) with ant lion optimization (ALO), biogeography-based optimization (BBO), the dragonfly algorithm (DA), evolutionary strategy (ES), invasive weed optimization (IWO), and league champion optimization (LCA) hybrid algorithms. Each ensemble is optimized in terms of the operating population. Accordingly, the ALO-MLP, BBO-MLP, DA-MLP, ES-MLP, IWO-MLP, and LCA-MLP presented their best performance for population sizes of 350, 400, 200, 500, 50, and 300, respectively. The comparison was carried out by implementing a ranking system. Based on the obtained overall scores (OSs), the BBO (OS = 36) featured as the most capable optimization technique, followed by ALO (OS = 27) and ES (OS = 20). Due to the efficient performance of these algorithms, the corresponding MLPs can be promising substitutes for traditional methods used for HL analysis.

Double-Target Based Neural Networks in Predicting Energy Consumption in Residential Buildings

A reliable prediction of sustainable energy consumption is key for designing environmentally friendly buildings. In this study, three novel hybrid intelligent methods, namely the grasshopper optimization algorithm (GOA), wind-driven optimization (WDO), and biogeography-based optimization (BBO), are employed to optimize the multitarget prediction of heating loads (HLs) and cooling loads (CLs) in the heating, ventilation and air conditioning (HVAC) systems. Concerning the optimization of the applied algorithms, a series of swarm-based iterations are performed, and the best structure is proposed for each model. The GOA, WDO, and BBO algorithms are mixed with a class of feedforward artificial neural networks (ANNs), which is called a multi-layer perceptron (MLP) to predict the HL and CL. According to the sensitivity analysis, the WDO with swarm size = 500 proposes the most-fitted ANN. The proposed WDO-ANN provided an accurate prediction in terms of heating load (training (R2 correlation = 0.977 and RMSE error = 0.183) and testing (R2 correlation = 0.973 and RMSE error = 0.190)) and yielded the best-fitted prediction in terms of cooling load (training (R2 correlation = 0.99 and RMSE error = 0.147) and testing (R2 correlation = 0.99 and RMSE error = 0.148)).

An Innovative Metaheuristic Strategy for Solar Energy Management through a Neural Networks Framework

Proper management of solar energy as an effective renewable source is of high importance toward sustainable energy harvesting. This paper offers a novel sophisticated method for predicting solar irradiance (SIr) from environmental conditions. To this end, an efficient metaheuristic technique, namely electromagnetic field optimization (EFO), is employed for optimizing a neural network. This algorithm quickly mines a publicly available dataset for nonlinearly tuning the network parameters. To suggest an optimal configuration, five influential parameters of the EFO are optimized by an extensive trial and error practice. Analyzing the results showed that the proposed model can learn the SIr pattern and predict it for unseen conditions with high accuracy. Furthermore, it provided about 10% and 16% higher accuracy compared to two benchmark optimizers, namely shuffled complex evolution and shuffled frog leaping algorithm. Hence, the EFO-supervised neural network can be a promising tool for the early prediction of SIr in practice. The findings of this research may shed light on the use of advanced intelligent models for efficient energy development.

Electrical Power Prediction through a Combination of Multilayer Perceptron with Water Cycle Ant Lion and Satin Bowerbird Searching Optimizers

Predicting the electrical power (PE) output is a significant step toward the sustainable development of combined cycle power plants. Due to the effect of several parameters on the simulation of PE, utilizing a robust method is of high importance. Hence, in this study, a potent metaheuristic strategy, namely, the water cycle algorithm (WCA), is employed to solve this issue. First, a nonlinear neural network framework is formed to link the PE with influential parameters. Then, the network is optimized by the WCA algorithm. A publicly available dataset is used to feed the hybrid model. Since the WCA is a population-based technique, its sensitivity to the population size is assessed by a trial-and-error effort to attain the most suitable configuration. The results in the training phase showed that the proposed WCA can find an optimal solution for capturing the relationship between the PE and influential factors with less than 1% error. Likewise, examining the test results revealed that this model can forecast the PE with high accuracy. Moreover, a comparison with two powerful benchmark techniques, namely, ant lion optimization and a satin bowerbird optimizer, pointed to the WCA as a more accurate technique for the sustainable design of the intended system. Lastly, two potential predictive formulas, based on the most efficient WCAs, are extracted and presented.

Genetic Algorithms to Automate the Design of Metasurfaces for Absorption Bandwidth Broadening

In this paper, we present a method to automate the design of an efficient metasurface, which widens the bandwidth of the substrate. This strategy maximizes the potential of the substrate for the application of broad-band absorption. The design is achieved by utilizing the coding metasurface and a combination of two types of intelligent algorithms. First, inspired by the coding metasurface, a large number of structures are generated to act as potential metasurface unit patterns by randomly generating the associated binary codes. Then, the binary codes are directly substituted as optimization objects into a genetic algorithm to find the optimal metasurface. Finally, a neural network is introduced to replace the finite element analysis method to correlate the binary codes with the absorbing bandwidth. With the participation of neural networks, the genetic algorithm can find the optimal solution in a considerably short time. This method bypassed the prerequisite physical knowledge required in the process of metasurface design, which can be used for reference in other applications of the metasurface.

Credal decision tree based novel ensemble models for spatial assessment of gully erosion and sustainable management

We introduce novel hybrid ensemble models in gully erosion susceptibility mapping (GESM) through a case study in the Bastam sedimentary plain of Northern Iran. Four new ensemble models including credal decision tree-bagging (CDT-BA), credal decision tree-dagging (CDT-DA), credal decision tree-rotation forest (CDT-RF), and credal decision tree-alternative decision tree (CDT-ADTree) are employed for mapping the gully erosion susceptibility (GES) with the help of 14 predictor factors and 293 gully locations. The relative significance of GECFs in modelling GES is assessed by random forest algorithm. Two cut-off-independent (area under success rate curve and area under predictor rate curve) and six cut-off-dependent metrics (accuracy, sensitivity, specificity, F-score, odd ratio and Cohen Kappa) were utilized based on both calibration as well as testing dataset. Drainage density, distance to road, rainfall and NDVI were found to be the most influencing predictor variables for GESM. The CDT-RF (AUSRC = 0.942, AUPRC = 0.945, accuracy = 0.869, specificity = 0.875, sensitivity = 0.864, RMSE = 0.488, F-score = 0.869 and Cohen's Kappa = 0.305) was found to be the most robust model which showcased outstanding predictive accuracy in mapping GES. Our study shows that the GESM can be utilized for conserving soil resources and for controlling future gully erosion.

Carbon and germanium nanocages as anode electrodes in sodium-ion and potassium-ion batteries

Here, the potential of C₃₆, C₄₈, and Ge₄₈ nanocages as anodes of Na-ion battery (IB) and K-IB are investigated by DFT/M06-2X and DFT/B3LYP in gas and solvent. The E_Formation and E_Gap of C₃₆, C₄₈, and Ge₄₈ nanocages are investigated by theoretical methods. The vertical and adiabatic EA and IP of C₃₆, C₄₈, and Ge₄₈ nanocages are examined in gas and solvent. The E_ad of Na⁺ and K⁺ on inner and outer positions of C₃₆, C₄₈, and Ge₄₈ nanocages are investigated. The V_cell and C_Theory of C₃₆, C₄₈, and Ge₄₈ as anodes of batteries are investigated. The results of this paper proposed the nano materials (C₄₈ and Ge₄₈ nanocage) as anodes of Na-IB and K-IB with higher C_Theory and V_cell than graphene nanosheet.