Ultra‐Wideband, Polarization‐Independent, Wide‐Angle Multilayer Swastika‐Shaped Metamaterial Solar Energy Absorber with Absorption Prediction using Machine Learning

Explainable Encoder-Prediction-Reconstruction Framework for the Prediction of Metasurface Absorption Spectra

The correlation between metasurface structures and their corresponding absorption spectra is inherently complex due to intricate physical interactions. Additionally, the reliance on Maxwell's equations for simulating these relationships leads to extensive computational demands, significantly hindering rapid development in this area. Numerous researchers have employed artificial intelligence (AI) models to predict absorption spectra. However, these models often act as black boxes. Despite training high-performance models, it remains challenging to verify if they are fitting to rational patterns or merely guessing outcomes. To address these challenges, we introduce the Explainable Encoder-Prediction-Reconstruction (EEPR) framework, which separates the prediction process into feature extraction and spectra generation, facilitating a deeper understanding of the physical relationships between metasurface structures and spectra and unveiling the model's operations at the feature level. Our model achieves a 66.23% reduction in average Mean Square Error (MSE), with an MSE of 2.843 × 10-4 compared to the average MSE of 8.421×10-4 for mainstream networks. Additionally, our model operates approximately 500,000 times faster than traditional simulations based on Maxwell's equations, with a time of 3×10-3 seconds per sample, and demonstrates excellent generalization capabilities. By utilizing the EEPR framework, we achieve feature-level explainability and offer insights into the physical properties and their impact on metasurface structures, going beyond the pixel-level explanations provided by existing research. Additionally, we demonstrate the capability to adjust absorption by changing the metasurface at the feature level. These insights potentially empower designers to refine structures and enhance their trust in AI applications.

An innovative machine learning based on feed-forward artificial neural network and equilibrium optimization for predicting solar irradiance

As is known, having a reliable analysis of energy sources is an important task toward sustainable development. Solar energy is one of the most advantageous types of renewable energy. Compared to fossil fuels, it is cleaner, freely available, and can be directly exploited for electricity. Therefore, this study is concerned with suggesting novel hybrid models for improving the forecast of Solar Irradiance (IS). First, a predictive model, namely Feed-Forward Artificial Neural Network (FFANN) forms the non-linear contribution between the IS and dominant meteorological and temporal parameters (including humidity, temperature, pressure, cloud coverage, speed and direction of wind, month, day, and hour). Then, this framework is optimized using several metaheuristic algorithms to create hybrid models for predicting the IS. According to the accuracy assessments, metaheuristic algorithms attained satisfying training for the FFANN by using 80% of the data. Moreover, applying the trained models to the remaining 20% proved their high proficiency in forecasting the IS in unseen environmental circumstances. A comparison among the optimizers revealed that Equilibrium Optimization (EO) could achieve a higher accuracy than Wind-Driven Optimization (WDO), Optics Inspired Optimization (OIO), and Social Spider Algorithm (SOSA). In another phase of this study, Principal Component Analysis (PCA) is applied to identify the most contributive meteorological and temporal factors. The PCA results can be used to optimize the problem dimension, as well as to suggest effective real-world measures for improving solar energy production. Lastly, the EO-based solution is yielded in the form of an explicit formula for a more convenient estimation of the IS.

Broadband and Efficient Metamaterial Absorber Design Based on Gold-MgF2-Tungsten Hybrid Structure for Solar Thermal Application

We have presented a solar absorber design with gold-MgF₂-tungsten materials. The solar absorber design is optimized with nonlinear optimization mathematical method to find and optimize geometrical parameters. The wideband absorber is made of a three-layer structure composed of tungsten, magnesium fluoride, and gold. This study analyzed the absorber's performance using numerical methods over the sun wavelength range of 0.25 μm to 3 μm. The solar AM 1.5 absorption spectrum is a benchmark against which the proposed structure's absorbing characteristics are evaluated and discussed. It is necessary to analyze the behavior of the absorber under a variety of various physical parameter conditions in order to determine the results and structural dimensions that are optimal. The nonlinear parametric optimization algorithm is applied to obtain the optimized solution. This structure can absorb more than 98% of light across the near-infrared and visible light spectrums. In addition, the structure has a high absorption efficiency for the far range of the infrared spectrum and the THz range. The absorber that has been presented is versatile enough to be used in a variety of solar applications, both narrowband and broadband. The design of the solar cell that has been presented will be of assistance in designing a solar cell that has high efficiency. The proposed optimized design with optimized parameters will help design solar thermal absorbers.

Ultra-Broadband Solar Absorber and High-Efficiency Thermal Emitter from UV to Mid-Infrared Spectrum

Solar energy is currently a very popular energy source because it is both clean and renewable. As a result, one of the main areas of research now is the investigation of solar absorbers with broad spectrum and high absorption efficiency. In this study, we create an absorber by superimposing three periodic Ti-Al₂O₃-Ti discs on a W-Ti-Al₂O₃ composite film structure. We evaluated the incident angle, structural components, and electromagnetic field distribution using the finite difference in time domain (FDTD) method in order to investigate the physical process by which the model achieves broadband absorption. We find that distinct wavelengths of tuned or resonant absorption may be produced by the Ti disk array and Al₂O₃ through near-field coupling, cavity-mode coupling, and plasmon resonance, all of which can effectively widen the absorption bandwidth. The findings indicate that the solar absorber's average absorption efficiency can range from 95.8% to 96% over the entire band range of 200 to 3100 nm, with the absorption bandwidth of 2811 nm (244-3055 nm) having the highest absorption rate. Additionally, the absorber only contains tungsten (W), titanium (Ti), and alumina (Al₂O₃), three materials with high melting points, which offers a strong assurance for the absorber's thermal stability. It also has a very high thermal radiation intensity, reaching a high radiation efficiency of 94.4% at 1000 K, and a weighted average absorption efficiency of 98.3% at AM1.5. Additionally, the incidence angle insensitivity of our suggested solar absorber is good (0-60°) and polarization independence is good (0-90°). These benefits enable a wide range of solar thermal photovoltaic applications for our absorber and offer numerous design options for the ideal absorber.

Deep neural network training method based on vectorgraphs for designing of metamaterial broadband polarization converters

In this work, we proposed a method of extracting feature parameters for deep neural network prediction based on the vectorgraph storage format, which can be applied to the design of electromagnetic metamaterials with sandwich structures. Compared to current methods of manually extracting feature parameters, this method can automatically and precisely extract the feature parameters of arbitrary two-dimensional surface patterns of the sandwich structure. The position and size of surface patterns can be freely defined, and the surface patterns can be easily scaled, rotated, translated, or transformed in other ways. Compared to the pixel graph feature extraction method, this method can adapt to very complex surface pattern design in a more efficient way. And the response band can be easily shifted by scaling the designed surface pattern. To illustrate and verify the method, a 7-layer deep neural network was built to design a metamaterial broadband polarization converter. Prototype samples were fabricated and tested to verify the accuracy of the prediction results. In general, the method is potentially applicable to the design of different kinds of sandwich-structure metamaterials, with different functions and in different frequency bands.

SARS-CoV-2 detecting rapid metasurface-based sensor

We have proposed a novel approach to detect COVID-19 by detecting the ethyl butanoate which high volume ratio is present in the exhaled breath of a COVID-19 infected person. We have employed a refractive index sensor (RIS) with the help of a metasurface-based slotted T-shape perfect absorber that can detect ethyl butanoate present in exhaled breath of COVID-19 infected person with high sensitivity and in-process SARS-CoV-2. The optimized structure of the sensor is obtained by varying several structure parameters including structure length and thickness, slotted T-shape resonator length, width, and thickness. Sensor's performance is evaluated based on numerous factors comprising of sensitivity, Q factor, detection limit, a figure of merit (FOM), detection accuracy, and other performance defining parameters. The proposed slotted T-shape RIS achieved the largest sensitivity of 2500 nm/RIU, Q factor of 131.06, a FOM of 131.58 RIU^-1, detection limit of 0.0224 RIU.

Recent Advances in Biosensors for Detection of COVID-19 and Other Viruses

This century has introduced very deadly, dangerous, and infectious diseases to humankind such as the influenza virus, Ebola virus, Zika virus, and the most infectious SARS-CoV-2 commonly known as COVID-19 and have caused epidemics and pandemics across the globe. For some of these diseases, proper medications, and vaccinations are missing and the early detection of these viruses will be critical to saving the patients. And even the vaccines are available for COVID-19, the new variants of COVID-19 such as Delta, and Omicron are spreading at large. The available virus detection techniques take a long time, are costly, and complex and some of them generates false negative or false positive that might cost patients their lives. The biosensor technique is one of the best qualified to address this difficult challenge. In this systematic review, we have summarized recent advancements in biosensor-based detection of these pandemic viruses including COVID-19. Biosensors are emerging as efficient and economical analytical diagnostic instruments for early-stage illness detection. They are highly suitable for applications related to healthcare, wearable electronics, safety, environment, military, and agriculture. We strongly believe that these insights will aid in the study and development of a new generation of adaptable virus biosensors for fellow researchers.

Highly efficient, perfect, large angular and ultrawideband solar energy absorber for UV to MIR range

Although different materials and designs have been tried in search of the ideal as well as ultra-wideband light absorber, achieving ultra-broadband and robust unpolarized light absorption over a wide angular range has proven to be a major issue. Light-field regulation capabilities provided by optical metamaterials are a potential new technique for perfect absorbers. It is our goal to design and demonstrate an ultra-wideband solar absorber for the ultraviolet to a mid-infrared region that has an absorptivity of TE/TM light of 96.2% on average. In the visible, NIR, and MIR bands of the solar spectrum, the absorbed energy is determined to be over 97.9%, above 96.1%, and over 95%, respectively under solar radiation according to the Air Mass Index 1.5 (AM1.5) spectrum investigation. In order to achieve this wideband absorption, the TiN material ground layer is followed by the SiO₂ layer, and on top of that, a Cr layer with patterned Ti-based resonators of circular and rectangular multiple patterns. More applications in integrated optoelectronic devices could benefit from the ideal solar absorber's strong absorption, large angular responses, and scalable construction.

Machine learning assisted metamaterial-based reconfigurable antenna for low-cost portable electronic devices

Antenna design has evolved from bulkier to small portable designs but there is a need for smarter antenna design using machine learning algorithms that can meet today's high growing demand for smart and fast devices. Here in this research, main focus is on developing smart antenna design using machine learning applicable in 5G mobile applications and portable Wi-Fi, Wi-MAX, and WLAN applications. Our design is based on the metamaterial concept where the patch is truncated and etched with a split ring resonator (SRR). The high gain requirement is met by adding metamaterial superstrates having thin wires (TW) and SRRs. The reconfigurability is achieved by adding three PIN diode switches. Multiple designs have been observed by adding superstrate layers ranging from one layer to four layers with interchanging TWs and SRRs. The TW metamaterial superstrate design with two layers is giving the best performance in gain, bandwidth, and the number of bands. The design is optimized by changing the path's physical parameters. To shrink simulation time, Extra Tree Regression based machine learning model is used to learn the behavior of the antenna and predict the reflectance value for a wide range of frequencies. Experimental results prove that the use of the Extra Tree Regression based model for simulation of antenna design can cut the simulation time, resource requirements by 80%.

Tunable Electromagnetically Induced Transparent Window of Terahertz Metamaterials and Its Sensing Performance

The electromagnetically induced transparency effect of terahertz metamaterials exhibits excellent modulation and sensing properties, and it is critical to investigate the modulation effect of the transparent window by optimizing structural parameters. In this work, a unilateral symmetrical metamaterial structure based on the cut-wire resonator and the U-shaped split ring resonator is demonstrated to achieve electromagnetically induced transparency-like (EIT-like) effect. Based on the symmetrical structure, by changing the structural parameters of the split ring, an asymmetric structure metamaterial is also studied to obtain better tuning and sensing characteristics. The parameters for controlling the transparent window of the metamaterial are investigated in both passive and active modulation modes. In addition, the metamaterial structure based on the cut-wire resonator, unilateral symmetric and asymmetric configurations are investigated for high performance refractive index sensing purposes, and it is found that the first two metamaterial structures can achieve sensitivity responses of 63.6 GHz/RIU and 84.4 GHz/RIU, respectively, while the asymmetric metamaterial is up to 102.3 GHz/RIU. The high sensitivity frequency response of the proposed metamaterial structures makes them good candidates for various chemical and biomedical sensing applications.

Ultra-broadband, wide-angle plus-shape slotted metamaterial solar absorber design with absorption forecasting using machine learning

Energy utilization is increasing day by day and there is a need for highly efficient renewable energy sources. Solar absorbers with high efficiency can be used to meet these growing energy demands by transforming solar energy into thermal energy. Solar absorber design with highly efficient and Ultra-broadband response covering visible, ultraviolet, and near-infrared spectrum is proposed in this paper. The absorption response is observed for three metamaterial designs (plus-shape slotted design, plus-shape design, and square-shape design) and one optimized design is used for solar absorber design based on its high efficiency. The design results are compared with AM 1.5 spectral irradiance response. The electric field response of the plus-shape slotted metamaterial design is also presented which matches well with the absorption results of different solar spectrum regions. The results proved that the attained absorption response showing wide angle of incidence. Machine learning is also used to examine the design data in order to forecast absorption for various substrate thickness, metasurface thickness, and incidence angles. Regression and forecasting simulations based on machine learning are used to try to anticipate absorber behaviour at forthcoming and intermediate wavelengths. Simulation results prove that Machine Learning based methods can lessen the obligatory simulation resources, time and can be used as an effective tool while designing the absorber. The proposed highly efficient, wide-angle, ultra-broadband solar absorber design with its behavior prediction capability using machine learning can be utilized for solar thermal energy harvesting applications.