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

Abstract

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.

Metasurface inverse designed by deep learning for quasi-entire terahertz wave absorption

“…These algorithms have a well-established history in the design of various metasurfaces and are recognized for their exceptional prediction capabilities, as evidenced in prior studies. 47–51 In this rigorous comparative validation, all algorithms utilized identical training and test datasets, and hyperparameters optimization was performed via grid search during training to maximize their performance.…”

Design of an ultra-broadband terahertz absorber based on a patterned graphene metasurface with machine learning

“…To verify the superiority of RF in absorption bandwidth prediction, linear regression (LR), support vector machine (SVM), least squares (LS) method, and k-nearest neighbor (KNN) were used to train and predict the absorption bandwidth. These algorithms, as classical ML algorithms, have been shown to have good accuracy for solar cell absorption spectrum prediction, 49,50 spectral classification, 51,52 device parameter optimization, 53 etc. Before testing the other algorithmic models, we first performed a grid search of the hyperparameters of each algorithmic model to ensure that they were optimal.…”

Recent Advances in Reconfigurable Metasurfaces: Principle and Applications

“…Furthermore, when the modulating signals are time-varying, the reflecting waves can be controlled in the frequency domain. Recently, the metasurface shows a tendency for multidisciplinary intersection, according to some of the latest research results [ 90 , 269 , 270 , 271 , 272 , 273 , 274 , 275 ].…”