A unique physics-inspired deep-learning-based platform introducing a generalized tool for rapid optical-response prediction and parametric-optimization for all-dielectric metasurfaces.

Metasurfaces are composed of a two-dimensional array of carefully engineered subwavelength structures. They provide a novel compact alternative to conventional voluminous optical components. However, their design involves a time-consuming hit and trial procedure, requiring many iterative electromagnetic simulations through expensive commercial solvers. To overcome this non-practical design strategy, recently, various deep-learning-based fast and low computational cost networks have been proposed to design and optimize individual meta-atoms and complete metasurfaces. Most of them focus on optimizing the amplitude response of nanostructures, whereas mapping the phase response is a much more challenging problem that needs to be addressed. Since the metaatom's optical response is entirely reliant on and vulnerable to its geometrical structure, underlying material, and operating wavelength, changing any of these parameters changes the entire physics of the problem in hand. Here, we propose novel deep-learning-based generalized forward and inverse design approaches to optimize all-dielectric transmissive metasurfaces. The proposed forward predicting neural networks take all the geometrical parameters and the physical properties of the bar-shaped dielectric nano-resonators as the input and predict the cross-polarized transmission amplitude and modulated phase at eight distinct rotation angles of the nano-bar. These networks are generalized to predict the electromagnetic (EM) response of different dielectric materials at different operating wavelengths. An inverse design neural network is also proposed that takes the target transmission amplitude and phase at eight discrete orientation angles of the nano-bar as the primary input. The underlying physics of the problem is also incorporated by feeding the intrinsic material properties and the operating wavelength of the nano-bar as a second input to the inverse neural network. It predicts the optimum set of geometrical parameters to achieve maximum cross-polarized transmission and complete Pancharatnam-Berry (PB) phase coverage from 0 to 2π. The average test data mean square error (MSE) achieved for the forward predicting neural network is 1.8 × 10-3 and that of the inverse design neural network is 2.8 × 10-1. The average MSEs for different material's test samples are demonstrated to validate the generalizability of the proposed models in terms of seen and unseen materials. A comparative analysis of the proposed approach with conventional EM software optimization tools is performed to prove that the proposed inverse design works much faster than the conventional methods, also it can handle a comparatively larger range of parameters and predicts the results in a single run with high accuracy.

Nanostructured chromium-based broadband absorbers and emitters to realize thermally stable solar thermophotovoltaic systems.

The efficiency of traditional solar cells is constrained due to the Shockley-Queisser limit, to circumvent this theoretical limit, the concept of solar thermophotovoltaics (STPVs) has been introduced. The typical design of an STPV system consists of a wideband absorber with its front side facing the sun. The back of this absorber is physically attached to the back of a selective emitter facing a low-bandgap photovoltaic (PV) cell. We demonstrate an STPV system consisting of a wideband absorber and emitter pair achieving a high absorptance of solar radiation within the range of 400-1500 nm (covering the visible and infrared regions), whereas the emitter achieves an emittance of >95% at a wavelength of 2.3 µm. This wavelength corresponds to the bandgap energy of InGaAsSb (0.54 eV), which is the targeted PV cell technology for our STPV system design. The material used for both the absorber and the emitter is chromium due to its high melting temperature of 2200 K. An absorber and emitter pair is also fabricated and the measured results are in agreement with the simulated results. The design achieves an overall solar-to-electrical simulated efficiency of 21% at a moderate temperature of 1573 K with a solar concentration of 3000 suns. Furthermore, an efficiency of 15% can be achieved at a low temperature of 873 K with a solar concentration of 500 suns. The designs are also insensitive to polarization and show negligible degradation in solar absorptance and thermal emittance with a change in the angle of incidence.

Exploiting zirconium nitride for an efficient heat-resistant absorber and emitter pair for solar thermophotovoltaic systems.

A perfect absorber in the visible-infrared regime maintaining its performance at elevated temperatures and under a harsh environment is needed for energy harvesting using solar-thermophotovoltaic (STPV) systems. A near-perfect metasurface absorber based on lossy refractory metal nitride, zirconium-nitride (ZrN), having a melting-point of 2,980°C, is presented. The numerically proposed design with metal-insulator-metal configuration exhibits an average of > 95% for 400-800 nm and 86% for 280-2200 nm. High absorption is attributed to magnetic resonance leading to free-space impedance matching. The subwavelength structure is polarization- and angle-insensitive and is highly tolerant to fabrication imperfections. An emitter is optimized for bandgap energy ranging from 0.7 eV-1.9 eV.