Search

Researchers have paid great attention to pursuing metal‐free nanostructures as alternatives to metallic counterparts in the field of surface‐enhanced Raman scattering (SERS) for label‐free sensing. However, these metal‐free investigations are hindered by the tiny enhancement factor of the local near field. Here, the design of all‐dielectric SERS metasurfaces is proposed with quasi‐bound states in the continuum (Q‐BIC), inspired by transformer‐based deep learning. By manipulating the incident angle, the mechanism of strong coupling Q‐BIC is introduced with a large Rabi splitting of ≈105 meV, which opens a bandgap and forms an anti‐crossing behavior. Compared to conventional approaches, the strong coupling Q‐BIC scheme not only boosts an extraordinary SERS enhancement factor of ≈107 but also extends the field‐enhancing scale up to ten‐fold. The theoretical optimization implies overwhelming dominance versus the conventional metallic nanostructure design for SERS. The study denotes an approach to utilize the strong coupling effects of Q‐BIC in all‐dielectric SERS metasurfaces and will provide essential design guides for more powerful sensing applications based on SERS. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

The design of plasmonic stack metamaterials (PSMs) is critical due to their promising potentials in the fields of optical absorbers, sensors, and thermal irradiation. Compared with the classical circuit‐based optimization, the design by deep learning (DL) has attracted greater attention, since it is not essential to obtain their equivalent circuit parameters. Currently, a DL model for their higher‐precision design, especially with complicated spectral features, is still quite in demand. Here, a divide‐and‐conquer DL model based on a bidirectional artificial neural network is proposed. As proof‐of‐concept examples, the PSMs consisting of two metal/dielectric/metal/dielectric subwavelength stacks are adopted to demonstrate the validity of the paradigm. It demonstrates a significant prediction error reduction of 37.5% with the 47.8% decrease of training parameters than the conventional method in the forward network, which supports a powerful inverse design from spectra to PSM structures. Furthermore, a flexible tool based on the free customer definition, which facilitates the real‐time design of PSMs with various circuit‐analog functions, is developed. The fabrication and measurement experiments verify the design performance of the method. The study enhances the precision and convenience of on‐demand circuit‐analog PSMs and will provide a guide for fast high‐performance inverse design of many other metamaterials. [ABSTRACT FROM AUTHOR]

Building extraction based on remote sensing images has been widely used in many industries. However, state-of-the-art methods produce an incomplete segmentation of buildings owing to unstable multi-scale context aggregation and a lack of consideration of semantic boundaries, ultimately resulting in large uncertainties in predictions at building boundaries. In this study, efficient fine building extraction methods were explored, which demonstrated that the rational use of edge features can significantly improve building recognition performance. Herein, a fine building extraction network based on a multi-scale edge constraint (MEC-Net) was proposed, which integrates the multi-scale feature fusion advantages of UNet++ and fuses edge features with other learnable multi-scale features to achieve the effect of prior constraints. Attention was paid to the alleviation of noise interference in the edge features. At the data level, according to the improvement of copy-paste according to the characteristics of remote sensing imaging, a data augmentation method for buildings (build-building) was proposed, which increased the number and diversity of positive samples by simulating the construction of buildings to increase the generalization of MEC-Net. MEC-Net achieved 91.13%, 81.05% and 74.13% IoU on the WHU, Massachusetts and Inria datasets, and it has a good inference efficiency. The experimental results show that MEC-Net outperforms the state-of-the-art methods, demonstrating its superiority. MEC-Net improves the accuracy of building boundaries by rationally using previous edge features. [ABSTRACT FROM AUTHOR]