SLPA-Net: A Real-Time Recognition Network for Intelligent Stomata Localization and Phenotypic Analysis.

Plant stomatal phenotype traits play an important role in improving crop water use efficiency, stress resistance and yield. However, at present, the acquisition of phenotype traits mainly relies on manual measurement, which is time-consuming and laborious. In order to obtain high-throughput stomatal phenotype traits, we proposed a real-time recognition network SLPA-Net for stomata localization and phenotypic analysis. After locating and identifying stomatal density data, ellipse fitting is used to automatically obtain phenotype data such as apertures. Aiming at the problems of small stomata and high similarity to background, we introduced ECANet to improve the accuracy of stoma and aperture location. In order to effectively alleviate the unbalance problem in bounding box regression, we replaced the Loss function with a more effective Focal EIoU Loss. The experimental results show that SLPA-Net has excellent performance in the migration generalization and robustness of stomata and apertures detection and identification, as well as the correlation between stomata phenotype data obtained and artificial data.

Enhancement and Manipulation of Near-Field Thermal Radiation Using Hybrid Hyperbolic Polaritons.

Owing to a high electromagnetic confinement and a strong photonic density of states, hyperbolic surface plasmon polaritons (HSPPs) provide a fascinating promise for applications in thermal photonics. In this work, we theoretically predict a possibility for the improvement of the near-field radiative heat transfer on the basis of tailoring the electromagnetic state of hyperbolic metasurfaces by the uniaxial hyperbolic substrate. By using the photonic tunneling coefficient and the polaritons dispersion, we present a comprehensive study of the hybrid effect of the hyperbolic substrate on HSPPs. We find that due to the hybrid effect of the hyperbolic substrate, the anisotropy surface state of hyperbolic metasurfaces would undergo significant deformations and even topological transition. Moreover, we systematically exhibit the evolution of such hybrid hyperbolic mode with different thicknesses of the hyperbolic substrate and analyze the thickness effect on radiative properties of the hybrid system. It is shown that the resulting heat transfer with the assistance of the hybrid hyperbolic mode by optimizing the substrate parameters is many times stronger than that of monolayer hyperbolic metasurface at the same vacuum gap. Taken together, our results provide a platform to tailor 2D hyperbolic plasmons as a potential strategy toward passive or active control of the near-field heat transfer, and the hybrid hyperbolic mode presented here may facilitate the system design for near-field energy harvesting, thermal imaging, and radiative cooling applications.