Compatible Stealth Metasurface for Laser and Infrared with Radiative Thermal Engineering Enabled by Machine Learning

Abstract

Metasurface-based mid-infrared stealth compatible with visual or laser provide a promising way to increase survivability of military installations. However, current designs of metasurfaces following traditional paradigm suffer from low efficiency on calculating global structural parameters for multispectral requirements and limited thermal radiation engineering. Here, a metasurface with high-performance compatible stealth and effect thermal management is proposed, based on a machine-learning-enabled inverse design approach. The approach can rapidly generate multiple non-unique solutions in global to match the desired spectra in multi-wavebands, utilizing neural networks with physical-based data dimensionality. The finally generated metasurface has low specular reflectance (<0.01) at near-infrared laser wavelength and enhanced broad absorptance peak at 5-8 µm, which is attributed to the reflection splitting effect and infrared plasmonic resonance, respectively. Furthermore, a lowcost fabrication method is developed to produce the metasurface by colloidal lithography. The metasurface is demonstrated to have excellent capability of radiative thermal control and significantly decrease the apparent temperature under thermal imager (>50 °C). This study reveals an opportunity to inversely generate multiple solutions for photonic structures targeting on multispectral responses, in a systematic and efficient manner.

Whole-infrared-band camouflage with dual-band radiative heat dissipation

“…Considerable efforts have been directed toward developing thermal camouflage using various techniques in the MWIR and LWIR bands, including metallic/dielectric structures 10 – 21 , electrochromic 22 – 29 and thermochromic 30 – 33 materials. Additionally, progress has been made in thermal camouflage through simultaneous radiative heat dissipation in the 5–8 μm non-atmospheric window using nano-structures (e.g., photonic crystals 34 , 35 , metal-insulator-metal metasurfaces 36 – 42 , Fabry-Perot cavities 43 , 44 , anti-reflection layers 43 – 45 , and porous nanostructures 46 ). Besides, some studies have combined thermal camouflage with visible camouflage (e.g., cheating coloration 35 , 39 , 46 , transparency 37 , 41 , 44 , and low reflection 47 ) or laser camouflage in the NIR band (by using metal-insulator-metal metasurfaces 38 , 39 , 42 , 48 or photonic crystals 35 to absorb or using coding metasurfaces 49 to scatter the incident lasers) to address multiband detectors.…”

“…Considerable efforts have been directed toward developing thermal camouflage using various techniques in the MWIR and LWIR bands, including metallic/dielectric structures [10][11][12][13][14][15][16][17][18][19][20][21] , electrochromic [22][23][24][25][26][27][28][29] and thermochromic [30][31][32][33] materials. Additionally, progress has been made in thermal camouflage through simultaneous radiative heat dissipation in the 5-8 μm non-atmospheric window using nano-structures (e.g., photonic crystals 34,35 , metal-insulator-metal metasurfaces [36][37][38][39][40][41][42] , Fabry-Perot cavities 43,44 , anti-reflection layers [43][44][45] , and porous nanostructures 46 ). Besides, some studies have combined thermal camouflage with visible camouflage (e.g., cheating coloration 35,39,46 , transparency 37,41,44 , and low reflection…”

Machine-Learning-Assisted Design of a Robust Biomimetic Radiative Cooling Metamaterial

“…Machine Learning (ML) has recently become a powerful and innovative technique for complex computational problems and inverse design, i.e., to predict the complete optical response of photonic structures for given geometric parameters, as well as to retrieve the optimal design parameters for the desired optical response . The ML approach can be applied to strike the balance between excellent spectral characteristics and manufacture availability, which is beneficial to obtain easy-to-process artificial structures and hence to reduce the fabrication cost. − Additionally, ML is accurate and efficient in establishing correlations and sensitivities between numerous design variables, determining the optimal parameter interval and thus enhancing the robustness of the material preparation. − Therefore, by utilizing ML, we can incorporate it into the construction of biomimetic photonic structures to enhance spectral performance, clarify parametric mechanisms of action, and reduce the cost of preparation.…”