光学精密工程2025，Vol.33Issue(7)：1042-1050,9.DOI:10.37188/OPE.20253307.1042
基于神经网络的全斯托克斯光电探测器
Full-stokes photodetector based on neural networks
摘要
Abstract
Traditional Full-Stokes detection methods are based on time-division or spatial-division ap-proaches,which suffer from drawbacks such as large device size,challenging integration,and inability to detect consistently in space and time.Recent advancements in two-dimensional materials and metamateri-als have made it possible to realize ultracompact,spatiotemporally coherent Full-Stokes detectors based on well-defined polarization-sensitive structures at subwavelength scales.This study proposes a polarization detector based on graphene-metal nanoantennas,which leverages vector photocurrents generated on gra-phene and a neural network algorithm for reconstruction,enabling spatiotemporally coherent Full-Stokes parameter detection.Vector photocurrents under different polarization states of incident light were ob-tained through FDTD simulations.Subsequently,a mapping relationship Ŝ=f(Î)between the Full-Stokes parameters Ŝ and the recorded vector photocurrents Î was established using a neural network algo-rithm,successfully enabling the detection of Full-Stokes parameters.At a wavelength of 4 μm,the mean square error was 0.007 69.The relative radius difference of the minimum enclosing spheres for the actual and predicted Stokes parameters of the incident light is 7.68%.This detector design offers a new ap-proach for achieving more integrated and miniaturized spatiotemporally coherent Full-Stokes detection.This detector effectively overcomes the inherent technical bottlenecks of time-division and spatial-division mechanisms,offering a novel approach for achieving more integrated and miniaturized spatiotemporally consistent full-Stokes detection.关键词
偏振光电探测器/全斯托克斯/时空一致/神经网络/石墨烯Key words
polarization photodetector/full-Stokes/spatiotemporal consistency/neural network/gra-phene分类
电子信息工程引用本文复制引用
王守桐,张然,褚金奎,蒙海龙,蔡德好..基于神经网络的全斯托克斯光电探测器[J].光学精密工程,2025,33(7):1042-1050,9.基金项目
国家自然科学基金资助项目(No.52275281,No.52175265) （No.52275281,No.52175265）
