Photonic-dispersion neural networks for inverse scattering problems  

作　　者：Tongyu Li Ang Chen Lingjie Fan Minjia Zheng Jiajun Wang Guopeng Lu Maoxiong Zhao Xinbin Cheng Wei Li Xiaohan Liu Haiwei Yin Lei Shi Jian Zi 

机构地区：[1]State Key Laboratory of Surface Physics,Key Laboratory of Micro-and NanoPhotonics Structures(Ministry of Education)and Department of Physics,Fudan University,Shanghai 200433,China [2]Shanghai Engineering Research Center of Optical Metrology for Nano-fabrication(SERCOM),Shanghai 200433,China [3]Institute of Precision Optical Engineering,School of Physics Science and Engineering,Tongji University,Shanghai 200092,China [4]National Institute of Metrology,Beijing 100029,China [5]Collaborative Innovation Center of Advanced Microstructures,Nanjing University,Nanjing 210093,China

出　　处：《Light(Science & Applications)》2021年第10期1819-1828,共10页光（科学与应用)（英文版）

基　　金：The work was supported by the China National Key Basic Research Program(2016YFA0301103,2016YFA0302000 and 2018YFA0306201);the National Science Foundation of China(11774063,11727811,91750102 and 91963212);A.C.was supported by Shanghai Rising-Star Program(20QB1402200);L.S.was further supported by the Science and Technology Commission of Shanghai Municipality(19XD1434600,2019SHZDZX01,and 19DZ2253000).

摘　　要：Inferring the properties of a scattering objective by analyzing the optical far-field responses within the framework of inverse problems is of great practical significance.However,it still faces major challenges when the parameter range is growing and involves inevitable experimental noises.Here,we propose a solving strategy containing robust neuralnetworks-based algorithms and informative photonic dispersions to overcome such challenges for a sort of inverse scattering problem—reconstructing grating profiles.Using two typical neural networks,forward-mapping type and inverse-mapping type,we reconstruct grating profiles whose geometric features span hundreds of nanometers with nanometric sensitivity and several seconds of time consumption.A forward-mapping neural network with a parameters-to-point architecture especially stands out in generating analytical photonic dispersions accurately,featured by sharp Fano-shaped spectra.Meanwhile,to implement the strategy experimentally,a Fourier-optics-based angle-resolved imaging spectroscopy with an all-fixed light path is developed to measure the dispersions by a single shot,acquiring adequate information.Our forward-mapping algorithm can enable real-time comparisons between robust predictions and experimental data with actual noises,showing an excellent linear correlation(R2>0.982)with the measurements of atomic force microscopy.Our work provides a new strategy for reconstructing grating profiles in inverse scattering problems.

关 键 词：SCATTERING DISPERSION NEURAL 

分 类 号：O43[机械工程—光学工程] TP183[理学—光学]