当前位置: X-MOL 学术ACS Photonics › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Transformation and Phase Retrieval of Electromagnetic Fields between a Plane and an Arbitrary Surface Using Machine Learning
ACS Photonics ( IF 6.5 ) Pub Date : 2020-11-20 , DOI: 10.1021/acsphotonics.0c00995
Sahar Froim 1 , Barak Hadad 1 , Amit Bekerman 1 , Yakir Hadad 1 , Alon Bahabad 1
Affiliation  

The ability to tailor a specific electromagnetic field pattern along an arbitrary selected surface is interesting and of substantial importance, given its numerous immediate applications. It belongs to a class of inverse source problems, and, as such, it is particularly challenging when only partial data are given. Here, a deep learning-based method that is able to map the electromagnetic field from an arbitrarily selected surface to a flat surface is presented. This method is used to realize, experimentally, arbitrary target field patterns on an arbitrary concave surface facing a source field on a flat programmable optical element. In addition, phase retrieval capability is demonstrated for finding both the phase and amplitude on an input flat surface from knowing only the amplitude on an arbitrarily selected surface.

中文翻译:

利用机器学习在平面与任意表面之间的电磁场的变换和相位提取

鉴于其众多的直接应用,沿着任意选定的表面定制特定的电磁场图案的能力非常有趣并且具有重要意义。它属于一类逆源问题,因此,当仅给出部分数据时,这尤其具有挑战性。在此,提出了一种基于深度学习的方法,该方法能够将电磁场从任意选择的表面映射到平坦表面。该方法用于在实验上在面对平面可编程光学元件上的源场的任意凹面上实现任意目标场图案。此外,还展示了相位恢复功能,可通过仅了解任意选择的表面上的振幅来找到输入平面上的相位和振幅。
更新日期:2020-12-16
down
wechat
bug