Liu Ang, Lin Tianying, Han Hailong, Zhang Xiaopei, Chen Ze, Gan Fuwan, Lv Haibin, Liu Xiaoping
Opt Express. 2018 Aug 20;26(17):22100-22109. doi: 10.1364/OE.26.022100.
A machine learning assisted modal power analyzing scheme designed for optical modes in integrated multi-mode waveguides is proposed and studied in this work. Convolutional neural networks (CNNs) are successfully trained to correlate the far-field diffraction intensity patterns of a superposition of multiple waveguide modes with its modal power distribution. In particular, a specialized CNN is trained to analyze thin optical waveguides, which are single-moded along one axis and multi-moded along the other axis. A full-scale CNN is also trained to cross-validate the results obtained from this specialized CNN model. Prediction accuracy for modal power is benchmarked statistically with square error and absolute error distribution. It is found that the overall accuracy of our trained specialized CNN is very satisfactory for thin optical waveguides while that of our trained full-scale CNN remains nearly unchanged but the training time doubles. This approach is further generalized and applied to a waveguide that is multi-moded along both horizontal and vertical axes and the influence of noise on our trained network is studied. Overall, we find that the performance in this general condition keeps nearly unchanged. This new concept of analyzing modal power may open the door for high fidelity information recovery in far field and holds great promise for potential applications in both integrated and fiber-based spatial-division demultiplexing.
本文提出并研究了一种用于集成多模波导中光模式的机器学习辅助模态功率分析方案。成功训练了卷积神经网络（CNN），以将多个波导模式叠加的远场衍射强度图案与其模态功率分布相关联。特别是，训练了一个专门的CNN来分析薄光波导，该光波导在一个轴上是单模的，在另一个轴上是多模的。还训练了一个全尺寸的CNN来交叉验证从这个专门的CNN模型获得的结果。模态功率的预测精度通过平方误差和绝对误差分布进行统计基准测试。结果发现，对于薄光波导，我们训练的专门CNN的整体精度非常令人满意，而我们训练的全尺寸CNN的精度几乎保持不变，但训练时间增加了一倍。这种方法被进一步推广并应用于在水平和垂直轴上都是多模的波导，并研究了噪声对我们训练网络的影响。总体而言，我们发现在这种一般情况下性能几乎保持不变。这种分析模态功率的新概念可能为远场中的高保真信息恢复打开大门，并在集成和基于光纤的空分复用中具有潜在应用的巨大前景。
