Dual-Output Mode Analysis of Multimode Laguerre-Gaussian Beams via Deep Learning

The Laguerre-Gaussian (LG) beam demonstrates great potential for optical communication due to its orthogonality between different eigenstates, and has gained increased research interest in recent years. Here, we propose a dual-output mode analysis method based on deep learning that can accurately obtain both the weight phase information of multimode LG beams. We reconstruct beams result predicted by convolutional neural network. It shows correlation coefficient values after reconstruction are above 0.9999, mean absolute error (MAE) weights phases about 1.4 × 10−3 2.9 10−3, respectively. model still maintains relatively accurate prediction associated unknown data set noise-disturbed samples. In addition, computation time single test sample takes only 0.975 ms average. These results show our good abilities generalization robustness allows nearly real-time modal analysis.