Search

Mode division multiplexing (MDM) is currently one of the most attractive multiplexing techniques in optical communications, as it allows for an increase in the number of channels available for data transmission. Optical modal converters are one of the main devices used in this technique. Therefore, the characterization and improvement of these devices are of great current interest. In this work, we present a dataset of 49,736 near-field intensity images of a modal converter based on a long-period fiber grating (LPFG) written on a few-mode fiber (FMF). This characterization was performed experimentally at various wavelengths, polarizations, and temperature conditions when the device converted from LP 01 mode to LP 11 mode. The results show that the modal converter can be tuned by adjusting these parameters, and that its operation is optimal under specific circumstances which have a great impact on its performance. Additionally, the potential application of the database is validated in this work. A modal decomposition technique based on the particle swarm algorithm (PSO) was employed as a tool for determining the most effective combinations of modal weights and relative phases from the spatial distributions collected in the dataset. The proposed dataset can open up new opportunities for researchers working on image segmentation, detection, and classification problems related to MDM technology. In addition, we implement novel artificial intelligence techniques that can help in finding the optimal operating conditions for this type of device. [ABSTRACT FROM AUTHOR]

The traditional numerical analysis in waveguide design can be time-consuming and inefficient. This is even more prominent in the THz region and with complex shapes and materials. As an alternative to overcome these drawbacks, we propose a machine learning (ML) approach to design porous-core photonic crystal fibers (PCFs) for the THz band. This method is based on an artificial neural network (ANN) model trained to predict key parameters such as the effective refractive index, effective area, dispersion, and loss values with accuracy and speed. In that sense, the network was trained to perform multiple-output regression of the above parameters. The training data for this model comes from numerical calculations that use the finite element method (FEM) to simulate and evaluate analytical expressions. Our results demonstrate the ML model's ability to capture the complex and nonlinear relationships between the input and output parameters and accurately predict the behavior of the THz PCF. Moreover, the proposed model has an inference time of ∼0.03584 s for a batch of 32 data sets, which substantially outperforms typical calculation times needed in FEM simulations for THz waveguide design. These results show that this approach is efficient and effective and has the potential to significantly accelerate the design process of PCFs for THz applications. [ABSTRACT FROM AUTHOR]