Artificial Neural Networks for the Chromatic Dispersion Prediction of Photonic Crystal Fibers

Rodríguez-Esquerre, V. F.; Lima, Joaquim Júnior Isídio de; Dourado-Sisnando, A.; Silva, F. G. Simões

doi:10.1002/mop.27753

Cited by 11 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The extremely skewed and non-uniform data distribution renders the artificial neural network unable to accurately predict the corresponding results. The solution [33,38,47] proposed to solve this problem in other papers was to take the logarithm of the initially collected α c values which forms a more uniform distribution.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Deep neural network for microstructured polymer fiber modeling

Li¹,

Chen²,

Chen³

et al. 2023

J. Phys. D: Appl. Phys.

View full text Add to dashboard Cite

Microstructured polymer ﬁbers have been widely studied for terahertz waveguides, sensing, environmental monitoring, and medicine. Time-consuming methods including ﬁnite element method and ﬁnite-diﬀerent time-domain have been used to design and simulate microstructure polymer ﬁbers. Deep learning method enabled by artiﬁcial neural networks provides an eﬀective alternative to accurately predicting the core mode of optical properties within a short time, which avoids the waste of data resources. Designing optimal artiﬁcial neural networks with various hyperparameters for each optical property considerably improve prediction accuracy. To assess whether high-accuracy artiﬁcial neural networks were trained by checking absolute percentage errors between predicted values and actual values on the validation set. We utilized the successfully trained artiﬁcial neural networks to accurately evaluate the optical properties of the unknown geometry including eﬀective refractive index neﬀ , and eﬀective mode area (Aeﬀ ) and took the logarithm to form a more uniform distribution also had been successfully predicted the conﬁnement loss (αc). We also demonstrated artiﬁcial neural networks that predict the output for unknown geometric parameters, with several orders of magnitude speed-up compared to the ﬁnite element method simulation. Moreover, this approach can be easily applied to other similar types of optical ﬁbers which accelerate the optical function device design process.

show abstract

Section: Methodsmentioning

confidence: 99%

“…They predicted the effective refractive index and the confinement loss respectively. In 2013, Rodríguez-Esquerre et al [38] used ANN to predict the dispersion of photonic crystal fibers. In 2019, Chugh et al [39] used ANN to predict the effective refractive index, confinement loss, dispersion, and effective mode simultaneously.…”

Section: Introductionmentioning

confidence: 99%

Deep neural network for microstructured polymer fiber modeling

Li¹,

Chen²,

Chen³

et al. 2023

J. Phys. D: Appl. Phys.

View full text Add to dashboard Cite

show abstract

“…To address this issue, machine learning (ML) techniques have emerged as a promising alternative for optimizing waveguide designs. In fact, ML techniques have been successfully applied to other photonic applications such as sensors, 15,16 the design of optical couplers, 17 microresonators, 18 hollow-core anti-resonant fibers, 19,20 prediction of the chromatic dispersion of PCFs, [21][22][23][24] cross-layer optimization of software-defined networks, 25 quality of transmission estimation, 25 design of nano-photonic structures, 26 and prediction of nonlinear phenomena in optical fibers. [27][28][29] For instance, Rodrigues-Esquerre et al 21 reported a multilayer perceptron (MLP) artificial neuronal network (ANN) to test and predict the chromatic dispersion of PCFs.…”

Section: Introductionmentioning

confidence: 99%

“…For instance, Rodrigues-Esquerre et al 21 . reported a multilayer perceptron (MLP) artificial neuronal network (ANN) to test and predict the chromatic dispersion of PCFs.…”

Section: Introductionmentioning

confidence: 99%

Design of porous-core photonic crystal fiber based on machine learning approach

Soto-Perdomo,

Reyes-Vera,

Montoya-Cardona

et al. 2024

Opt. Eng.

View full text Add to dashboard Cite

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.

show abstract

“…Sobre Redes Neurais Artificiais (RNAs), há diversos trabalhos que mostram sua utilização na modelagem de projetos de fibras, tais como acopladores direcionais [9], design de PCF com alta birrefringência e baixas perdas para dois modos de polarização [10]. Seu uso também possibilitou melhorias na dispersão cromática em fibras microestruturadas [11], previsão da relação de dispersão e de bandas fotônicas em cristais fotônicos 2D [12].…”

Section: Introductionunclassified

Reconhecimento de portas lógicas em projeto de acopladores de fibra de cristal fotônico

Rodrigues,

Martins,

Pinto Júnior

et al. 2024

Braz. J. Develop.

View full text Add to dashboard Cite

Este trabalho investiga a relação entre os parâmetros físicos e lógicos de um acoplador duplo simétrico de Fibra de Cristal Fotônico (PCF), utilizando redes neurais Perceptrons Multicamadas (MLPs). Sob modulação PAM e on-off (OOK), o estudo mostra que, as variações das combinações específicas dos valores dos parâmetros físicos determinam os pulsos de saídas lógicas desta PCF. Tais combinações foram analisadas por uma rede MLP, e esta foi capaz de classificar e determinar com precisão de 98,71% as características físicas que determinam a ocorrência da porta lógica OR. Assim, pelo alto percentual de acertos, pode-se concluir que as MLPs podem ser usadas, com sucesso, para classificar as relações entre características físicas e lógicas desta PFC.

show abstract

Artificial Neural Networks for the Chromatic Dispersion Prediction of Photonic Crystal Fibers

Abstract: Multilayer perceptron artificial neural networks have been used for the efficient evaluation and prediction of the chromatic dispersion properties of microstructured optical fibers, with very low computational resources and efforts in an easy, efficient, and simple way.

Cited by 11 publications

References 11 publications

Deep neural network for microstructured polymer fiber modeling

Deep neural network for microstructured polymer fiber modeling

Design of porous-core photonic crystal fiber based on machine learning approach

Reconhecimento de portas lógicas em projeto de acopladores de fibra de cristal fotônico

Contact Info

Product

Resources

About