Artificial neural network approaches for modeling absorption spectrum of nanowire solar cells

Hamedi, Samaneh; Kordrostami, Zoheir; Yadollahi, Ali

doi:10.1007/s00521-019-04406-3

Cited by 14 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their research shows how neural networks can improve the speed of predicting the optical properties of plasmonic nanoparticles. An MLP model and radial basis function (RBF) method are used for predicting the absorption spectra of silicon nanowire solar cells as developed by Hamedi et al (2019). The FDTD method is used to produce the dataset for training the model.…”

Section: Introductionmentioning

confidence: 99%

Prediction of optical properties of uniaxial hyperbolic nanospheres via artificial neural network

Edward,

Johnson

2024

Preprint

View full text Add to dashboard Cite

In this study, absorption and scattering multilayer perceptron models are developed and validated for the prediction of the optical spectra of uniaxial hyperbolic nanospheres. The finite difference time domain method is used to generate the dataset of the absorption and scattering optical spectra. The models' optimal performance is achieved for 5 hidden layers and 80 neurons for the absorption and the same hidden layers with 120 neurons for the scattering. The predictions by the model on the test dataset give a low aggregate mean squared error of 0.000145 for the absorption and 0.00071 for the scattering. We also performed a robustness test by using parameters outside the initial parameters used for the training and the predictions are in good agreement with the actual datasets for both absorption and scattering. This research shows the application of artificial neural network to predict the optical properties of hyperbolic materials and lay a groundwork for developing more complicated neural network models in predicting complex phenomena in hyperbolic metamaterials which are faster and computationally less expensive than using conventional simulation methods.

show abstract

Section: Introductionmentioning

confidence: 99%