Prediction of Dispersion Relation and PBGs in 2-D PCs by Using Artificial Neural Networks

The prediction of dispersion relation and photonic band gaps in 2-D photonic crystals using artificial neural networks is demonstrated in this letter. Two case studies are carried out in order to evaluate the advantages of using this approach in conjunction with numerical methods. The results obtained present values that are very close to those obtained by a numerical solver and with short time-processing. We also compare artificial neural networks' outputs and well-known interpolation techniques.