Figure 1 | Scientific Reports

Figure 1

From: A cyclical deep learning based framework for simultaneous inverse and forward design of nanophotonic metasurfaces

Figure 1

Illustration of gap-plasmon based HM. (a) A data sample composed of 2D cross sectional image of structural design of Al-nanoantennae and corresponding conversion efficiency as optical response. (b) Examples from structural design classes used for training of DL-NNs: cGAN and SNN. The pixel intensity of structural designs represents the thickness of the \(\hbox {SiO}_2\) dielectric spacer.

Back to article page