A Deep Learning Approach for Inverse Design of Metasurfaces with A Wider Shape Gamut
Posted on 13.05.2022 - 15:46
The versatility of optical metasurfaces arises from the large design degrees of freedom (DOF) they possess; in principle, the shape and placement parameters of each of the constituent meta-atoms can be independently chosen. However, the large number of DOF makes the inverse design difficult. Metasurface designers mostly rely on simple shapes and ordered placements, which restricts the achievable performance. We report a deep learning based inverse design flow which enables a fuller exploitation of the meta-atom shape. Using a polygonal shape encoding that covers a broad gamut of lithographically-realizable resonators, we demonstrate the inverse design of color filters in an amorphous silicon material platform. The inverse-designed transmission-mode color filter metasurfaces were experimentally realized and exhibited enhancement in the color gamut. Our results show that deep learning based inverse design of metasurfaces may be helpful in enhancing the application potential of optical metasurfaces.
CITE THIS COLLECTION
Panda, Soumyashree; Choudhary, Sumit; Joshi, Siddharth; Kumar, Sharma Satinder; Hegde, Ravi (2022): A Deep Learning Approach for Inverse Design of Metasurfaces with A Wider Shape Gamut. Optica Publishing Group. Collection. https://doi.org/10.6084/m9.figshare.c.5956866.v2
Select your citation style and then place your mouse over the citation text to select it.
Read the peer-reviewed publication
Sharma Satinder Kumar