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

Abstract

The conventional approach to nanophotonic metasurface design and optimization for a targeted electromagnetic response involves exploring large geometry and material spaces. This is a highly iterative process based on trial and error, which is computationally costly and time consuming. Moreover, the non-uniqueness of structural designs and high non-linearity between electromagnetic response and design makes this problem challenging. To model this unintuitive relationship between electromagnetic response and metasurface structural design as a probability distribution in the design space, we introduce a framework for inverse design of nanophotonic metasurfaces based on cyclical deep learning (DL). The proposed framework performs inverse design and optimization mechanism for the generation of meta-atoms and meta-molecules as metasurface units based on DL models and genetic algorithm. The framework includes consecutive DL models that emulate both numerical electromagnetic simulation and iterative processes of optimization, and generate optimized structural designs while simultaneously performing forward and inverse design tasks. A selection and evaluation of generated structural designs is performed by the genetic algorithm to construct a desired optical response and design space that mimics real world responses. Importantly, our cyclical generation framework also explores the space of new metasurface topologies. As an example application of the utility of our proposed architecture, we demonstrate the inverse design of gap-plasmon based half-wave plate metasurface for user-defined optical response. Our proposed technique can be easily generalized for designing nanophtonic metasurfaces for a wide range of targeted optical response.

Deep learning modeling strategy for material science: from natural materials to metamaterials

“…Based on the DL model and genetic model, inverse design and optimized generation of structural units in metamaterials can be realized [133]. This can also be achieved through the combination of the DL model and PSO algorithm [134].…”

Artificial intelligence for photonics and photonic materials

“…In particular, the recent application of deep learning (or ANNs) to nanophotonics design problems has provided a significant design flexibility compared with conventional optimization methods. Indeed, the advantages of ANNs over traditional optimization approaches have been highlighted in many recent publications [58][59][60] showing that ANNs enable to automate and solve design problems in a much faster way than conventional optimization methods (once the neural network is trained) [61] and, additionally, deep learning allows to tackle the direct and inverse problem at the same time [62,63] and can help to find complex, nonintuitive relationship between the structure and its optical response as shown in Figure 4a [ In this work, Peurifoy et al [5] have used an ANN to approximate light scattering by multilayer nanoparticles. Once the neural network is trained, it can simulate the optical properties of nanoparticles orders of magnitude faster than conventional simulations.…”

A unique physics-inspired deep-learning-based platform introducing a generalized tool for rapid optical-response prediction and parametric-optimization for all-dielectric metasurfaces

“…Deep learning based metasurface modeling approaches have turned out to be very effective to predict the EM amplitude response [39][40][41] and performing inverse design for it. However, the prediction of phase and the optimization of dielectric resonators for full phase coverage is a much more challenging problem due to the abrupt discontinuities as discussed in the previous paragraph.…”