Simulator-based training of generative neural networks for the inverse design of metasurfaces
Abstract
Metasurfaces are subwavelength-structured artificial media that can shape and localize electromagnetic waves in unique ways. The inverse design of these devices is a non-convex optimization problem in a high dimensional space, making global optimization a major challenge. We present a new type of population-based global optimization algorithm for metasurfaces that is enabled by the training of a generative neural network. The loss function used for backpropagation depends on the generated pattern layouts, their efficiencies, and efficiency gradients, which are calculated by the adjoint variables method using forward and adjoint electromagnetic simulations. We observe that the distribution of devices generated by the network continuously shifts towards high performance design space regions over the course of optimization. Upon training completion, the best generated devices have efficiencies comparable to or exceeding the best devices designed using standard topology optimization. Our proposed global optimization algorithm can generally apply to other gradient-based optimization problems in optics, mechanics, and electronics.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Nov 19, 2019
- Source ID
- 10.1515/nanoph-2019-0330
Entities
People
- Jiaqi Jiang
- Jonathan A. Fan
Organizations
- Office of Naval Research
- Stanford University
- United States Air Force