WaveY-Net: Physics-augmented deep learning for high-speed electromagnetic simulation and optimization
This addresses the need for faster simulation and optimization in photonic device design, offering a potential replacement for traditional Maxwell simulators, though it appears incremental as it builds on existing physics-augmented methods.
The paper tackled the problem of slow electromagnetic field simulations for photonic devices by introducing WaveY-Net, a hybrid deep learning model that predicts field distributions with ultra-fast speeds and high accuracy, achieving this through physics-augmented training and enabling effective optimization of metagratings.
The calculation of electromagnetic field distributions within structured media is central to the optimization and validation of photonic devices. We introduce WaveY-Net, a hybrid data- and physics-augmented convolutional neural network that can predict electromagnetic field distributions with ultra fast speeds and high accuracy for entire classes of dielectric photonic structures. This accuracy is achieved by training the neural network to learn only the magnetic near-field distributions of a system and to use a discrete formalism of Maxwell's equations in two ways: as physical constraints in the loss function and as a means to calculate the electric fields from the magnetic fields. As a model system, we construct a surrogate simulator for periodic silicon nanostructure arrays and show that the high speed simulator can be directly and effectively used in the local and global freeform optimization of metagratings. We anticipate that physics-augmented networks will serve as a viable Maxwell simulator replacement for many classes of photonic systems, transforming the way they are designed.