Predicting nonlinear optical scattering with physics-driven neural networks

Abstract

Deep neural networks trained on physical losses are emerging as promising surrogates of nonlinear numerical solvers. These tools can predict solutions of Maxwell's equations and compute gradients of output fields with respect to the material and geometrical properties in millisecond times which makes them attractive for inverse design or inverse scattering applications. Here we develop a tunable version of MaxwellNet, a physics driven neural network able to compute light scattering from inhomogenous media with a size comparable with the incident wavelength in the presence of the optical Kerr effect. The weights of the network are dynamically adjusted to take into account the intensity-dependent refractive index of the material.

References in corpus (5)

• Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems
• Global optimization of dielectric metasurfaces using a physics-driven neural network
• Scalable Optical Learning Operator
• Physics-informed neural networks for imaging and parameter retrieval of photonic nanostructures from near-field data
• MO-PaDGAN: Reparameterizing Engineering Designs for Augmented Multi-objective Optimization

Cited by in corpus (3)

• Auxiliary Physics-Informed Neural Networks for Forward, Inverse, and Coupled Radiative Transfer Problems
• Physical Neural Networks with Self-Learning Capabilities
• Accelerated Time-Domain Simulation of Complex Photonic Structures with a Data-Aware Fourier Neural Operator