Solving Complex Electromagnetic Scattering Problem Based on Physics-Informed Neural Network with Adaptive Sampling Method

In complex scattering environments, multiple equivalent singularities can make it difficult to solve problems through manual adjustments of collocation points. To address this issue, we propose a physics-informed neural network (PINN) approach with an adaptive sampling method. Our incremental method of sampling for adjusting collocation points automatically allows us to solve problems with unknown singularities. The sampling method significantly reduces the number of collocation points required, making solutions faster and more efficient, offering a promising approach to solve problems with unknown singularities in complex scattering environments.