Arbitrary Customization of Absorption Characteristic of Resonant Metasurface Based on Neural Network and Particle Swarm Optimization Algorithm

In this paper, we propose an arbitrary custom metasurface resonance absorption model based on a neural network and Particle Swarm Optimization (PSO) algorithm. Experimental results show that this method can quickly find the optimal geometric parameters according to the input absorption target, and can customize the absorption characteristic curve on demand. The predicted and target results are in good agreement with the actual results, which greatly saves manpower and time. This method enhances the application flexibility of metasurface absorbers by arbitrarily customizing the absorption characteristic and has potential application value in intelligent metasurface and absorber design.