High-Accuracy Prediction of Metal-Insulator-Metal Metasurface with Deep Learning

TL;DR

This paper demonstrates that a ResNets-10 deep learning model can accurately predict plasmonic metasurface parameters, significantly reducing computation time and potentially replacing traditional electromagnetic simulation methods.

Contribution

The study introduces a ResNets-10 based prediction model with two-stage training that achieves ultralow error rates for metal-insulator-metal metasurfaces, enhancing electromagnetic design efficiency.

Findings

Prediction loss for aluminum, gold, and silver metasurfaces was -48.45, -46.47, and -35.54.

The model trains in less than 1,100 epochs, reducing design time.

The approach can be applied to design meta-diffractive devices and biosensors.

Abstract

Deep learning prediction of electromagnetic software calculation results has been a widely discussed issue in recent years. But the prediction accuracy was still one of the challenges to be solved. In this work, we proposed that the ResNets-10 model was used for predicting plasmonic metasurface S11 parameters. The two-stage training was performed by the k-fold cross-validation and small learning rate. After the training was completed, the prediction loss for aluminum, gold, and silver metal-insulator-metal metasurfaces was -48.45, -46.47, and -35.54, respectively. Due to the ultralow error value, the proposed network can replace the traditional electromagnetic computing method for calculation within a certain structural range. Besides, this network can finish the training process less than 1,100 epochs. This means that the network training process can effectively lower the design process time. The ResNets-10 model we proposed can also be used to design meta-diffractive devices and biosensors, thereby reducing the time required for the calculation process. The ultralow error of the network indicates that this work contributes to the development of future artificial intelligence electromagnetic computing software.