Enhanced posterior sampling via diffusion models for efficient metasurfaces inverse design

TL;DR

This paper introduces a diffusion-based generative framework with advanced posterior sampling for efficient and accurate inverse design of metasurfaces, capable of handling large-scale configurations with reduced computational effort.

Contribution

It presents a novel diffusion model approach with consistency constraints for metasurface inverse design, enabling scalable, rapid, and high-precision electromagnetic device creation.

Findings

Enhanced accuracy and reliability in metasurface design.

Scalable methodology for large configurations up to 98x98 nanopillars.

Rapid design generation within minutes using smaller trained models.

Abstract

The inverse design of metasurfaces faces inherent challenges due to the nonlinear and highly complex relationship between geometric configurations and their electromagnetic behavior. Traditional optimization approaches often suffer from excessive computational demands and a tendency to converge to suboptimal solutions. This study presents a diffusion-based generative framework that incorporates a dedicated consistency constraint and advanced posterior sampling methods to ensure adherence to desired electromagnetic specifications. Through rigorous validation on small-scale metasurface configurations, the proposed approach demonstrates marked enhancements in both accuracy and reliability of the generated designs. Furthermore, we introduce a scalable methodology that extends inverse design capabilities to large-scale metasurfaces, validated for configurations of up to $98 \times 98$ nanopillars. Notably, this approach enables rapid design generation completed in minute by leveraging models trained on substantially smaller arrays ($23 \times 23$). These innovations establish a robust and efficient framework for high-precision metasurface inverse design.