Inverse Design of Metasurface based Absorbers using Physics Guided Conditional Diffusion Models

TL;DR

This paper introduces a physics-guided diffusion model for the inverse design of metasurface absorbers, enabling rapid generation of practical, high-fidelity electromagnetic designs conditioned on spectral targets.

Contribution

It presents a novel diffusion framework incorporating physics-based regularization and conditional features for efficient, accurate metasurface design, outperforming traditional iterative methods.

Findings

Achieves spectral MSE of 0.0006 and 95.8% band accuracy.

Generates designs in approximately 30 seconds, compared to months for conventional methods.

Produces diverse design options for the same spectral condition.

Abstract

Inverse design of metasurfaces for specific electromagnetic responses requires generating geometries that satisfy stringent spectral constraints while maintaining manufacturability. Conventional design methodologies rely on iterative optimization routines using full wave simulations, which become extremely time consuming and computationally intensive for large design spaces. In addition, commonly employed generative approaches often exhibit limited conditional fidelity and the generated designs often contain fine or irregular features that are impractical to fabricate. In this regard, we propose a physics guided condition quality enhanced diffusion framework for the inverse design of metasurface based absorbers. Here, the conditioning information consisting of target reflection characteristics is integrated into the model using feature wise linear modulation (FiLM). Furthermore, to enforce adherence to target spectra, a pre trained surrogate EM simulator is embedded into the framework introducing physics aware regularization through spectrum level loss functions. The efficiency of the proposed model is demonstrated by generating practically realizable metasurfaces for different types of reflection characteristics in the frequency range of 2 to 18 GHz. The proposed framework achieves an average spectral mean squared error of 0.0006 and band alignment accuracy of 0.958 between the target spectra and the spectra produced by the generated designs, demonstrating high conditional accuracy. In addition, the model generates multiple geometries for the same condition, thereby providing diverse design alternatives to the engineer. The proposed model produces the suitable design in approximately 30 seconds, whereas the conventional approach can take several months under comparable computational resources. The efficiency of the model is also established via experimental measurements.