Anchor-Controlled Generative Adversarial Network for High-Fidelity Electromagnetic and Structurally Diverse Metasurface Design

TL;DR

This paper introduces AcGAN, a novel GAN framework that enhances electromagnetic fidelity and structural diversity in metasurface design through spectral fidelity assessment, real-time feedback, and a cluster-guided controller, achieving significant improvements over existing methods.

Contribution

The paper proposes AcGAN, a new GAN-based framework with spectral fidelity metrics, real-time electromagnetic feedback, and a cluster-guided controller to improve metasurface inverse design.

Findings

Reduces MSE by 73% compared to state-of-the-art GANs.

Expands the design space for diverse metasurface architectures.

Achieves high electromagnetic fidelity and structural diversity.

Abstract

Metasurfaces, capable of manipulating light at subwavelength scales, hold great potential for advancing optoelectronic applications. Generative models, particularly Generative Adversarial Networks (GANs), offer a promising approach for metasurface inverse design by efficiently navigating complex design spaces and capturing underlying data patterns. However, existing generative models struggle to achieve high electromagnetic fidelity and structural diversity. These challenges arise from the lack of explicit electromagnetic constraints during training, which hinders accurate structure-to-electromagnetic response mapping, and the absence of mechanisms to handle one-to-many mappings dilemma, resulting in insufficient structural diversity. To address these issues, we propose the Anchor-controlled Generative Adversarial Network (AcGAN), a novel framework that improves both electromagnetic fidelity and structural diversity. To achieve high electromagnetic fidelity, AcGAN proposes the Spectral Overlap Coefficient (SOC) for precise spectral fidelity assessment and develops AnchorNet, which provides real-time feedback on electromagnetic performance to refine the structure-to-electromagnetic mapping. To enhance structural diversity, AcGAN incorporates a cluster-guided controller that refines input processing and ensures multi-level spectral integration, guiding the generation process to explore multiple configurations for the same spectral target. Additionally, a dynamic loss function progressively shifts the focus from data-driven learning to optimizing both spectral fidelity and structural diversity. Empirical analysis shows that AcGAN reduces the Mean Squared Error (MSE) by 73% compared to current state-of-the-art GANs methods and significantly expands the design space to generate diverse metasurface architectures that meet precise spectral demands.