GiBS: Generative Input-side Basis-driven Structures

TL;DR

GiBS is an inverse-design framework that uses compact basis functions and machine learning to efficiently create complex, broadband metasurfaces with nonlocal optical effects, validated through experimental realization.

Contribution

Introduces GiBS, a scalable inverse-design method combining basis-driven representations with manifold learning for efficient metasurface design.

Findings

Achieved over tenfold reduction in design space dimensionality.

Successfully designed and experimentally validated a broadband scattering metasurface.

Demonstrated high fidelity between measured and simulated optical responses.

Abstract

Designing large-scale metasurfaces with nonlocal optical effects remains challenging due to the immense dimensionality and fabrication constraints of conventional optimization methods. We introduce GiBS (Generative Input-side Basis-driven Structures), an inverse-design framework that represents the entire device using a compact set of coefficients from smooth parametric bases such as Fourier or Chebyshev functions. This formulation compresses the design space by more than an order of magnitude, enabling efficient optimization of complex, broadband, and aperiodic geometries. GiBS integrates this low-dimensional representation with an autoencoder-based manifold-learning workflow to map the relationship between geometry and optical response, facilitating rapid exploration, discovery of high-performance designs, and systematic analysis of fabrication sensitivity. The inherent smoothness of the basis functions ensures manufacturability while capturing the asymmetry required for nonlocal optical interactions. We experimentally validated the framework through the realization of a PEDOT:PSS broadband scattering metasurface, whose measured response closely matched full-wave simulations across 500-1100 nm. These results establish GiBS as a scalable, data-efficient, and fabrication-aware platform for the inverse design of multifunctional metasurfaces, bridging AI-guided representation learning with experimentally realizable photonic architectures.