A NEAT Approach to Evolving Neural-Network-based Optimization of Chiral Photonic Metasurfaces: Application of a Neuro-Evolution Pipeline

TL;DR

This paper integrates NEAT, a neuro-evolution algorithm, into a deep-learning framework to optimize chiral metasurfaces, resulting in efficient, adaptable neural networks that improve design accuracy and generalization in nanophotonics.

Contribution

It introduces the use of NEAT for evolving neural network architectures within a photonic metasurface optimization pipeline, enabling automatic architecture tuning and resource-efficient models.

Findings

NEAT-evolved models match or outperform dense networks in accuracy.

Standardized feature scaling improves model performance.

Resource-efficient models enable transfer learning to experimental data.

Abstract

The design of chiral metasurfaces with tailored optical properties remains a central challenge in nanophotonics due to the highly nonlinear relationship between geometry and chiroptical response. Machine-learning-assisted optimization pipelines have recently emerged as efficient tools to accelerate this process, yet their performance strongly depends on the choice of neural-network (NN) architecture. In this work, we integrate the NeuroEvolution of Augmenting Topologies (NEAT) algorithm into an established deep-learning optimization framework for dielectric chiral metasurfaces. NEAT autonomously evolves both network topology and connection weights, enabling task-specific architectures without manual tuning, whereas the reinforcement-learning strategy in our framework evolves knowledge of the solution space and fine-tunes a model's weights in parallel. Using a pipeline-produced dataset of 9,600 simulated GaP metasurface geometries, we evaluate NEAT under varying input dimensionalities, feature-scaling methods, and data sizes. With standardized feature scaling yielding the most consistent performance for both examined output dimensionalities, the relatively compact NEAT-evolved NN models, when integrated into the full optimization pipeline, achieve similar or improved predictive accuracy and generalization compared to initially employed dense few-layer perceptrons. Accordingly, these resource-efficient models successfully perform inference of metasurfaces exhibiting strong circular dichroism in the visible spectrum, allowing for transfer learning between simulated and experimental data. This approach demonstrates a scalable path toward adaptive, self-configuring machine-learning frameworks for automated photonic design both standalone and as building block for agentic artificial intelligence (AI).