Inverse Design in Nanophotonics via Representation Learning
Open Access
- 28 November 2025
- journal article
- Published by Wiley in Advanced Optical Materials
- Vol. 14 (1)
Abstract
Inverse design in nanophotonics, the computational discovery of structures achieving targeted electromagnetic (EM) responses, has become a key tool for recent optical advances. Traditional intuition‐driven or iterative optimization methods struggle with the inherently high‐dimensional, non‐convex design spaces and the substantial computational demands of EM simulations. Recently, machine learning (ML) has emerged to address these bottlenecks effectively. This review frames ML‐enhanced inverse design methodologies through the lens of representation learning , classifying them into two categories: output‐side and input‐side approaches. Output‐side methods use ML to learn a representation in the solution space to create a differentiable solver that accelerates optimization. Conversely, input‐side techniques employ ML to learn compact, latent‐space representations of feasible device geometries, enabling efficient global exploration through generative models. Each strategy presents unique trade‐offs in data requirements, generalization capacity, and novel design discovery potentials. Hybrid frameworks that combine physics‐based optimization with data‐driven representations help escape poor local optima, improve scalability, and facilitate knowledge transfer. Data efficiency, transferable representations, fabrication‐aware design, faster solvers, and hybrid multiphysics co‐design are emphasized.Keywords
All Related Versions
Funding Information
- National Science Foundation (2435905)
- National Science Foundation (2212533)
- National Science Foundation (2240414)
This publication has 109 references indexed in Scilit:
- HiLAB: A Hybrid Inverse‐Design FrameworkSmall Methods, 2025
- High‐dimensional Bayesian optimization for metamaterial designMaterials Genome Engineering Advances, 2024
- Mixed formulation of physics‐informed neural networks for thermo‐mechanically coupled systems and heterogeneous domainsInternational Journal for Numerical Methods in Engineering, 2023
- Advances in Electromagnetics Empowered by Artificial Intelligence and Deep Learning2023
- Heterogeneous Transfer‐Learning‐Enabled Diverse Metasurface DesignAdvanced Optical Materials, 2022
- Deep Learning the Electromagnetic Properties of Metamaterials—A Comprehensive ReviewAdvanced Functional Materials, 2021
- Knowledge Discovery in Nanophotonics Using Geometric Deep LearningAdvanced Intelligent Systems, 2019
- Deep Learning Reveals Underlying Physics of Light–Matter Interactions in Nanophotonic DevicesAdvanced Theory and Simulations, 2019
- Probabilistic Representation and Inverse Design of Metamaterials Based on a Deep Generative Model with Semi‐Supervised Learning StrategyAdvanced Materials, 2019
- Finite Element Method2012