arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2507.00546physics.app-phcs.AIcs.LGphysics.optics
收藏

纳米光子学中的逆向设计:基于表示学习

Inverse Design in Nanophotonics via Representation Learning

Reza Marzban, Ali Adibi, Raphael Pestourie

AI总结:

本文综述了纳米光子学逆向设计中基于表示学习的机器学习方法,分为输出端和输入端两类,并探讨了混合框架的优势及未来挑战。

摘要:

纳米光子学中的逆向设计,即通过计算发现能够实现目标电磁(EM)响应的结构,已成为近期光学进展的关键工具。传统的基于直觉或迭代优化的方法难以应对本质上高维、非凸的设计空间以及电磁模拟的巨大计算需求。近年来,机器学习(ML)的出现有效解决了这些瓶颈。本综述从表示学习的视角对机器学习增强的逆向设计方法进行梳理,将其分为两类:输出端方法和输入端方法。输出端方法利用机器学习在解空间中学习一种表示,以创建可微分的求解器,从而加速优化。相反,输入端技术利用机器学习学习可行器件几何形状的紧凑潜在空间表示,从而通过生成模型实现高效的全局探索。每种策略在数据需求、泛化能力和新颖设计发现潜力方面都呈现出独特的权衡。将基于物理的优化与数据驱动表示相结合的混合框架有助于摆脱较差的局部最优解,提高可扩展性,并促进知识迁移。最后,我们强调了开放性的挑战和机遇,重点关注复杂性管理、与几何无关的表示、制造约束的整合以及多物理场协同设计的进展。

英文摘要:

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. We conclude by highlighting open challenges and opportunities, emphasizing complexity management, geometry-independent representations, integration of fabrication constraints, and advancements in multiphysics co-designs.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑