Elucidating the Behavior of Nanophotonic Structures Through Explainable Machine Learning Algorithms

Abstract

A central challenge in the development of nanophotonic structures is identifying the optimal design for a target functionality, and understanding the physical mechanisms that enable the optimized device's capabilities. Previously investigated design methods for nanophotonic structures, including both conventional optimization approaches as well as nascent machine learning (ML) strategies, have made progress, yet they remain 'black boxes' that lack explanations for their predictions. Here we demonstrate that convolutional neural networks (CNN) trained to predict the electromagnetic response of classes of metal-dielectric-metal metamaterials, including complex freeform designs, can be explained to reveal deeper insights into the underlying physics of nanophotonic structures. Using an explainable AI (XAI) approach, we show that we can identify the importance of specific spatial regions of a nanophotonic structure for the presence or lack of an absorption peak. Our results highlight that ML strategies can be used for physics discovery, as well as design optimization, in optics and photonics.

References in corpus (10)

• Outlook for inverse design in nanophotonics
• Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
• Training deep neural networks for the inverse design of nanophotonic structures
• Explainable Machine Learning for Scientific Insights and Discoveries
• A Generative Model for Inverse Design of Metamaterials
• Freeform Diffractive Metagrating Design Based on Generative Adversarial Networks
• Intelligent Nanophotonics: Merging Photonics and Artificial Intelligence at the Nanoscale
• Deep learning meets nanophotonics: A generalized accurate predictor for near fields and far fields of arbitrary 3D nanostructures
• Topology Optimized Multi-layered Meta-optics
• Inverse designed metalenses with extended depth of focus

Cited by in corpus (12)

• Deep learning in nano-photonics: inverse design and beyond
• Global Inverse Design Across Multiple Photonic Structure Classes Using Generative Deep Learning
• Deep learning enabled design of complex transmission matrices for universal optical components
• Manifold Learning for Knowledge Discovery and Intelligent Inverse Design of Photonic Nanostructures: Breaking the Geometric Complexity
• Enhancing Adjoint Optimization-based Photonics Inverse Design with Explainable Machine Learning
• Machine-Learning-Assisted Photonic Device Development: A Multiscale Approach from Theory to Characterization
• Deep learning for nano-photonic materials -- The solution to everything!?
• Designing Multi-functional Metamaterials
• Dark soliton detection using persistent homology
• A deep learning approach for inverse design of the metasurface for dual-polarized waves
• The Impact of Feature Representation on the Accuracy of Photonic Neural Networks
• Deep learning estimation of complex reverberant wave fields by a programmable metasurface