Machine-Learning-Assisted Photonic Device Development: A Multiscale Approach from Theory to Characterization

Abstract

Photonic device development (PDD) has achieved remarkable success in designing and implementing new devices for controlling light across various wavelengths, scales, and applications, including telecommunications, imaging, sensing, and quantum information processing. PDD is an iterative, five-step process that consists of: i) deriving device behavior from design parameters, ii) simulating device performance, iii) finding the optimal candidate designs from simulations, iv) fabricating the optimal device, and v) measuring device performance. Classically, all these steps involve Bayesian optimization, material science, control theory, and direct physics-driven numerical methods. However, many of these techniques are computationally intractable, monetarily costly, or difficult to implement at scale. In addition, PDD suffers from large optimization landscapes, uncertainties in structural or optical characterization, and difficulties in implementing robust fabrication processes. However, the advent of machine learning over the past decade has provided novel, data-driven strategies for tackling these challenges, including surrogate estimators for speeding up computations, generative modeling for noisy measurement modeling and data augmentation, reinforcement learning for fabrication, and active learning for experimental physical discovery. In this review, we present a comprehensive perspective on these methods to enable machine-learning-assisted PDD (ML-PDD) for efficient design optimization with powerful generative models, fast simulation and characterization modeling under noisy measurements, and reinforcement learning for fabrication. This review will provide researchers from diverse backgrounds with valuable insights into this emerging topic, fostering interdisciplinary efforts to accelerate the development of complex photonic devices and systems.

References in corpus (61)

• Adam: A Method for Stochastic Optimization
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Generative Adversarial Networks
• Diffusion Models Beat GANs on Image Synthesis
• Outlook for inverse design in nanophotonics
• Photonics for artificial intelligence and neuromorphic computing
• Deep Unsupervised Learning using Nonequilibrium Thermodynamics
• Training deep neural networks for the inverse design of nanophotonic structures
• Fourier Neural Operator for Parametric Partial Differential Equations
• A Generative Model for Inverse Design of Metamaterials
• Quantum error correction below the surface code threshold
• Physics-informed neural networks for inverse problems in nano-optics and metamaterials
• Photonic quantum information processing: a review
• Deep neural networks for the evaluation and design of photonic devices
• Deep learning in nano-photonics: inverse design and beyond
• CT Super-resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble(GAN-CIRCLE)
• Global optimization of dielectric metasurfaces using a physics-driven neural network
• High-threshold and low-overhead fault-tolerant quantum memory
• A universal 3D imaging sensor on a silicon photonics platform
• Deep Generative Modeling for Mechanistic-based Learning and Design of Metamaterial Systems
• Adjoint method and inverse design for nonlinear nanophotonic devices
• Nanophotonic Computational Design
• Deep learning meets nanophotonics: A generalized accurate predictor for near fields and far fields of arbitrary 3D nanostructures
• Inverse design in photonics by topology optimization: tutorial
• Machine-Learning-Assisted Metasurface Design for High-Efficiency Thermal Emitter Optimization
• Interpretable Machine Learning for Science with PySR and SymbolicRegression.jl
• Expanding the horizon of automated metamaterials discovery via quantum annealing
• Simulator-based training of generative models for the inverse design of metasurfaces
• Misalignment Resilient Diffractive Optical Networks
• Robust topology optimization of three-dimensional photonic-crystal band-gap structures
• Understanding Diffusion Models: A Unified Perspective
• Elucidating the Behavior of Nanophotonic Structures Through Explainable Machine Learning Algorithms
• Biomimetic Ultra-Broadband Perfect Absorbers Optimised with Reinforcement Learning
• Quantum-enhanced Markov chain Monte Carlo
• Physics-informed neural networks for imaging and parameter retrieval of photonic nanostructures from near-field data
• Learning Parameters and Constitutive Relationships with Physics Informed Deep Neural Networks
• Diffusion Probabilistic Model Based Accurate and High-Degree-of-Freedom Metasurface Inverse Design
• Hypothesis Learning in Automated Experiment: Application to Combinatorial Materials Libraries
• Stabilizing Generative Adversarial Networks: A Survey
• Multi-objective and categorical global optimization of photonic structures based on ResNet generative neural networks
• Bayesian optimization with experimental failure for high-throughput materials growth
• A topological encoding method for data-driven photonics inverse design
• Rapid classification of quantum sources enabled by machine learning
• METASET: Exploring Shape and Property Spaces for Data-Driven Metamaterials Design
• Enhancing Adjoint Optimization-based Photonics Inverse Design with Explainable Machine Learning
• Modeling Sparse Deviations for Compressed Sensing using Generative Models
• Machine Learning Framework for Quantum Sampling of Highly-Constrained, Continuous Optimization Problems
• Generating Multivariate Load States Using a Conditional Variational Autoencoder
• Style2Fab: Functionality-Aware Segmentation for Fabricating Personalized 3D Models with Generative AI
• Inverse Design of Grating Couplers Using the Policy Gradient Method from Reinforcement Learning
• Towards optimization of photonic-crystal surface-emitting lasers via quantum annealing
• Physics-informed reinforcement learning for sample-efficient optimization of freeform nanophotonic devices
• Autonomous scanning probe microscopy with hypothesis learning: Exploring the physics of domain switching in ferroelectric materials
• Materials Discovery with Extreme Properties via Reinforcement Learning-Guided Combinatorial Chemistry
• Reinforcement Learning for Photonic Component Design
• An Overview of Diffusion Models: Applications, Guided Generation, Statistical Rates and Optimization
• NeurOLight: A Physics-Agnostic Neural Operator Enabling Parametric Photonic Device Simulation
• Co-orchestration of Multiple Instruments to Uncover Structure-Property Relationships in Combinatorial Libraries
• Non-native Quantum Generative Optimization with Adversarial Autoencoders
• Fabrication-Aware Inverse Design For Shape Optimization
• PearSAN: A Machine Learning Method for Inverse Design using Pearson Correlated Surrogate Annealing