The data-science revolution is poised to transform the way photonic systems are simulated and designed. Photonic systems are, in many ways, an ideal substrate for machine learning: the objective of much of computational electromagnetics is the capture of nonlinear relationships in high-dimensional spaces, which is the core strength of neural networks. Additionally, the mainstream availability of Maxwell solvers makes the training and evaluation of neural networks broadly accessible and tailorable to specific problems. In this Review, we show how deep neural networks, configured as discriminative networks, can learn from training sets and operate as high-speed surrogate electromagnetic solvers. We also examine how deep generative networks can learn geometric features in device distributions and even be configured to serve as robust global optimizers. Fundamental data-science concepts framed within the context of photonics are also discussed, including the network-training process, delineation of different network classes and architectures, and dimensionality reduction. Neural networks can capture nonlinear relationships in high-dimensional spaces and are powerful tools for photonic-system modelling. This Review discusses how deep neural networks can serve as surrogate electromagnetic solvers, inverse modelling tools and global device optimizers.

Deep neural networks for the evaluation and design of photonic devices

The data sciences revolution is poised to transform the way photonic systems are simulated and designed. Photonics are in many ways an ideal substrate for machine learning: the objective of much of computational electromagnetics is the capture of non-linear relationships in high dimensional spaces, which is the core strength of neural networks. Additionally, the mainstream availability of Maxwell solvers makes the training and evaluation of neural networks broadly accessible and tailorable to specific problems. In this Review, we will show how deep neural networks, configured as discriminative networks, can learn from training sets and operate as high-speed surrogate electromagnetic solvers. We will also examine how deep generative networks can learn geometric features in device distributions and even be configured to serve as robust global optimizers. Fundamental data sciences concepts framed within the context of photonics will also be discussed, including the network training process, delineation of different network classes and architectures, and dimensionality reduction.

Deep learning in the context of nano-photonics is mostly discussed in terms of its potential for inverse design of photonic devices or nano-structures. Many of the recent works on machine-learning inverse design are highly specific, and the drawbacks of the respective approaches are often not immediately clear. In this review we want therefore to provide a critical review on the capabilities of deep learning for inverse design and the progress which has been made so far. We classify the different deep-learning-based inverse design approaches at a higher level as well as by the context of their respective applications and critically discuss their strengths and weaknesses. While a significant part of the community’s attention lies on nano-photonic inverse design, deep learning has evolved as a tool for a large variety of applications. The second part of the review will focus therefore on machine learning research in nano-photonics “beyond inverse design.” This spans from physics-informed neural networks for tremendous acceleration of photonics simulations, over sparse data reconstruction, imaging and “knowledge discovery” to experimental applications.

/pdf/deep-learning-in-nano-photonics-inverse-design-and-beyond-4lpbfo8urm.pdf

Deep learning in nano-photonics: inverse design and beyond

Alloy modelling has a history of machine-learning-like approaches, preceding the tide of data-science-inspired work. The dawn of computational databases has made the integration of analysis, prediction and discovery the key theme in accelerated alloy research. Advances in machine-learning methods and enhanced data generation have created a fertile ground for computational materials science. Pairing machine learning and alloys has proven to be particularly instrumental in pushing progress in a wide variety of materials, including metallic glasses, high-entropy alloys, shape-memory alloys, magnets, superalloys, catalysts and structural materials. This Review examines the present state of machine-learning-driven alloy research, discusses the approaches and applications in the field and summarizes theoretical predictions and experimental validations. We foresee that the partnership between machine learning and alloys will lead to the design of new and improved systems. Machine learning is enabling a metallurgical renaissance. This Review discusses recent progress in representations, descriptors and interatomic potentials, overviewing metallic glasses, high-entropy alloys, superalloys and shape-memory alloys, magnets and catalysts, and the prediction of mechanical and thermal properties.

Machine learning for alloys

The growing maturity of nanofabrication has ushered massive sophisticated optical structures available on a photonic chip. The integration of subwavelength-structured metasurfaces and metamaterials on the canonical building block of optical waveguides is gradually reshaping the landscape of photonic integrated circuits, giving rise to numerous meta-waveguides with unprecedented strength in controlling guided electromagnetic waves. Here, we review recent advances in meta-structured waveguides that synergize various functional subwavelength photonic architectures with diverse waveguide platforms, such as dielectric or plasmonic waveguides and optical fibers. Foundational results and representative applications are comprehensively summarized. Brief physical models with explicit design tutorials, either physical intuition-based design methods or computer algorithms-based inverse designs, are cataloged as well. We highlight how meta-optics can infuse new degrees of freedom to waveguide-based devices and systems, by enhancing light-matter interaction strength to drastically boost device performance, or offering a versatile designer media for manipulating light in nanoscale to enable novel functionalities. We further discuss current challenges and outline emerging opportunities of this vibrant field for various applications in photonic integrated circuits, biomedical sensing, artificial intelligence and beyond.

Optical meta-waveguides for integrated photonics and beyond.

Inverse design algorithms are the basis for realizing high-performance, freeform nanophotonic devices. Current methods to enforce geometric constraints, such as practical fabrication constraints, a...

Mingkun Chen

Papers

Deep neural networks for the evaluation and design of photonic devices

Deep neural networks for the evaluation and design of photonic devices

Design Space Reparameterization Enforces Hard Geometric Constraints in Inverse-Designed Nanophotonic Devices

Thermodynamics analysis and temperature response mechanism during methane hydrate production by depressurization

High Speed Simulation and Freeform Optimization of Nanophotonic Devices with Physics-Augmented Deep Learning