Inverse deep learning methods and benchmarks for artificial electromagnetic material design

Ren, Simiao; Mahendra, Ashwin M.; Khatib, Omar; Deng, Yang; Padilla, Willie J.; Malof, Jordan M.

doi:10.1039/d1nr08346e

Cited by 26 publications

(11 citation statements)

References 49 publications

(62 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This allows a trained system to be able to either analyze or generate structures without needing time-intensive numerical simulations. Different ML and ANN techniques, such as convolutional neural networks (CNNs), , deep neural networks (DNNs), , and generative adversarial networks (GANs) , have been explored for the forward − and inverse design ,,,− of nanophotonic structures. Moreover, recent works have investigated the use of pretrained networks − in photonic applications, showing the promise of transfer learning as well.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning in Interpolation and Extrapolation for Nanophotonic Inverse Design

Acharige

Johlin

2022

ACS Omega

View full text Add to dashboard Cite

The algorithmic design of nanophotonic structures promises to significantly improve the efficiency of nanophotonic components due to the strong dependence of electromagnetic function on geometry and the unintuitive connection between structure and response. Such approaches, however, can be highly computationally intensive and do not ensure a globally optimal solution. Recent theoretical results suggest that machine learning techniques could address these issues as they are capable of modeling the response of nanophotonic structures at orders of magnitude lower time per result. In this work, we explore the utilization of artificial neural network (ANN) techniques to improve the algorithmic design of simple absorbing nanophotonic structures. We show that different approaches show various aptitudes in interpolation versus extrapolation, as well as peak performances versus consistency. Combining ANNs with classical machine learning techniques can outperform some standard ANN techniques for forward design, both in terms of training speed and accuracy in interpolation, but extrapolative performance can suffer. Networks pretrained on general image classification perform well in predicting optical responses of both interpolative and extrapolative structures, with very little additional training time required. Furthermore, we show that traditional deep neural networks are able to perform significantly better in extrapolation than more complicated architectures using convolutional or autoencoder layers. Finally, we show that such networks are able to perform extrapolation tasks in structure generation to produce structures with spectral responses significantly outside those of the structures on which they are trained.

show abstract

Section: Introductionmentioning

confidence: 99%

Machine Learning in Interpolation and Extrapolation for Nanophotonic Inverse Design

Acharige

Johlin

2022

ACS Omega

View full text Add to dashboard Cite

show abstract

“…In general, adopting a probabilistic approach provides a more complete picture of all the possible solutions to an inverse design problem and how confident the algorithm is. Here we note that very recently the use of cINNs has been mentioned in the context of benchmarking different deep learning approaches to inverse models for designing artificial electromagnetic materials [41], but without considering multimodal device distributions. On a similar note, GANs have also been employed for inverse photonic design [10,17] but have not been thoroughly explored to generate distributions of devices in the context of generative modeling.…”

Section: Discussionmentioning

confidence: 99%

Tackling multimodal device distributions in inverse photonic design using invertible neural networks

Frising

Bravo‐Abad

Prins

2023

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

We show how conditional generative neural networks can be used to efficiently find nanophotonic devices with desired properties, also known as inverse photonic design. Machine learning has emerged as a promising approach to overcome limitations imposed by the dimensionality and topology of the parameter space. Importantly, traditional optimization routines assume an invertible mapping between the design parameters and response. However, different designs may have comparable or even identical performance confusing the optimization algorithm when performing inverse design. Our generative modeling approach provides the full distribution of possible solutions to the inverse design problem, including multiple solutions. We compare a commonly used conditional Variational Autoencoder (cVAE) and a conditional Invertible Neural Network (cINN) on a proof-of-principle nanophotonic problem, consisting in tailoring the transmission spectrum trough a metallic film milled by subwavelength indentations. We show how cINNs have superior flexibility compared to cVAEs when dealing with multimodal device distributions.

show abstract

“…Due to its self-invertible characteristics, the inverse design relies only on a single model. 41,42 In addition, the INNs can be trained with exact log-likelihood, which leads to better convergence and performance. 39 Further, we propose a novel prior reshaping (PR) method to explore the feasible design parameter space more efficiently, which can be adjusted freely with a hyperparameter τ without regenerating new data.…”

Section: Introductionmentioning

confidence: 99%

“…In recent literature, the normalizing flow architecture has also been termed invertible neural networks (INNs). , Although not new, NF is re-emerging as a generative method and is gaining significant attention in the machine learning community for its capacity to explicitly model probability distributions. Due to its self-invertible characteristics, the inverse design relies only on a single model. , In addition, the INNs can be trained with exact log-likelihood, which leads to better convergence and performance …”

Section: Introductionmentioning

confidence: 99%

Normalizing Flows for Efficient Inverse Design of Thermophotovoltaic Emitters

Yang

Fan

et al. 2023

ACS Photonics

Self Cite

View full text Add to dashboard Cite

Metasurfaces have shown flexibility in realizing various functionalities via shaping the geometry on the subwavelength scale. However, with increased design complexity, the flexibility makes the traditional paradigm based on expert knowledge less effective. Due to the ability to learn knowledge from raw data, deep-learning techniques have made remarkable progress in the automatic design of highperformance nanophotonic devices. However, deep-learning-based methods require a large amount of training data, which is very expensive for metasurface design. Therefore, there is still a need for efficient inverse design methods with lower data complexity and higher performance. In this Article, we modeled the inverse design problem as a probabilistic distribution learning problem and introduce normalizing flow as a flexible model to explicitly learn the distribution. To efficiently explore prior distributions without generating extra training data, we proposed a prior reshaping method that reweighs the original training data according to their fitness to the design target. The algorithm is implemented for designing niobium-based emitters in a GaSb thermophotovoltaic (TPV) cell, achieving an in-band emittance efficiency close to 99%. To further improve the data efficiency of inverse design, we explored the transfer learning ability of the proposed normalizing flow model. A new tungstenbased emitter for a GaInAsSb TPV cell was obtained with comparable performance using only 5% of data compared to the original design problem. The demonstrated approach is not only applicable to TPV device designs, but may also be used in various datadriven inverse design problems, such as artificially structured materials, synthetic materials, and mechanical devices.

show abstract

Inverse deep learning methods and benchmarks for artificial electromagnetic material design

Abstract: Solving inverse material design problems with deep learning: we compare eight deep learning models on three problems, identifying the best approaches and demonstrating that they are highly effective.

Cited by 26 publications

References 49 publications

Machine Learning in Interpolation and Extrapolation for Nanophotonic Inverse Design

Machine Learning in Interpolation and Extrapolation for Nanophotonic Inverse Design

Tackling multimodal device distributions in inverse photonic design using invertible neural networks

Normalizing Flows for Efficient Inverse Design of Thermophotovoltaic Emitters

Contact Info

Product

Resources

About