NEUTRON: Neural particle swarm optimization for material-aware inverse design of structural color

Wang, Haozhu; Guo, L. Jay

doi:10.1016/j.isci.2022.104339

Cited by 8 publications

(13 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Structural colors can be designed purely with dielectric materials though, as shown in our previous work. ,, They can also be designed with a dielectric layer overcoat to protect the thin metal layer . In fact, structural colors can utilize a variety of structures and materials, and machine learning can assist with the design automatically when a list of materials are provided. , Such a list can include criteria like thermal expansion matching and high-temperature stability.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Integrating Structural Colors with Additive Manufacturing Using Atomic Layer Deposition

Rorem

Cho

Farjam

et al. 2022

ACS Appl. Mater. Interfaces

Self Cite

View full text Add to dashboard Cite

We demonstrate tunable structural color patterns that span the visible spectrum using atomic layer deposition (ALD). Asymmetric metal–dielectric–metal structures were sequentially deposited with nickel, zinc oxide, and a thin copper layer to form an optical cavity. The color response was precisely adjusted by tuning the zinc oxide (ZnO) thickness using ALD, which was consistent with model predictions. Owing to the conformal nature of ALD, this allows for uniform and tunable coloration of non-planar three-dimensional (3D) objects, as exemplified by adding color to 3D-printed parts produced by metal additive manufacturing. Proper choice of inorganic layered structures and materials allows the structural color to be stable at elevated temperatures, in contrast to traditional paints. To print multiple colors on a single sample, polymer inhibitors were patterned in a desired geometry using electrohydrodynamic jet (e-jet) printing, followed by area-selective ALD in the unpassivated regions. The ability to achieve 3D color printing, both at the micro- and macroscales, provides a new pathway to tune the optical and aesthetic properties during additive manufacturing.

show abstract

Section: Discussionmentioning

confidence: 99%

“…68 In fact, structural colors can utilize a variety of structures and materials, 10 and machine learning can assist with the design automatically when a list of materials are provided. 69,70 Such a list can include criteria like thermal expansion matching and high-temperature stability.…”

Section: ■ Conclusionmentioning

confidence: 99%

Integrating Structural Colors with Additive Manufacturing Using Atomic Layer Deposition

Rorem

Cho

Farjam

et al. 2022

ACS Appl. Mater. Interfaces

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this inverse design problem, our target is to produce the same reflection spectrum as that of chrome-coated objects. The method is generally applicable to generate a multilayer structure to produce any target optical response, 27 an example of which is provided in the Supporting Information (Figure S1 shows a replacement structure that can produce the same reflection spectrum as that of gold). We begin by initializing the algorithm with the target reflectance spectrum of the coating that we are interested in replicating.…”

Section: ■ Methodsmentioning

confidence: 99%

“…A few of these structures have been shown in the Supporting Information (Figure S3), and some can be found in our previous work. 27 Of these, we chose structure 1 and structure 2 for fabrication and demonstration in this work for two primary reasons: ease of availability of the materials and the ability to complete the fabrication in one evaporation chamber. We picked structures with materials that were readily available in the same evaporator in our cleanroom facility to minimize the workflow transitions between multiple chambers.…”

Section: ■ Experimental Methodsmentioning

confidence: 99%

“…Additionally, as the number of layers in the design increases, the search space for the structures increases exponentially, which makes the search for good designs inefficient and challenging. Recently, many machine learning-based methods have been proposed that demonstrate good performance for inverse design. − In this work, we use a reinforcement learning (RL) algorithm that we developed previously: Optical MultiLayer-Proximal Policy Optimization (OML-PPO), which learns from its past results when searching within a large space.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Environmentally Sustainable and Multifunctional Chrome-like Coatings Having No Chromium Designed with Reinforcement Learning

Saha

Wang

et al. 2023

ACS Appl. Mater. Interfaces

Self Cite

View full text Add to dashboard Cite

Decorative chrome plating (DCP) continues to be ubiquitous in creating highly appealing metal finishings and coatings, beating out other organic dye-based finishes. However, the hazardous chrome plating process is fraught with adverse health effects for the workers involved and causes significant environmental damage. In this work, we present a multilayer thin film structure to mimic the chrome appearance. To find a design efficiently, we employ a reinforcement learning (RL) algorithm to perform an automatic inverse design. This results in structures composed of environmentally friendly materials that not only have the chrome color but can also achieve additional functions beyond decoration. As an example, one structure is designed to have high transmission in the radio frequency regime, a property that general metals cannot have, which can broaden the decorative chrome applications to include microwave operating devices. The experimental structures are fabricated by physical vapor deposition to demonstrate the indistinguishable chrome color and validate the effectiveness of the RL inverse design approach.

show abstract

Inverse Design of Plasmonic Nanohole Arrays by Combing Spectra and Structural Color in Deep Learning

Zhang

Zhao

et al. 2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

Herein, deep learning (DL) is used to predict the structural parameters of Ag nanohole arrays (NAs) for spectrum‐driving and color‐driving plasmonic applications. A dataset of transmission spectra and structural parameters of NAs is generated using finite‐difference time‐domain (FDTD) calculations and is converted to vivid structural colors using the corresponding transmission spectrum. A bidirectional neural network is used to train the transmission spectrum and structural color together. The accuracy of predicting the structural parameters using a desired spectrum is tested and found to be up to 0.99, with a determination coefficient of reproducing the desired spectrum and color to be 0.97 and 0.96, respectively. These values are higher compared to those when only training for spectrum, but requiring less training time. This strategy is able to inverse design the NAs in less than 1 s to maximize surface‐enhanced Raman scattering (SERS) enhancement by matching transmission resonance and laser excitation wavelength, and accurately regenerate colored images in 7.5 s, allowing for nanoscale printing at a resolution of approximately 100 000 dots in−1. This work has important implications for the efficient design of nanostructures for various plasmonic applications, such as plasmonic sensors, optical filters, metal‐enhanced fluorescence, SERS, and super‐resolution displays.

show abstract

NEUTRON: Neural particle swarm optimization for material-aware inverse design of structural color

Cited by 8 publications

References 36 publications

Integrating Structural Colors with Additive Manufacturing Using Atomic Layer Deposition

Integrating Structural Colors with Additive Manufacturing Using Atomic Layer Deposition

Environmentally Sustainable and Multifunctional Chrome-like Coatings Having No Chromium Designed with Reinforcement Learning

Inverse Design of Plasmonic Nanohole Arrays by Combing Spectra and Structural Color in Deep Learning

Contact Info

Product

Resources

About