Predicting Laser-Induced Colors of Random Plasmonic Metasurfaces and Optimizing Image Multiplexing Using Deep Learning

Abstract

Structural colors of plasmonic metasurfaces have been promised to a strong technological impact thanks to their high brightness, durability, and dichroic properties. However, fabricating metasurfaces whose spatial distribution must be customized at each implementation and over large areas is still a challenge. Since the demonstration of printed image multiplexing on quasi-random plasmonic metasurfaces, laser processing appears as a promising technology to reach the right level of accuracy and versatility. The main limit comes from the absence of physical models to predict the optical properties that can emerge from the laser processing of metasurfaces in which random metallic nanostructures are characterized by their statistical properties. Here, we demonstrate that deep neural networks trained from experimental data can predict the spectra and colors of laser-induced plasmonic metasurfaces in various observation modes. With thousands of experimental data, produced in a rapid and efficient way, the training accuracy is better than the perceptual just noticeable change. This accuracy enables the use of the predicted continuous color charts to find solutions for printing multiplexed images. Our deep learning approach is validated by an experimental demonstration of laser-induced two-image multiplexing. This approach greatly improves the performance of the laser-processing technology for both printing color images and finding optimized parameters for multiplexing. The article also provides a simple mining algorithm for implementing multiplexing with multiple observation modes and colors from any printing technology. This study can improve the optimization of laser processes for high-end applications in security, entertainment, or data storage.

Recent progress on structural coloration

“…In order to achieve more extreme control over electromagnetic waves on metasurfaces, there have been many recent studies that introduce optimization algorithms and ML into the design of metasurfaces [154,[164][165][166][167][168][169][170] . Additionally, color itself is the perception of electromagnetic waves by the human visual system, where different spectra could be perceived as the same color.…”

Accurate prediction of the optical properties of nanoalloys with both plasmonic and magnetic elements

“…In nanoparticles (NPs) and nanostructures, conduction electrons can be excited also by electromagnetic radiation, leading to surface plasmons and localized surface plasmons (LSP) 1 , 2 . Over the last decades, plasmonics permeated a wide range of sectors with critical importance for future technological challenges, such as sensing 3 , 4 , photocatalysis 5 – 7 , sunlight conversion 8 , metamaterials 9 , nanomedicine 10 , nonlinear 11 and quantum 12 , 13 optics. Each of these applications has specific requirements that cannot be simultaneously fulfilled by a single material 14 – 16 .…”

Metal Nanopillar Arrays Fabricated with Moth-Eye Films for Adjustable Plasmonic Colors and Colorimetric Plasmonic Sensing

“…25−27 Nevertheless, the condition of the laser exposure has to be precisely controlled, and certain equipment is required. 28 For practical applications, large-area nanofabrication techniques based on nanoimprinting such as the roll-to-roll process are attractive. 29,30 Moth-eye films are industrially produced for optical antireflection.…”

“…However, the fabricable area of nanostructures is limited to a centimeter scale, and reproducibility is not sufficient in general. Laser writing is an effective way to fabricate metal nanostructures over a large area with controllability of the colors. − Nevertheless, the condition of the laser exposure has to be precisely controlled, and certain equipment is required …”